Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- reward/IP_checkpoints/blip_checkpoints/animate_recoginzer.pth +3 -0
- reward/IP_checkpoints/grouding-dino-base/.gitattributes +35 -0
- reward/IP_checkpoints/grouding-dino-base/README.md +69 -0
- reward/IP_checkpoints/grouding-dino-base/config.json +81 -0
- reward/IP_checkpoints/grouding-dino-base/model.safetensors +3 -0
- reward/IP_checkpoints/grouding-dino-base/preprocessor_config.json +25 -0
- reward/IP_checkpoints/grouding-dino-base/pytorch_model.bin +3 -0
- reward/IP_checkpoints/grouding-dino-base/special_tokens_map.json +7 -0
- reward/IP_checkpoints/grouding-dino-base/tokenizer.json +0 -0
- reward/IP_checkpoints/grouding-dino-base/tokenizer_config.json +56 -0
- reward/IP_checkpoints/grouding-dino-base/vocab.txt +0 -0
- reward/IP_checkpoints/sam2_checkpoints/sam2.1_hiera_base_plus.pt +3 -0
- reward/videos.tar.gz +3 -0
- reward/weights/Pretrain_humangt_meanvideo_trainset_wGT/checkpoint_06.pth +3 -0
- reward/weights/Pretrain_text_humangt_meanvideo_trainset_wGT_random_samescore/checkpoint_05.pth +3 -0
- reward/weights/bert-base-uncased/.gitattributes +11 -0
- reward/weights/bert-base-uncased/LICENSE +201 -0
- reward/weights/bert-base-uncased/README.md +251 -0
- reward/weights/bert-base-uncased/config.json +23 -0
- reward/weights/bert-base-uncased/coreml/fill-mask/float32_model.mlpackage/Data/com.apple.CoreML/model.mlmodel +3 -0
- reward/weights/bert-base-uncased/coreml/fill-mask/float32_model.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
- reward/weights/bert-base-uncased/coreml/fill-mask/float32_model.mlpackage/Manifest.json +18 -0
- reward/weights/bert-base-uncased/flax_model.msgpack +3 -0
- reward/weights/bert-base-uncased/model.onnx +3 -0
- reward/weights/bert-base-uncased/model.safetensors +3 -0
- reward/weights/bert-base-uncased/pytorch_model.bin +3 -0
- reward/weights/bert-base-uncased/rust_model.ot +3 -0
- reward/weights/bert-base-uncased/tf_model.h5 +3 -0
- reward/weights/bert-base-uncased/tokenizer.json +0 -0
- reward/weights/bert-base-uncased/tokenizer_config.json +1 -0
- reward/weights/bert-base-uncased/vocab.txt +0 -0
- reward/weights/copy_data.sh +25 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/added_tokens.json +5 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/chat_template.json +3 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/config.json +241 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/generation_config.json +18 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00001-of-00004.safetensors +3 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00002-of-00004.safetensors +3 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00003-of-00004.safetensors +3 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00004-of-00004.safetensors +3 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model.safetensors.index.json +771 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/preprocessor_config.json +26 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/processor_config.json +4 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/special_tokens_map.json +53 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/tokenizer.json +0 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/tokenizer.model +3 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/tokenizer_config.json +73 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/training_args.bin +3 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-quality_4096_regression/checkpoint-final/added_tokens.json +5 -0
- reward/weights/mantis-8b-idefics2-video-eval-24frame-quality_4096_regression/checkpoint-final/chat_template.json +3 -0
reward/IP_checkpoints/blip_checkpoints/animate_recoginzer.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35b62d1b0178fa679e58a1394521fc29a5b25fd9e096b190679710122d5cd41c
|
| 3 |
+
size 7598749375
|
reward/IP_checkpoints/grouding-dino-base/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
reward/IP_checkpoints/grouding-dino-base/README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- vision
|
| 5 |
+
inference: false
|
| 6 |
+
pipeline_tag: zero-shot-object-detection
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Grounding DINO model (base variant)
|
| 10 |
+
|
| 11 |
+
The Grounding DINO model was proposed in [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://arxiv.org/abs/2303.05499) by Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang. Grounding DINO extends a closed-set object detection model with a text encoder, enabling open-set object detection. The model achieves remarkable results, such as 52.5 AP on COCO zero-shot.
|
| 12 |
+
|
| 13 |
+
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/grouding_dino_architecture.png"
|
| 14 |
+
alt="drawing" width="600"/>
|
| 15 |
+
|
| 16 |
+
<small> Grounding DINO overview. Taken from the <a href="https://arxiv.org/abs/2303.05499">original paper</a>. </small>
|
| 17 |
+
|
| 18 |
+
## Intended uses & limitations
|
| 19 |
+
|
| 20 |
+
You can use the raw model for zero-shot object detection (the task of detecting things in an image out-of-the-box without labeled data).
|
| 21 |
+
|
| 22 |
+
### How to use
|
| 23 |
+
|
| 24 |
+
Here's how to use the model for zero-shot object detection:
|
| 25 |
+
|
| 26 |
+
```python
|
| 27 |
+
import requests
|
| 28 |
+
|
| 29 |
+
import torch
|
| 30 |
+
from PIL import Image
|
| 31 |
+
from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection
|
| 32 |
+
|
| 33 |
+
model_id = "IDEA-Research/grounding-dino-base"
|
| 34 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 35 |
+
|
| 36 |
+
processor = AutoProcessor.from_pretrained(model_id)
|
| 37 |
+
model = AutoModelForZeroShotObjectDetection.from_pretrained(model_id).to(device)
|
| 38 |
+
|
| 39 |
+
image_url = "http://images.cocodataset.org/val2017/000000039769.jpg"
|
| 40 |
+
image = Image.open(requests.get(image_url, stream=True).raw)
|
| 41 |
+
# Check for cats and remote controls
|
| 42 |
+
# VERY important: text queries need to be lowercased + end with a dot
|
| 43 |
+
text = "a cat. a remote control."
