xzuyn commited on
Commit
ff380b5
·
verified ·
1 Parent(s): 0521894

Upload 9 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "PJMixers-Dev/Gemma-3-Earthen-Completion-v0.1-4B",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": null,
9
+ "inference_mode": false,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 256,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.125,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 256,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": "language_model.model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj",
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Gemma3ForConditionalGeneration"
5
+ ],
6
+ "boi_token_index": 255999,
7
+ "eoi_token_index": 256000,
8
+ "image_token_index": 262144,
9
+ "initializer_range": 0.02,
10
+ "mm_tokens_per_image": 256,
11
+ "model_type": "gemma3",
12
+ "quantization_config": {
13
+ "_load_in_4bit": true,
14
+ "_load_in_8bit": false,
15
+ "bnb_4bit_compute_dtype": "bfloat16",
16
+ "bnb_4bit_quant_storage": "bfloat16",
17
+ "bnb_4bit_quant_type": "nf4",
18
+ "bnb_4bit_use_double_quant": true,
19
+ "llm_int8_enable_fp32_cpu_offload": false,
20
+ "llm_int8_has_fp16_weight": false,
21
+ "llm_int8_skip_modules": null,
22
+ "llm_int8_threshold": 6.0,
23
+ "load_in_4bit": true,
24
+ "load_in_8bit": false,
25
+ "quant_method": "bitsandbytes"
26
+ },
27
+ "text_config": {
28
+ "attention_bias": false,
29
+ "attention_dropout": 0.0,
30
+ "attn_logit_softcapping": null,
31
+ "cache_implementation": "hybrid",
32
+ "final_logit_softcapping": null,
33
+ "head_dim": 256,
34
+ "hidden_activation": "gelu_pytorch_tanh",
35
+ "hidden_size": 2560,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 10240,
38
+ "max_position_embeddings": 131072,
39
+ "model_type": "gemma3_text",
40
+ "num_attention_heads": 8,
41
+ "num_hidden_layers": 34,
42
+ "num_key_value_heads": 4,
43
+ "query_pre_attn_scalar": 256,
44
+ "rms_norm_eps": 1e-06,
45
+ "rope_local_base_freq": 10000.0,
46
+ "rope_scaling": {
47
+ "factor": 8.0,
48
+ "rope_type": "linear"
49
+ },
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": 1024,
52
+ "sliding_window_pattern": 6,
53
+ "torch_dtype": "bfloat16",
54
+ "use_cache": false,
55
+ "vocab_size": 262208
56
+ },
57
+ "torch_dtype": "bfloat16",
58
+ "transformers_version": "4.51.3",
59
+ "vision_config": {
60
+ "attention_dropout": 0.0,
61
+ "hidden_act": "gelu_pytorch_tanh",
62
+ "hidden_size": 1152,
63
+ "image_size": 896,
64
+ "intermediate_size": 4304,
65
+ "layer_norm_eps": 1e-06,
66
+ "model_type": "siglip_vision_model",
67
+ "num_attention_heads": 16,
68
+ "num_channels": 3,
69
+ "num_hidden_layers": 27,
70
+ "patch_size": 14,
71
+ "torch_dtype": "bfloat16",
72
+ "vision_use_head": false
73
+ }
74
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff