Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,429 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:4893
+- loss:TripletLoss
+base_model: microsoft/deberta-base
+widget:
+- source_sentence: Perfect working condition. Then what you say leads obviously to
+    one alternative. The source of radiation is not from our universe. Nor in our
+    universe, Captain. It came from outside. Outside? Yes, that would explain a lot.
+    Another universe, perhaps in another dimension, occupying the same space at the
+    same time. The possible existence of a parallel universe has been scientifically
+    conceded, Captain.[SEP]All right. What would happen if another universe, say a
+    minus universe, came into contact with a positive universe such as ours?
+  sentences:
+  - ' How''s your leg? You seem to be favoring your left side.'
+  - Unquestionably a warp. A distortion of physical laws on an immense scale.
+  - Queen to queen's level three.
+- source_sentence: The transporter refuses to function, even at maximum power. But
+    all the circuits test out. It appears to be the same energy block that's jamming
+    our communications. I cannot pinpoint a source. Captain, there's something over
+    there in the trees. Metal alloy like the planetary shell. It might tell us something.
+    There's an inscription, several languages.[SEP]The Keeper's dead.
+  sentences:
+  - ' How much heat are you taking from the parents?'
+  - This vault was constructed about a half a million years ago. About the same time
+    the planet surface was destroyed, if our sensor readings are accurate.
+  - An astute medical observation, Doctor, if we can believe this information. Tricorder
+    readings indicate there is a body interred here.
+- source_sentence: Welcome home, Jim. I had a whole universe to myself after the Defiant
+    was thrown out. There was absolutely no one else in it. I must say I prefer a
+    crowded universe much better. How did you two get along without me? Oh, we managed.
+    Mister Spock gave the orders, and I found the answers. Good. No problems between
+    you? None worth reporting, Captain.[SEP]Try me.
+  sentences:
+  - Only such minor disturbances as are inevitable when humans are involved.
+  - ' Harder than the right?'
+  - Good. Report to Sickbay, Mister Sulu.
+- source_sentence: Too bad, Captain. Maybe I can't go home, but neither can you. You're
+    as much a prisoner in time as I am. Recommendation for his disposition, dear?
+    Maintenance note. My recording computer has a serious malfunction. Recommend it
+    either be corrected or scrapped. Compute. Computed. Bridge to Captain Kirk.[SEP]Kirk
+    here.
+  sentences:
+  - Have some new information regarding Captain Christopher. Important I see you both
+    immediately.
+  - Several times, Captain. I do not wish to surrender hope, but the facts remain
+    unchangeable.
+  - ' [almost imitating an orgasm] Ohhh, yes! Get a head CT, draw a blood culture,
+    run a chem panel and get a complete blood count.'
+- source_sentence: That's paradise? We have no need or want, Captain. It's a true
+    Eden, Jim. There's belonging and love. No wants. No needs. We weren't meant for
+    that. None of us. Man stagnates if he has no ambition, no desire to be more than
+    he is. We have what we need.[SEP]Except a challenge.
+  sentences:
+  - Sir?
+  - ' Happy Valentine''s Day.'