|
| 44 |
+
|
| 45 |
+
inputs = processor(images=image, text=text, return_tensors="pt").to(device)
|
| 46 |
+
with torch.no_grad():
|
| 47 |
+
outputs = model(**inputs)
|
| 48 |
+
|
| 49 |
+
results = processor.post_process_grounded_object_detection(
|
| 50 |
+
outputs,
|
| 51 |
+
inputs.input_ids,
|
| 52 |
+
box_threshold=0.4,
|
| 53 |
+
text_threshold=0.3,
|
| 54 |
+
target_sizes=[image.size[::-1]]
|
| 55 |
+
)
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
### BibTeX entry and citation info
|
| 59 |
+
|
| 60 |
+
```bibtex
|
| 61 |
+
@misc{liu2023grounding,
|
| 62 |
+
title={Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection},
|
| 63 |
+
author={Shilong Liu and Zhaoyang Zeng and Tianhe Ren and Feng Li and Hao Zhang and Jie Yang and Chunyuan Li and Jianwei Yang and Hang Su and Jun Zhu and Lei Zhang},
|
| 64 |
+
year={2023},
|
| 65 |
+
eprint={2303.05499},
|
| 66 |
+
archivePrefix={arXiv},
|
| 67 |
+
primaryClass={cs.CV}
|
| 68 |
+
}
|
| 69 |
+
```
|
reward/IP_checkpoints/grouding-dino-base/config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "relu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GroundingDinoForObjectDetection"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auxiliary_loss": false,
|
| 9 |
+
"backbone": null,
|
| 10 |
+
"backbone_config": {
|
| 11 |
+
"depths": [
|
| 12 |
+
2,
|
| 13 |
+
2,
|
| 14 |
+
18,
|
| 15 |
+
2
|
| 16 |
+
],
|
| 17 |
+
"embed_dim": 128,
|
| 18 |
+
"hidden_size": 1024,
|
| 19 |
+
"image_size": 384,
|
| 20 |
+
"model_type": "swin",
|
| 21 |
+
"num_heads": [
|
| 22 |
+
4,
|
| 23 |
+
8,
|
| 24 |
+
16,
|
| 25 |
+
32
|
| 26 |
+
],
|
| 27 |
+
"out_features": [
|
| 28 |
+
"stage2",
|
| 29 |
+
"stage3",
|
| 30 |
+
"stage4"
|
| 31 |
+
],
|
| 32 |
+
"out_indices": [
|
| 33 |
+
2,
|
| 34 |
+
3,
|
| 35 |
+
4
|
| 36 |
+
],
|
| 37 |
+
"window_size": 12
|
| 38 |
+
},
|
| 39 |
+
"backbone_kwargs": null,
|
| 40 |
+
"bbox_cost": 5.0,
|
| 41 |
+
"bbox_loss_coefficient": 5.0,
|
| 42 |
+
"class_cost": 1.0,
|
| 43 |
+
"d_model": 256,
|
| 44 |
+
"decoder_attention_heads": 8,
|
| 45 |
+
"decoder_bbox_embed_share": true,
|
| 46 |
+
"decoder_ffn_dim": 2048,
|
| 47 |
+
"decoder_layers": 6,
|
| 48 |
+
"decoder_n_points": 4,
|
| 49 |
+
"disable_custom_kernels": false,
|
| 50 |
+
"dropout": 0.1,
|
| 51 |
+
"embedding_init_target": true,
|
| 52 |
+
"encoder_attention_heads": 8,
|
| 53 |
+
"encoder_ffn_dim": 2048,
|
| 54 |
+
"encoder_layers": 6,
|
| 55 |
+
"encoder_n_points": 4,
|
| 56 |
+
"focal_alpha": 0.25,
|
| 57 |
+
"fusion_dropout": 0.0,
|
| 58 |
+
"fusion_droppath": 0.1,
|
| 59 |
+
"giou_cost": 2.0,
|
| 60 |
+
"giou_loss_coefficient": 2.0,
|
| 61 |
+
"init_std": 0.02,
|
| 62 |
+
"is_encoder_decoder": true,
|
| 63 |
+
"layer_norm_eps": 1e-05,
|
| 64 |
+
"max_text_len": 256,
|
| 65 |
+
"model_type": "grounding-dino",
|
| 66 |
+
"num_feature_levels": 4,
|
| 67 |
+
"num_queries": 900,
|
| 68 |
+
"position_embedding_type": "sine",
|
| 69 |
+
"positional_embedding_temperature": 20,
|
| 70 |
+
"query_dim": 4,
|
| 71 |
+
"text_config": {
|
| 72 |
+
"model_type": "bert"
|
| 73 |
+
},
|
| 74 |
+
"text_enhancer_dropout": 0.0,
|
| 75 |
+
"torch_dtype": "float32",
|
| 76 |
+
"transformers_version": "4.40.0.dev0",
|
| 77 |
+
"two_stage": true,
|
| 78 |
+
"two_stage_bbox_embed_share": false,
|
| 79 |
+
"use_pretrained_backbone": false,
|
| 80 |
+
"use_timm_backbone": false
|
| 81 |
+
}
|
reward/IP_checkpoints/grouding-dino-base/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5548f844c928c4b6f411fa8cbcc2bfa8dbbba437cb1d513975519f93c2a9ed21
|
| 3 |
+
size 933400872
|
reward/IP_checkpoints/grouding-dino-base/preprocessor_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_pad": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"format": "coco_detection",
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.485,
|
| 9 |
+
0.456,
|
| 10 |
+
0.406
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "GroundingDinoImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.229,
|
| 15 |
+
0.224,
|
| 16 |
+
0.225
|
| 17 |
+
],
|
| 18 |
+
"processor_class": "GroundingDinoProcessor",
|
| 19 |
+
"resample": 2,
|
| 20 |
+
"rescale_factor": 0.00392156862745098,
|
| 21 |
+
"size": {
|
| 22 |
+
"longest_edge": 1333,
|
| 23 |
+
"shortest_edge": 800
|
| 24 |
+
}
|
| 25 |
+
}
|
reward/IP_checkpoints/grouding-dino-base/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b51daf2969525a12df8f074b1f6084a69cd2796a565396ea1f4dfb7e5431aaa
|
| 3 |
+
size 936002005
|
reward/IP_checkpoints/grouding-dino-base/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
reward/IP_checkpoints/grouding-dino-base/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
reward/IP_checkpoints/grouding-dino-base/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"processor_class": "GroundingDinoProcessor",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
reward/IP_checkpoints/grouding-dino-base/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
reward/IP_checkpoints/sam2_checkpoints/sam2.1_hiera_base_plus.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2345aede8715ab1d5d31b4a509fb160c5a4af1970f199d9054ccfb746c004c5
|
| 3 |
+
size 323606802
|
reward/videos.tar.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08934173928d2977c63fb40ab55eadb3301411e3d71980addccae67889148481
|
| 3 |
+
size 1168654580
|
reward/weights/Pretrain_humangt_meanvideo_trainset_wGT/checkpoint_06.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ce8fe6358b0b99f7eb1f3040f977a6112dcbdf5b73d8da500903d2da0fa8bcd
|
| 3 |
+
size 1043975114
|
reward/weights/Pretrain_text_humangt_meanvideo_trainset_wGT_random_samescore/checkpoint_05.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f245d7a26cca519d30d317255d613645130ef732ad214dba944d770d971df20
|
| 3 |
+
size 2464452159
|
reward/weights/bert-base-uncased/.gitattributes
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
reward/weights/bert-base-uncased/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
| 178 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 179 |
+
|
| 180 |
+
To apply the Apache License to your work, attach the following
|
| 181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 182 |
+
replaced with your own identifying information. (Don't include
|
| 183 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 184 |
+
comment syntax for the file format. We also recommend that a
|
| 185 |
+
file or class name and description of purpose be included on the
|
| 186 |
+
same "printed page" as the copyright notice for easier
|
| 187 |
+
identification within third-party archives.
|
| 188 |
+
|
| 189 |
+
Copyright [yyyy] [name of copyright owner]
|
| 190 |
+
|
| 191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 192 |
+
you may not use this file except in compliance with the License.
|
| 193 |
+
You may obtain a copy of the License at
|
| 194 |
+
|
| 195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 196 |
+
|
| 197 |
+
Unless required by applicable law or agreed to in writing, software
|
| 198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 200 |
+
See the License for the specific language governing permissions and
|
| 201 |
+
limitations under the License.
|
reward/weights/bert-base-uncased/README.md
ADDED
|
@@ -0,0 +1,251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
tags:
|
| 4 |
+
- exbert
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
datasets:
|
| 7 |
+
- bookcorpus
|
| 8 |
+
- wikipedia
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# BERT base model (uncased)
|
| 12 |
+
|
| 13 |
+
Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
|
| 14 |
+
[this paper](https://arxiv.org/abs/1810.04805) and first released in
|
| 15 |
+
[this repository](https://github.com/google-research/bert). This model is uncased: it does not make a difference
|
| 16 |
+
between english and English.
|
| 17 |
+
|
| 18 |
+
Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by
|
| 19 |
+
the Hugging Face team.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
|
| 24 |
+
was pretrained on the raw texts only, with no humans labeling them in any way (which is why it can use lots of
|
| 25 |
+
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
|
| 26 |
+
was pretrained with two objectives:
|
| 27 |
+
|
| 28 |
+
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
|
| 29 |
+
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
|
| 30 |
+
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
|
| 31 |
+
GPT which internally masks the future tokens. It allows the model to learn a bidirectional representation of the
|
| 32 |
+
sentence.
|
| 33 |
+
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
|
| 34 |
+
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
|
| 35 |
+
predict if the two sentences were following each other or not.
|
| 36 |
+
|
| 37 |
+
This way, the model learns an inner representation of the English language that can then be used to extract features
|
| 38 |
+
useful for downstream tasks: if you have a dataset of labeled sentences, for instance, you can train a standard
|
| 39 |
+
classifier using the features produced by the BERT model as inputs.
|
| 40 |
+
|
| 41 |
+
## Model variations
|
| 42 |
+
|
| 43 |
+
BERT has originally been released in base and large variations, for cased and uncased input text. The uncased models also strips out an accent markers.
|
| 44 |
+
Chinese and multilingual uncased and cased versions followed shortly after.
|
| 45 |
+
Modified preprocessing with whole word masking has replaced subpiece masking in a following work, with the release of two models.
|
| 46 |
+
Other 24 smaller models are released afterward.
|
| 47 |
+
|
| 48 |
+
The detailed release history can be found on the [google-research/bert readme](https://github.com/google-research/bert/blob/master/README.md) on github.
|
| 49 |
+
|
| 50 |
+
| Model | #params | Language |
|
| 51 |
+
|------------------------|--------------------------------|-------|
|
| 52 |
+
| [`bert-base-uncased`](https://huggingface.co/bert-base-uncased) | 110M | English |
|
| 53 |
+
| [`bert-large-uncased`](https://huggingface.co/bert-large-uncased) | 340M | English | sub
|
| 54 |
+
| [`bert-base-cased`](https://huggingface.co/bert-base-cased) | 110M | English |
|
| 55 |
+
| [`bert-large-cased`](https://huggingface.co/bert-large-cased) | 340M | English |
|
| 56 |
+
| [`bert-base-chinese`](https://huggingface.co/bert-base-chinese) | 110M | Chinese |
|
| 57 |
+
| [`bert-base-multilingual-cased`](https://huggingface.co/bert-base-multilingual-cased) | 110M | Multiple |
|
| 58 |
+
| [`bert-large-uncased-whole-word-masking`](https://huggingface.co/bert-large-uncased-whole-word-masking) | 340M | English |
|
| 59 |
+
| [`bert-large-cased-whole-word-masking`](https://huggingface.co/bert-large-cased-whole-word-masking) | 340M | English |
|
| 60 |
+
|
| 61 |
+
## Intended uses & limitations
|
| 62 |
+
|
| 63 |
+
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
|
| 64 |
+
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=bert) to look for
|
| 65 |
+
fine-tuned versions of a task that interests you.
|
| 66 |
+
|
| 67 |
+
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
|
| 68 |
+
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
|
| 69 |
+
generation you should look at model like GPT2.
|
| 70 |
+
|
| 71 |
+
### How to use
|
| 72 |
+
|
| 73 |
+
You can use this model directly with a pipeline for masked language modeling:
|
| 74 |
+
|
| 75 |
+
```python
|
| 76 |
+
>>> from transformers import pipeline
|
| 77 |
+
>>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
|
| 78 |
+
>>> unmasker("Hello I'm a [MASK] model.")
|
| 79 |
+
|
| 80 |
+
[{'sequence': "[CLS] hello i'm a fashion model. [SEP]",
|
| 81 |
+
'score': 0.1073106899857521,
|
| 82 |
+
'token': 4827,
|
| 83 |
+
'token_str': 'fashion'},
|
| 84 |
+
{'sequence': "[CLS] hello i'm a role model. [SEP]",
|
| 85 |
+
'score': 0.08774490654468536,
|
| 86 |
+
'token': 2535,
|
| 87 |
+
'token_str': 'role'},
|
| 88 |
+
{'sequence': "[CLS] hello i'm a new model. [SEP]",
|
| 89 |
+
'score': 0.05338378623127937,
|
| 90 |
+
'token': 2047,
|
| 91 |
+
'token_str': 'new'},
|
| 92 |
+
{'sequence': "[CLS] hello i'm a super model. [SEP]",
|
| 93 |
+
'score': 0.04667217284440994,
|
| 94 |
+
'token': 3565,
|
| 95 |
+
'token_str': 'super'},
|
| 96 |
+
{'sequence': "[CLS] hello i'm a fine model. [SEP]",
|
| 97 |
+
'score': 0.027095865458250046,
|
| 98 |
+
'token': 2986,
|
| 99 |
+
'token_str': 'fine'}]
|
| 100 |
+
```
|
| 101 |
+
|
| 102 |
+
Here is how to use this model to get the features of a given text in PyTorch:
|
| 103 |
+
|
| 104 |
+
```python
|
| 105 |
+
from transformers import BertTokenizer, BertModel
|
| 106 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
| 107 |
+
model = BertModel.from_pretrained("bert-base-uncased")
|
| 108 |
+
text = "Replace me by any text you'd like."
|
| 109 |
+
encoded_input = tokenizer(text, return_tensors='pt')
|
| 110 |
+
output = model(**encoded_input)
|
| 111 |
+
```
|
| 112 |
+
|
| 113 |
+
and in TensorFlow:
|
| 114 |
+
|
| 115 |
+
```python
|
| 116 |
+
from transformers import BertTokenizer, TFBertModel
|
| 117 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
| 118 |
+
model = TFBertModel.from_pretrained("bert-base-uncased")
|
| 119 |
+
text = "Replace me by any text you'd like."
|
| 120 |
+
encoded_input = tokenizer(text, return_tensors='tf')
|
| 121 |
+
output = model(encoded_input)
|
| 122 |
+
```
|
| 123 |
+
|
| 124 |
+
### Limitations and bias
|
| 125 |
+
|
| 126 |
+
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
|
| 127 |
+
predictions:
|
| 128 |
+
|
| 129 |
+
```python
|
| 130 |
+
>>> from transformers import pipeline
|
| 131 |
+
>>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
|
| 132 |
+
>>> unmasker("The man worked as a [MASK].")
|
| 133 |
+
|
| 134 |
+
[{'sequence': '[CLS] the man worked as a carpenter. [SEP]',
|
| 135 |
+
'score': 0.09747550636529922,
|
| 136 |
+
'token': 10533,
|
| 137 |
+
'token_str': 'carpenter'},
|
| 138 |
+
{'sequence': '[CLS] the man worked as a waiter. [SEP]',
|
| 139 |
+
'score': 0.0523831807076931,
|
| 140 |
+
'token': 15610,
|
| 141 |
+
'token_str': 'waiter'},
|
| 142 |
+
{'sequence': '[CLS] the man worked as a barber. [SEP]',
|
| 143 |
+
'score': 0.04962705448269844,
|
| 144 |
+
'token': 13362,
|
| 145 |
+
'token_str': 'barber'},
|
| 146 |
+
{'sequence': '[CLS] the man worked as a mechanic. [SEP]',
|
| 147 |
+
'score': 0.03788609802722931,
|
| 148 |
+
'token': 15893,
|
| 149 |
+
'token_str': 'mechanic'},
|
| 150 |
+
{'sequence': '[CLS] the man worked as a salesman. [SEP]',
|
| 151 |
+
'score': 0.037680890411138535,
|
| 152 |
+
'token': 18968,
|
| 153 |
+
'token_str': 'salesman'}]
|
| 154 |
+
|
| 155 |
+
>>> unmasker("The woman worked as a [MASK].")