+  - You don't understand, Jim, but you'll come around sooner or later. Join us. Please.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+model-index:
+- name: SentenceTransformer based on microsoft/deberta-base
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: evaluator enc
+      type: evaluator_enc
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9991825222969055
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: evaluator val
+      type: evaluator_val
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9814814925193787
+      name: Cosine Accuracy
+---
+
+# SentenceTransformer based on microsoft/deberta-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) <!-- at revision 0d1b43ccf21b5acd9f4e5f7b077fa698f05cf195 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DebertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("greatakela/gnlp_hw1_encoder_1")
+# Run inference
+sentences = [
+    "That's paradise? We have no need or want, Captain. It's a true Eden, Jim. There's belonging and love. No wants. No needs. We weren't meant for that. None of us. Man stagnates if he has no ambition, no desire to be more than he is. We have what we need.[SEP]Except a challenge.",
+    "You don't understand, Jim, but you'll come around sooner or later. Join us. Please.",
+    " Happy Valentine's Day.",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Triplet
+
+* Datasets: `evaluator_enc` and `evaluator_val`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | evaluator_enc | evaluator_val |
+|:--------------------|:--------------|:--------------|
+| **cosine_accuracy** | **0.9992**    | **0.9815**    |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 4,893 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                         | sentence_2                                                                         |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 83.32 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 18.63 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 18.98 tokens</li><li>max: 128 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | sentence_1                                                                                                               | sentence_2                                                                                                                                                                                                                                                                          |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Don't know yet. Engineering. No casualties, Captain, but trouble aplenty with the engines. Every dilithium crystal connection's smashed in the warp engine circuitry. We're trying to bypass them now. What about main circuits? Well, you have to see it to believe it, sir. Those big crystals in there have come apart. Each of them unpeeling like the rind of an orange. Analysis, Spock.[SEP]Our only hope now is rewiring impulse. But there are a thousand broken connections.</code> | <code>Captain, this is quite unprecedented. Notice the fracturing is spiro-form, similar to long chain molecules.</code> | <code> No signs of drug use or acetaminophen poisoning in his tox screen. Maybe the water was contaminated.</code>                                                                                                                                                                  |
+  | <code>Behold. That is most significant. An instinct new to the essence of her being is generating. Compassion for another is becoming part of her functioning life system. She is afraid. She's saving herself. She does not yet have the instinct to save her people. We have failed?[SEP]No. No, not yet.</code>                                                                                                                                                                                  | <code>Captain, Dr. McCoy's life is not solely dependent on Gem. The Vians too must be capable of saving his life.</code> | <code> Not right now. She's already on a respirator. The maParkne is breathing for her. I can do whatEver I want to her lungs. If you're playing catch in the living room and you break your mother's vase you might as well keep playing catch. The vase is already broken.</code> |
+  | <code>He was aware of what might happen when he went. I should never have let him go. You had no choice, Captain. You could not have stopped him. How can you ignore that? A Vulcan would not cry out so.[SEP]Whether he's a Vulcan or not, he's in agony.</code>                                                                                                                                                                                                                                   | <code>I am not insensitive to it, Captain.</code>                                                                        | <code> What about something vascular, polyarteritis nodosa.</code>                                                                                                                                                                                                                  |
+* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
+      "triplet_margin": 5
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 8
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | evaluator_enc_cosine_accuracy | evaluator_val_cosine_accuracy |
+|:------:|:----:|:-------------:|:-----------------------------:|:-----------------------------:|
+| -1     | -1   | -             | 0.6203                        | -                             |
+| 0.4902 | 300  | -             | 0.9789                        | -                             |
+| 0.8170 | 500  | 0.8516        | -                             | -                             |
+| 0.9804 | 600  | -             | 0.9931                        | -                             |
+| 1.0    | 612  | -             | 0.9937                        | -                             |
+| 1.4706 | 900  | -             | 0.9955                        | -                             |
+| 1.6340 | 1000 | 0.1586        | -                             | -                             |
+| 1.9608 | 1200 | -             | 0.9982                        | -                             |
+| 2.0    | 1224 | -             | 0.9992                        | -                             |
+| 2.4510 | 1500 | 0.0644        | 0.9992                        | -                             |
+| 2.9412 | 1800 | -             | 0.9992                        | -                             |
+| 3.0    | 1836 | -             | 0.9992                        | -                             |
+| -1     | -1   | -             | -                             | 0.9815                        |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### TripletLoss
+```bibtex
+@misc{hermans2017defense,
+    title={In Defense of the Triplet Loss for Person Re-Identification},
+    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
+    year={2017},
+    eprint={1703.07737},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "microsoft/deberta-base",
+  "architectures": [
+    "DebertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8183b3fd54c073e9a380efb364c4500297686d41cb95e8c2146e9caabd2f3385
+size 554429144

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "gpt2"
+}