|
| 156 |
+
|
| 157 |
+
[{'sequence': '[CLS] the woman worked as a nurse. [SEP]',
|
| 158 |
+
'score': 0.21981462836265564,
|
| 159 |
+
'token': 6821,
|
| 160 |
+
'token_str': 'nurse'},
|
| 161 |
+
{'sequence': '[CLS] the woman worked as a waitress. [SEP]',
|
| 162 |
+
'score': 0.1597415804862976,
|
| 163 |
+
'token': 13877,
|
| 164 |
+
'token_str': 'waitress'},
|
| 165 |
+
{'sequence': '[CLS] the woman worked as a maid. [SEP]',
|
| 166 |
+
'score': 0.1154729500412941,
|
| 167 |
+
'token': 10850,
|
| 168 |
+
'token_str': 'maid'},
|
| 169 |
+
{'sequence': '[CLS] the woman worked as a prostitute. [SEP]',
|
| 170 |
+
'score': 0.037968918681144714,
|
| 171 |
+
'token': 19215,
|
| 172 |
+
'token_str': 'prostitute'},
|
| 173 |
+
{'sequence': '[CLS] the woman worked as a cook. [SEP]',
|
| 174 |
+
'score': 0.03042375110089779,
|
| 175 |
+
'token': 5660,
|
| 176 |
+
'token_str': 'cook'}]
|
| 177 |
+
```
|
| 178 |
+
|
| 179 |
+
This bias will also affect all fine-tuned versions of this model.
|
| 180 |
+
|
| 181 |
+
## Training data
|
| 182 |
+
|
| 183 |
+
The BERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
|
| 184 |
+
unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
|
| 185 |
+
headers).
|
| 186 |
+
|
| 187 |
+
## Training procedure
|
| 188 |
+
|
| 189 |
+
### Preprocessing
|
| 190 |
+
|
| 191 |
+
The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
|
| 192 |
+
then of the form:
|
| 193 |
+
|
| 194 |
+
```
|
| 195 |
+
[CLS] Sentence A [SEP] Sentence B [SEP]
|
| 196 |
+
```
|
| 197 |
+
|
| 198 |
+
With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus, and in
|
| 199 |
+
the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
|
| 200 |
+
consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
|
| 201 |
+
"sentences" has a combined length of less than 512 tokens.
|
| 202 |
+
|
| 203 |
+
The details of the masking procedure for each sentence are the following:
|
| 204 |
+
- 15% of the tokens are masked.
|
| 205 |
+
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
|
| 206 |
+
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
|
| 207 |
+
- In the 10% remaining cases, the masked tokens are left as is.
|
| 208 |
+
|
| 209 |
+
### Pretraining
|
| 210 |
+
|
| 211 |
+
The model was trained on 4 cloud TPUs in Pod configuration (16 TPU chips total) for one million steps with a batch size
|
| 212 |
+
of 256. The sequence length was limited to 128 tokens for 90% of the steps and 512 for the remaining 10%. The optimizer
|
| 213 |
+
used is Adam with a learning rate of 1e-4, \\(\beta_{1} = 0.9\\) and \\(\beta_{2} = 0.999\\), a weight decay of 0.01,
|
| 214 |
+
learning rate warmup for 10,000 steps and linear decay of the learning rate after.
|
| 215 |
+
|
| 216 |
+
## Evaluation results
|
| 217 |
+
|
| 218 |
+
When fine-tuned on downstream tasks, this model achieves the following results:
|
| 219 |
+
|
| 220 |
+
Glue test results:
|
| 221 |
+
|
| 222 |
+
| Task | MNLI-(m/mm) | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE | Average |
|
| 223 |
+
|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
|
| 224 |
+
| | 84.6/83.4 | 71.2 | 90.5 | 93.5 | 52.1 | 85.8 | 88.9 | 66.4 | 79.6 |
|
| 225 |
+
|
| 226 |
+
|
| 227 |
+
### BibTeX entry and citation info
|
| 228 |
+
|
| 229 |
+
```bibtex
|
| 230 |
+
@article{DBLP:journals/corr/abs-1810-04805,
|
| 231 |
+
author = {Jacob Devlin and
|
| 232 |
+
Ming{-}Wei Chang and
|
| 233 |
+
Kenton Lee and
|
| 234 |
+
Kristina Toutanova},
|
| 235 |
+
title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language
|
| 236 |
+
Understanding},
|
| 237 |
+
journal = {CoRR},
|
| 238 |
+
volume = {abs/1810.04805},
|
| 239 |
+
year = {2018},
|
| 240 |
+
url = {http://arxiv.org/abs/1810.04805},
|
| 241 |
+
archivePrefix = {arXiv},
|
| 242 |
+
eprint = {1810.04805},
|
| 243 |
+
timestamp = {Tue, 30 Oct 2018 20:39:56 +0100},
|
| 244 |
+
biburl = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib},
|
| 245 |
+
bibsource = {dblp computer science bibliography, https://dblp.org}
|
| 246 |
+
}
|
| 247 |
+
```
|
| 248 |
+
|
| 249 |
+
<a href="https://huggingface.co/exbert/?model=bert-base-uncased">
|
| 250 |
+
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
|
| 251 |
+
</a>
|
reward/weights/bert-base-uncased/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"gradient_checkpointing": false,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "bert",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"position_embedding_type": "absolute",
|
| 19 |
+
"transformers_version": "4.6.0.dev0",
|
| 20 |
+
"type_vocab_size": 2,
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"vocab_size": 30522
|
| 23 |
+
}
|
reward/weights/bert-base-uncased/coreml/fill-mask/float32_model.mlpackage/Data/com.apple.CoreML/model.mlmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59ebda1b73ce46947d8e6be8b39f018aae7d6c4d5809537225fdaaadd940e993
|
| 3 |
+
size 164911
|
reward/weights/bert-base-uncased/coreml/fill-mask/float32_model.mlpackage/Data/com.apple.CoreML/weights/weight.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0c9f4914b4f0053785e96b8583cd59cda63c2f1b6e95a03970d772bf097e289
|
| 3 |
+
size 531833856
|
reward/weights/bert-base-uncased/coreml/fill-mask/float32_model.mlpackage/Manifest.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"fileFormatVersion": "1.0.0",
|
| 3 |
+
"itemInfoEntries": {
|
| 4 |
+
"9D749A46-ADA0-43CA-B5C2-8E722B91F41E": {
|
| 5 |
+
"author": "com.apple.CoreML",
|
| 6 |
+
"description": "CoreML Model Specification",
|
| 7 |
+
"name": "model.mlmodel",
|
| 8 |
+
"path": "com.apple.CoreML/model.mlmodel"
|
| 9 |
+
},
|
| 10 |
+
"D545B13F-2D5E-4CFB-BFF1-C10E9EFD70DA": {
|
| 11 |
+
"author": "com.apple.CoreML",
|
| 12 |
+
"description": "CoreML Model Weights",
|
| 13 |
+
"name": "weights",
|
| 14 |
+
"path": "com.apple.CoreML/weights"
|
| 15 |
+
}
|
| 16 |
+
},
|
| 17 |
+
"rootModelIdentifier": "9D749A46-ADA0-43CA-B5C2-8E722B91F41E"
|
| 18 |
+
}
|
reward/weights/bert-base-uncased/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea201fabe466ef7182f1f687fb5be4b62a73d3a78883f11264ff7f682cdb54bf
|
| 3 |
+
size 438064459
|
reward/weights/bert-base-uncased/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44d7a2896d341c51fb1eba89aea3a590e6af0ce33e25481136f7eeecb62e5f7f
|
| 3 |
+
size 532091246
|
reward/weights/bert-base-uncased/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68d45e234eb4a928074dfd868cead0219ab85354cc53d20e772753c6bb9169d3
|
| 3 |
+
size 440449768
|
reward/weights/bert-base-uncased/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:097417381d6c7230bd9e3557456d726de6e83245ec8b24f529f60198a67b203a
|
| 3 |
+
size 440473133
|
reward/weights/bert-base-uncased/rust_model.ot
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afd9aa425fd45c5655d3d43a0d041f9b76729bf475d6c017a0e9304a38f89972
|
| 3 |
+
size 534240408
|
reward/weights/bert-base-uncased/tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a17d6d844b5de815ccab5f42cad6d24496db3850a2a43d8258221018ce87d2
|
| 3 |
+
size 536063208
|
reward/weights/bert-base-uncased/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
reward/weights/bert-base-uncased/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "model_max_length": 512}
|
reward/weights/bert-base-uncased/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
reward/weights/copy_data.sh
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/chenbaoyou/work/ttv/vae/benchmark/videos/ogv/209258028_267845299-Scene-220.mp4 .
|
| 2 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/chenbaoyou/work/ttv/vae/benchmark/videos/ogv/ . --recursive
|
| 3 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/chenbaoyou/work/ttv/vae/benchmark/videos/kinetics/ kinetics --recursive
|
| 4 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/chenbaoyou/work/ttv/vae/benchmark/videos/panda/ panda --recursive
|
| 5 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/wuxiaoxuan/test_sub_data test_sub_data --recursive
|
| 6 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_data/wuyidi/annotate/ annotate --recursive
|
| 7 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_data/wuyidi/actionclip-traindata/ actionclip-traindata --recursive
|
| 8 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/chenbaoyou/dataset/ogv
|
| 9 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/xubaohan/video_generation/cogvideox_bilibili/data/animate_clip_0812_all_filter_cap_aes_flow_cm_motion35_6s.json .
|
| 10 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp dongman_0901_11w.json s3://cv_platform/seasonyang/data/caption_data/dongman_0901_11w.json
|
| 11 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp dongman_0901_42w.json s3://cv_platform/seasonyang/data/caption_data/dongman_0901_42w.json
|
| 12 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/yinmingyu/tmp/animate_clip_0812_all_filter_cap_aes_flow_cm_motion35_3s_new.json .
|
| 13 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/yinmingyu/tmp/animate_clip_0812_all_filter_cap_aes_flow_cm_motion35_new.json .
|
| 14 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/seasonyang/data/vae_eval_data_480p/ vae_eval_data_480p --recursive
|
| 15 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp eval_res s3://cv_platform/seasonyang/data/eval_res --recursive
|
| 16 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp benchmark_sample_200.csv s3://cv_platform/seasonyang/data/list/benchmark_sample_200.csv
|
| 17 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/yinmingyu/tmp/benckmark_1106/720/generated_v2 generated_v2 --recursive
|
| 18 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/yinmingyu/tmp/benckmark_1106/720/generated_v2 generated_v2 --recursive
|
| 19 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/xubaohan/video_generation/anisora_benchmark/checkpoints/Mantis-8B-Idefics2/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression --recursive
|
| 20 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/xubaohan/video_generation/anisora_benchmark/checkpoints/Mantis-8B-Idefics2/mantis-8b-idefics2-video-eval-24frame-quality_4096_regression mantis-8b-idefics2-video-eval-24frame-quality_4096_regression --recursive
|
| 21 |
+
aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/yinmingyu/DATA/workshop/personal/benchmark/BLIP/output/Pretrain_humangt_meanvideo_trainset_wGT Pretrain_humangt_meanvideo_trainset_wGT --recursive
|
| 22 |
+
aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/yinmingyu/DATA/workshop/personal/benchmark/BLIP/output/Pretrain_text_humangt_meanvideo_trainset_wGT_random_samescore Pretrain_text_humangt_meanvideo_trainset_wGT_random_samescore --recursive
|
| 23 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/wuxiaoxuan/train_datas train_data.json
|
| 24 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_platform/wuxiaoxuan/test_datas test_datas --recursive
|
| 25 |
+
#aws --endpoint-url=http://jssz-boss.bilibili.co s3 cp s3://cv_data/wuyidi/benchmark_semi_results/ benchmark_semi_results --recursive
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<end_of_utterance>": 32002,
|
| 3 |
+
"<fake_token_around_image>": 32000,
|
| 4 |
+
"<image>": 32001
|
| 5 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
|
| 3 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/DATA/bvac/personal/video_generation/benchmark/VideoScore/Mantis/mantis/Mantis-8B-Idefics2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Idefics2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"id2label": {
|
| 7 |
+
"0": "LABEL_0"
|
| 8 |
+
},
|
| 9 |
+
"image_token_id": 32001,
|
| 10 |
+
"label2id": {
|
| 11 |
+
"LABEL_0": 0
|
| 12 |
+
},
|
| 13 |
+
"model_type": "idefics2",
|
| 14 |
+
"perceiver_config": {
|
| 15 |
+
"_name_or_path": "",
|
| 16 |
+
"add_cross_attention": false,
|
| 17 |
+
"architectures": null,
|
| 18 |
+
"attention_dropout": 0.0,
|
| 19 |
+
"bad_words_ids": null,
|
| 20 |
+
"begin_suppress_tokens": null,
|
| 21 |
+
"bos_token_id": null,
|
| 22 |
+
"chunk_size_feed_forward": 0,
|
| 23 |
+
"cross_attention_hidden_size": null,
|
| 24 |
+
"decoder_start_token_id": null,
|
| 25 |
+
"diversity_penalty": 0.0,
|
| 26 |
+
"do_sample": false,
|
| 27 |
+
"early_stopping": false,
|
| 28 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 29 |
+
"eos_token_id": null,
|
| 30 |
+
"exponential_decay_length_penalty": null,
|
| 31 |
+
"finetuning_task": null,
|
| 32 |
+
"forced_bos_token_id": null,
|
| 33 |
+
"forced_eos_token_id": null,
|
| 34 |
+
"hidden_act": "silu",
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"is_decoder": false,
|
| 40 |
+
"is_encoder_decoder": false,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1
|
| 44 |
+
},
|
| 45 |
+
"length_penalty": 1.0,
|
| 46 |
+
"max_length": 20,
|
| 47 |
+
"min_length": 0,
|
| 48 |
+
"model_type": "idefics2",
|
| 49 |
+
"no_repeat_ngram_size": 0,
|
| 50 |
+
"num_beam_groups": 1,
|
| 51 |
+
"num_beams": 1,
|
| 52 |
+
"num_key_value_heads": 4,
|
| 53 |
+
"num_return_sequences": 1,
|
| 54 |
+
"output_attentions": false,
|
| 55 |
+
"output_hidden_states": false,
|
| 56 |
+
"output_scores": false,
|
| 57 |
+
"pad_token_id": null,
|
| 58 |
+
"prefix": null,
|
| 59 |
+
"problem_type": null,
|
| 60 |
+
"pruned_heads": {},
|
| 61 |
+
"remove_invalid_values": false,
|
| 62 |
+
"repetition_penalty": 1.0,
|
| 63 |
+
"resampler_depth": 3,
|
| 64 |
+
"resampler_head_dim": 96,
|
| 65 |
+
"resampler_n_heads": 16,
|
| 66 |
+
"resampler_n_latents": 64,
|
| 67 |
+
"return_dict": true,
|
| 68 |
+
"return_dict_in_generate": false,
|
| 69 |
+
"sep_token_id": null,
|
| 70 |
+
"suppress_tokens": null,
|
| 71 |
+
"task_specific_params": null,
|
| 72 |
+
"temperature": 1.0,
|
| 73 |
+
"tf_legacy_loss": false,
|
| 74 |
+
"tie_encoder_decoder": false,
|
| 75 |
+
"tie_word_embeddings": true,
|
| 76 |
+
"tokenizer_class": null,
|
| 77 |
+
"top_k": 50,
|
| 78 |
+
"top_p": 1.0,
|
| 79 |
+
"torch_dtype": null,
|
| 80 |
+
"torchscript": false,
|
| 81 |
+
"typical_p": 1.0,
|
| 82 |
+
"use_bfloat16": false
|
| 83 |
+
},
|
| 84 |
+
"problem_type": "regression",
|
| 85 |
+
"text_config": {
|
| 86 |
+
"_name_or_path": "",
|
| 87 |
+
"add_cross_attention": false,
|
| 88 |
+
"architectures": null,
|
| 89 |
+
"attention_dropout": 0.0,
|
| 90 |
+
"bad_words_ids": null,
|
| 91 |
+
"begin_suppress_tokens": null,
|
| 92 |
+
"bos_token_id": 1,
|
| 93 |
+
"chunk_size_feed_forward": 0,
|
| 94 |
+
"cross_attention_hidden_size": null,
|
| 95 |
+
"decoder_start_token_id": null,
|
| 96 |
+
"diversity_penalty": 0.0,
|
| 97 |
+
"do_sample": false,
|
| 98 |
+
"early_stopping": false,
|
| 99 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 100 |
+
"eos_token_id": 2,
|
| 101 |
+
"exponential_decay_length_penalty": null,
|
| 102 |
+
"finetuning_task": null,
|
| 103 |
+
"forced_bos_token_id": null,
|
| 104 |
+
"forced_eos_token_id": null,
|
| 105 |
+
"head_dim": 128,
|
| 106 |
+
"hidden_act": "silu",
|
| 107 |
+
"hidden_size": 4096,
|
| 108 |
+
"id2label": {
|
| 109 |
+
"0": "LABEL_0",
|
| 110 |
+
"1": "LABEL_1"
|
| 111 |
+
},
|
| 112 |
+
"initializer_range": 0.02,
|
| 113 |
+
"intermediate_size": 14336,
|
| 114 |
+
"is_decoder": false,
|
| 115 |
+
"is_encoder_decoder": false,
|
| 116 |
+
"label2id": {
|
| 117 |
+
"LABEL_0": 0,
|
| 118 |
+
"LABEL_1": 1
|
| 119 |
+
},
|
| 120 |
+
"length_penalty": 1.0,
|
| 121 |
+
"max_length": 20,
|
| 122 |
+
"max_position_embeddings": 32768,
|
| 123 |
+
"min_length": 0,
|
| 124 |
+
"model_type": "mistral",
|
| 125 |
+
"no_repeat_ngram_size": 0,
|
| 126 |
+
"num_attention_heads": 32,
|
| 127 |
+
"num_beam_groups": 1,
|
| 128 |
+
"num_beams": 1,
|
| 129 |
+
"num_hidden_layers": 32,
|
| 130 |
+
"num_key_value_heads": 8,
|
| 131 |
+
"num_return_sequences": 1,
|
| 132 |
+
"output_attentions": false,
|
| 133 |
+
"output_hidden_states": false,
|
| 134 |
+
"output_scores": false,
|
| 135 |
+
"pad_token_id": 0,
|
| 136 |
+
"prefix": null,
|
| 137 |
+
"problem_type": null,
|
| 138 |
+
"pruned_heads": {},
|
| 139 |
+
"remove_invalid_values": false,
|
| 140 |
+
"repetition_penalty": 1.0,
|
| 141 |
+
"return_dict": true,
|
| 142 |
+
"return_dict_in_generate": false,
|
| 143 |
+
"rms_norm_eps": 1e-05,
|
| 144 |
+
"rope_theta": 10000.0,
|
| 145 |
+
"sep_token_id": null,
|
| 146 |
+
"sliding_window": 4096,
|
| 147 |
+
"suppress_tokens": null,
|
| 148 |
+
"task_specific_params": null,
|
| 149 |
+
"temperature": 1.0,
|
| 150 |
+
"tf_legacy_loss": false,
|
| 151 |
+
"tie_encoder_decoder": false,
|
| 152 |
+
"tie_word_embeddings": false,
|
| 153 |
+
"tokenizer_class": null,
|
| 154 |
+
"top_k": 50,
|
| 155 |
+
"top_p": 1.0,
|
| 156 |
+
"torch_dtype": null,
|
| 157 |
+
"torchscript": false,
|
| 158 |
+
"typical_p": 1.0,
|
| 159 |
+
"use_bfloat16": false,
|
| 160 |
+
"use_cache": true,
|
| 161 |
+
"vocab_size": 32003
|
| 162 |
+
},
|
| 163 |
+
"tie_word_embeddings": false,
|
| 164 |
+
"torch_dtype": "bfloat16",
|
| 165 |
+
"transformers_version": "4.45.1",
|
| 166 |
+
"use_cache": true,
|
| 167 |
+
"vision_config": {
|
| 168 |
+
"_name_or_path": "",
|
| 169 |
+
"add_cross_attention": false,
|
| 170 |
+
"architectures": null,
|
| 171 |
+
"attention_dropout": 0.0,
|
| 172 |
+
"bad_words_ids": null,
|
| 173 |
+
"begin_suppress_tokens": null,
|
| 174 |
+
"bos_token_id": null,
|
| 175 |
+
"chunk_size_feed_forward": 0,
|
| 176 |
+
"cross_attention_hidden_size": null,
|
| 177 |
+
"decoder_start_token_id": null,
|
| 178 |
+
"diversity_penalty": 0.0,
|
| 179 |
+
"do_sample": false,
|
| 180 |
+
"early_stopping": false,
|
| 181 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 182 |
+
"eos_token_id": null,
|
| 183 |
+
"exponential_decay_length_penalty": null,
|
| 184 |
+
"finetuning_task": null,
|
| 185 |
+
"forced_bos_token_id": null,
|
| 186 |
+
"forced_eos_token_id": null,
|
| 187 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 188 |
+
"hidden_size": 1152,
|
| 189 |
+
"id2label": {
|
| 190 |
+
"0": "LABEL_0",
|
| 191 |
+
"1": "LABEL_1"
|
| 192 |
+
},
|
| 193 |
+
"image_size": 980,
|
| 194 |
+
"initializer_range": 0.02,
|
| 195 |
+
"intermediate_size": 4304,
|
| 196 |
+
"is_decoder": false,
|
| 197 |
+
"is_encoder_decoder": false,
|
| 198 |
+
"label2id": {
|
| 199 |
+
"LABEL_0": 0,
|
| 200 |
+
"LABEL_1": 1
|
| 201 |
+
},
|
| 202 |
+
"layer_norm_eps": 1e-06,
|
| 203 |
+
"length_penalty": 1.0,
|
| 204 |
+
"max_length": 20,
|
| 205 |
+
"min_length": 0,
|
| 206 |
+
"model_type": "idefics2",
|
| 207 |
+
"no_repeat_ngram_size": 0,
|
| 208 |
+
"num_attention_heads": 16,
|
| 209 |
+
"num_beam_groups": 1,
|
| 210 |
+
"num_beams": 1,
|
| 211 |
+
"num_channels": 3,
|
| 212 |
+
"num_hidden_layers": 27,
|
| 213 |
+
"num_return_sequences": 1,
|
| 214 |
+
"output_attentions": false,
|
| 215 |
+
"output_hidden_states": false,
|
| 216 |
+
"output_scores": false,
|
| 217 |
+
"pad_token_id": null,
|
| 218 |
+
"patch_size": 14,
|
| 219 |
+
"prefix": null,
|
| 220 |
+
"problem_type": null,
|
| 221 |
+
"pruned_heads": {},
|
| 222 |
+
"remove_invalid_values": false,
|
| 223 |
+
"repetition_penalty": 1.0,
|
| 224 |
+
"return_dict": true,
|
| 225 |
+
"return_dict_in_generate": false,
|
| 226 |
+
"sep_token_id": null,
|
| 227 |
+
"suppress_tokens": null,
|
| 228 |
+
"task_specific_params": null,
|
| 229 |
+
"temperature": 1.0,
|
| 230 |
+
"tf_legacy_loss": false,
|
| 231 |
+
"tie_encoder_decoder": false,
|
| 232 |
+
"tie_word_embeddings": true,
|
| 233 |
+
"tokenizer_class": null,
|
| 234 |
+
"top_k": 50,
|
| 235 |
+
"top_p": 1.0,
|
| 236 |
+
"torch_dtype": null,
|
| 237 |
+
"torchscript": false,
|
| 238 |
+
"typical_p": 1.0,
|
| 239 |
+
"use_bfloat16": false
|
| 240 |
+
}
|
| 241 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/generation_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bad_words_ids": [
|
| 4 |
+
[
|
| 5 |
+
32000
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
32001
|
| 9 |
+
]
|
| 10 |
+
],
|
| 11 |
+
"bos_token_id": 1,
|
| 12 |
+
"eos_token_id": [
|
| 13 |
+
2,
|
| 14 |
+
32002
|
| 15 |
+
],
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"transformers_version": "4.45.1"
|
| 18 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e5809f7a0e453b6845d247ea714591334134281a9085075c925329235220b8e
|
| 3 |
+
size 4966706832
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9965f51eeeffa3936ebecddc5bb334959cf79852a708d8fb2bf4fc3a6f74e6e
|
| 3 |
+
size 4915917232
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a8cd53a1f742b33c0ce747a4af39beb882b0cf8edc90240cdee81889b8a343e
|
| 3 |
+
size 4999820504
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:befe6d63435e1b45704cd6dfad3c7b44d7b05281c023b2a2fa60ae5923794686
|
| 3 |
+
size 1661030650
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,771 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16543375842
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.connector.modality_projection.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 7 |
+
"model.connector.modality_projection.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.connector.modality_projection.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.connector.perceiver_resampler.latents": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.connector.perceiver_resampler.layers.0.input_context_norm.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.connector.perceiver_resampler.layers.0.input_latents_norm.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.connector.perceiver_resampler.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.connector.perceiver_resampler.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.connector.perceiver_resampler.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.connector.perceiver_resampler.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.connector.perceiver_resampler.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.connector.perceiver_resampler.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.connector.perceiver_resampler.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.connector.perceiver_resampler.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.connector.perceiver_resampler.layers.1.input_context_norm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.connector.perceiver_resampler.layers.1.input_latents_norm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.connector.perceiver_resampler.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.connector.perceiver_resampler.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.connector.perceiver_resampler.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.connector.perceiver_resampler.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.connector.perceiver_resampler.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.connector.perceiver_resampler.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.connector.perceiver_resampler.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.connector.perceiver_resampler.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.connector.perceiver_resampler.layers.2.input_context_norm.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.connector.perceiver_resampler.layers.2.input_latents_norm.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.connector.perceiver_resampler.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.connector.perceiver_resampler.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"model.connector.perceiver_resampler.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 35 |
+
"model.connector.perceiver_resampler.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.connector.perceiver_resampler.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 37 |
+
"model.connector.perceiver_resampler.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 38 |
+
"model.connector.perceiver_resampler.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 39 |
+
"model.connector.perceiver_resampler.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 40 |
+
"model.connector.perceiver_resampler.norm.weight": "model-00001-of-00004.safetensors",
|
| 41 |
+
"model.text_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 42 |
+
"model.text_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 43 |
+
"model.text_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 44 |
+
"model.text_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 45 |
+
"model.text_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 46 |
+
"model.text_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 47 |
+
"model.text_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 48 |
+
"model.text_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 49 |
+
"model.text_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 50 |
+
"model.text_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 51 |
+
"model.text_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 52 |
+
"model.text_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 53 |
+
"model.text_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 54 |
+
"model.text_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 55 |
+
"model.text_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 56 |
+
"model.text_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 57 |
+
"model.text_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 58 |
+
"model.text_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 59 |
+
"model.text_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 60 |
+
"model.text_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.text_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.text_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.text_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.text_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.text_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.text_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.text_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.text_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.text_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.text_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.text_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.text_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.text_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.text_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.text_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.text_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.text_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.text_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.text_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.text_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.text_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.text_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.text_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.text_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.text_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.text_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.text_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.text_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.text_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.text_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.text_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.text_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.text_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.text_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.text_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.text_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.text_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.text_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.text_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.text_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.text_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.text_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.text_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.text_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.text_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.text_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.text_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.text_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.text_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.text_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.text_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.text_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.text_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.text_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 115 |
+
"model.text_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.text_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.text_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.text_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.text_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.text_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.text_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.text_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.text_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.text_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.text_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.text_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.text_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.text_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.text_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.text_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.text_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.text_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.text_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.text_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.text_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.text_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.text_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.text_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.text_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.text_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.text_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.text_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.text_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.text_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.text_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.text_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.text_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.text_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.text_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.text_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.text_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.text_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"model.text_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.text_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.text_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.text_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.text_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.text_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.text_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.text_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.text_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.text_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.text_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.text_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.text_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.text_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.text_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.text_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.text_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.text_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.text_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.text_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.text_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.text_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.text_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.text_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.text_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.text_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.text_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.text_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.text_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.text_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.text_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.text_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.text_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.text_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.text_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.text_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.text_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.text_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.text_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.text_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.text_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.text_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.text_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.text_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.text_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.text_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.text_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.text_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.text_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.text_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.text_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.text_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.text_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.text_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.text_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.text_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.text_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.text_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.text_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.text_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.text_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.text_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.text_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.text_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.text_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.text_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.text_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.text_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.text_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.text_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.text_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.text_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.text_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.text_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.text_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.text_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.text_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.text_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.text_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 232 |
+
"model.text_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 233 |
+
"model.text_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.text_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.text_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 236 |
+
"model.text_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.text_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.text_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.text_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.text_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 241 |
+
"model.text_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 242 |
+
"model.text_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 243 |
+
"model.text_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 244 |
+
"model.text_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 245 |
+
"model.text_model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 246 |
+
"model.text_model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 247 |
+
"model.text_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 248 |
+
"model.text_model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 249 |
+
"model.text_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.text_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.text_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.text_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 253 |
+
"model.text_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.text_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 255 |
+
"model.text_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"model.text_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.text_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.text_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.text_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.text_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 261 |
+
"model.text_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 262 |
+
"model.text_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 263 |
+
"model.text_model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 264 |
+
"model.text_model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 265 |
+
"model.text_model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 266 |
+
"model.text_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 267 |
+
"model.text_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 268 |
+
"model.text_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 269 |
+
"model.text_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 270 |
+
"model.text_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 271 |
+
"model.text_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 272 |
+
"model.text_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 273 |
+
"model.text_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 274 |
+
"model.text_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 275 |
+
"model.text_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 276 |
+
"model.text_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.text_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.text_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.text_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.text_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.text_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.text_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.text_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.text_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.text_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 286 |
+
"model.text_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 287 |
+
"model.text_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.text_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.text_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.text_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.text_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.text_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.text_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.text_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.text_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.text_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 297 |
+
"model.text_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"model.text_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 299 |
+
"model.text_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 300 |
+
"model.text_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"model.text_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 302 |
+
"model.text_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 303 |
+
"model.text_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 304 |
+
"model.text_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 305 |
+
"model.text_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 306 |
+
"model.text_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 307 |
+
"model.text_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 308 |
+
"model.text_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"model.text_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"model.text_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"model.text_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 312 |
+
"model.text_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"model.text_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 314 |
+
"model.text_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"model.text_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"model.text_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.text_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.text_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.text_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.text_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.text_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.text_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.text_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.text_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.text_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.text_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.text_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 328 |
+
"model.text_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 329 |
+
"model.text_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 330 |
+
"model.text_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
|
| 332 |
+
"model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
|
| 334 |
+
"model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 335 |
+
"model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 336 |
+
"model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 337 |
+
"model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 338 |
+
"model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 339 |
+
"model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 395 |
+
"model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
+
"model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 398 |
+
"model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 399 |
+
"model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 405 |
+
"model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 406 |
+
"model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 407 |
+
"model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 408 |
+
"model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 409 |
+
"model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 410 |
+
"model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 412 |
+
"model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 413 |
+
"model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 414 |
+
"model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 417 |
+
"model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 419 |
+
"model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 421 |
+
"model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 429 |
+
"model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 431 |
+
"model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 433 |
+
"model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 441 |
+
"model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 453 |
+
"model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 465 |
+
"model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 475 |
+
"model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 477 |
+
"model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 487 |
+
"model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 489 |
+
"model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 490 |
+
"model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 491 |
+
"model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 493 |
+
"model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 497 |
+
"model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 499 |
+
"model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 505 |
+
"model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 507 |
+
"model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 509 |
+
"model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 511 |
+
"model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 513 |
+
"model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 515 |
+
"model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 517 |
+
"model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 519 |
+
"model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 523 |
+
"model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 525 |
+
"model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 527 |
+
"model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 531 |
+
"model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 533 |
+
"model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 535 |
+
"model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 537 |
+
"model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 545 |
+
"model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 547 |
+
"model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 549 |
+
"model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 553 |
+
"model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 557 |
+
"model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 558 |
+
"model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 559 |
+
"model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 561 |
+
"model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 562 |
+
"model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 563 |
+
"model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 565 |
+
"model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 566 |
+
"model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 569 |
+
"model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 570 |
+
"model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 571 |
+
"model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 573 |
+
"model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 574 |
+
"model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 575 |
+
"model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 576 |
+
"model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 577 |
+
"model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 579 |
+
"model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 581 |
+
"model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 583 |
+
"model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 585 |
+
"model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 587 |
+
"model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 589 |
+
"model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 591 |
+
"model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 593 |
+
"model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 595 |
+
"model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 597 |
+
"model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 599 |
+
"model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 601 |
+
"model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 603 |
+
"model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 605 |
+
"model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 607 |
+
"model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 609 |
+
"model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 615 |
+
"model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 619 |
+
"model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 621 |
+
"model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 623 |
+
"model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 625 |
+
"model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 627 |
+
"model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 631 |
+
"model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 633 |
+
"model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 641 |
+
"model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 643 |
+
"model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 645 |
+
"model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 647 |
+
"model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 649 |
+
"model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 653 |
+
"model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 654 |
+
"model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 655 |
+
"model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 657 |
+
"model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 659 |
+
"model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 661 |
+
"model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 663 |
+
"model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 667 |
+
"model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 669 |
+
"model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 671 |
+
"model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 672 |
+
"model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 673 |
+
"model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 674 |
+
"model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 676 |
+
"model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 678 |
+
"model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 679 |
+
"model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 681 |
+
"model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 682 |
+
"model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 684 |
+
"model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 687 |
+
"model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 688 |
+
"model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 689 |
+
"model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 691 |
+
"model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 693 |
+
"model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 696 |
+
"model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 697 |
+
"model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 698 |
+
"model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 700 |
+
"model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 701 |
+
"model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 703 |
+
"model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 705 |
+
"model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 706 |
+
"model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 707 |
+
"model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 709 |
+
"model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 711 |
+
"model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 712 |
+
"model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 713 |
+
"model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 714 |
+
"model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 715 |
+
"model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 717 |
+
"model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 719 |
+
"model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 720 |
+
"model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 721 |
+
"model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 722 |
+
"model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 723 |
+
"model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 724 |
+
"model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 729 |
+
"model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 731 |
+
"model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 732 |
+
"model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 733 |
+
"model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 734 |
+
"model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 735 |
+
"model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 736 |
+
"model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 738 |
+
"model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 740 |
+
"model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 743 |
+
"model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 745 |
+
"model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 747 |
+
"model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 748 |
+
"model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 749 |
+
"model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 750 |
+
"model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 751 |
+
"model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 752 |
+
"model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 753 |
+
"model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 756 |
+
"model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 757 |
+
"model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 758 |
+
"model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 759 |
+
"model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 760 |
+
"model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 761 |
+
"model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 762 |
+
"model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 763 |
+
"model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 764 |
+
"model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 765 |
+
"model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 766 |
+
"model.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
|
| 767 |
+
"model.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 768 |
+
"score.bias": "model-00004-of-00004.safetensors",
|
| 769 |
+
"score.weight": "model-00004-of-00004.safetensors"
|
| 770 |
+
}
|
| 771 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_image_splitting": false,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_pad": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Idefics2ImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Idefics2Processor",
|
| 20 |
+
"resample": 2,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 980,
|
| 24 |
+
"shortest_edge": 378
|
| 25 |
+
}
|
| 26 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_len": 64,
|
| 3 |
+
"processor_class": "Idefics2Processor"
|
| 4 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/special_tokens_map.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<fake_token_around_image>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<image>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<end_of_utterance>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"bos_token": {
|
| 26 |
+
"content": "<s>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"eos_token": {
|
| 33 |
+
"content": "</s>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"pad_token": {
|
| 40 |
+
"content": "<unk>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"unk_token": {
|
| 47 |
+
"content": "<unk>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false
|
| 52 |
+
}
|
| 53 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/tokenizer_config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<fake_token_around_image>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<image>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<end_of_utterance>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"additional_special_tokens": [
|
| 56 |
+
"<fake_token_around_image>",
|
| 57 |
+
"<image>",
|
| 58 |
+
"<end_of_utterance>"
|
| 59 |
+
],
|
| 60 |
+
"bos_token": "<s>",
|
| 61 |
+
"clean_up_tokenization_spaces": false,
|
| 62 |
+
"do_image_splitting": false,
|
| 63 |
+
"eos_token": "</s>",
|
| 64 |
+
"legacy": false,
|
| 65 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 66 |
+
"pad_token": "<unk>",
|
| 67 |
+
"processor_class": "Idefics2Processor",
|
| 68 |
+
"sp_model_kwargs": {},
|
| 69 |
+
"spaces_between_special_tokens": false,
|
| 70 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 71 |
+
"unk_token": "<unk>",
|
| 72 |
+
"use_default_system_prompt": true
|
| 73 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-benchmark-1epoch_4096_regression/checkpoint-final/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93afd7999e76e3f0d04b81f9207ade2d749cf6a57262717fbc23fb15c4f9a29c
|
| 3 |
+
size 6584
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-quality_4096_regression/checkpoint-final/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<end_of_utterance>": 32002,
|
| 3 |
+
"<fake_token_around_image>": 32000,
|
| 4 |
+
"<image>": 32001
|
| 5 |
+
}
|
reward/weights/mantis-8b-idefics2-video-eval-24frame-quality_4096_regression/checkpoint-final/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
|
| 3 |
+
}
|