Hugging Face's logo

LeiGong
/
vlm_3d_tracking_annotator_opensource_checkpoints

Image-Text-to-Text
Safetensors
mirror
vision-language
point-tracking
tap-vid-davis
Model card Files
xet
 Community
LeiGong commited on
Commit
270dfc1
·
verified ·
1 Parent(s): 1ca0f20

remove 8 model folders: OpenGVLab--InternVL3-14B-hf, OpenGVLab--InternVL3-1B-hf, OpenGVLab--InternVL3-2B-hf, OpenGVLab--InternVL3-38B-AWQ, OpenGVLab--InternVL3-8B-hf, OpenGVLab--InternVL3-9B, deepseek-ai--deepseek-vl2-small, deepseek-ai--deepseek-vl2-tiny

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. OpenGVLab--InternVL3-14B-hf/added_tokens.json +0 -34
  2. OpenGVLab--InternVL3-14B-hf/chat_template.jinja +0 -6
  3. OpenGVLab--InternVL3-14B-hf/config.json +0 -79
  4. OpenGVLab--InternVL3-14B-hf/generation_config.json +0 -6
  5. OpenGVLab--InternVL3-14B-hf/merges.txt +0 -0
  6. OpenGVLab--InternVL3-14B-hf/model-00001-of-00007.safetensors +0 -3
  7. OpenGVLab--InternVL3-14B-hf/model-00002-of-00007.safetensors +0 -3
  8. OpenGVLab--InternVL3-14B-hf/model-00003-of-00007.safetensors +0 -3
  9. OpenGVLab--InternVL3-14B-hf/model-00004-of-00007.safetensors +0 -3
  10. OpenGVLab--InternVL3-14B-hf/model-00005-of-00007.safetensors +0 -3
  11. OpenGVLab--InternVL3-14B-hf/model-00006-of-00007.safetensors +0 -3
  12. OpenGVLab--InternVL3-14B-hf/model-00007-of-00007.safetensors +0 -3
  13. OpenGVLab--InternVL3-14B-hf/model.safetensors.index.json +0 -1028
  14. OpenGVLab--InternVL3-14B-hf/preprocessor_config.json +0 -34
  15. OpenGVLab--InternVL3-14B-hf/processor_config.json +0 -4
  16. OpenGVLab--InternVL3-14B-hf/special_tokens_map.json +0 -44
  17. OpenGVLab--InternVL3-14B-hf/tokenizer.json +0 -3
  18. OpenGVLab--InternVL3-14B-hf/tokenizer_config.json +0 -306
  19. OpenGVLab--InternVL3-14B-hf/vocab.json +0 -0
  20. OpenGVLab--InternVL3-1B-hf/added_tokens.json +0 -34
  21. OpenGVLab--InternVL3-1B-hf/chat_template.jinja +0 -6
  22. OpenGVLab--InternVL3-1B-hf/config.json +0 -79
  23. OpenGVLab--InternVL3-1B-hf/generation_config.json +0 -6
  24. OpenGVLab--InternVL3-1B-hf/merges.txt +0 -0
  25. OpenGVLab--InternVL3-1B-hf/model.safetensors +0 -3
  26. OpenGVLab--InternVL3-1B-hf/preprocessor_config.json +0 -34
  27. OpenGVLab--InternVL3-1B-hf/processor_config.json +0 -4
  28. OpenGVLab--InternVL3-1B-hf/special_tokens_map.json +0 -44
  29. OpenGVLab--InternVL3-1B-hf/tokenizer.json +0 -3
  30. OpenGVLab--InternVL3-1B-hf/tokenizer_config.json +0 -306
  31. OpenGVLab--InternVL3-1B-hf/vocab.json +0 -0
  32. OpenGVLab--InternVL3-2B-hf/added_tokens.json +0 -34
  33. OpenGVLab--InternVL3-2B-hf/chat_template.jinja +0 -6
  34. OpenGVLab--InternVL3-2B-hf/config.json +0 -79
  35. OpenGVLab--InternVL3-2B-hf/generation_config.json +0 -6
  36. OpenGVLab--InternVL3-2B-hf/merges.txt +0 -0
  37. OpenGVLab--InternVL3-2B-hf/model.safetensors +0 -3
  38. OpenGVLab--InternVL3-2B-hf/preprocessor_config.json +0 -34
  39. OpenGVLab--InternVL3-2B-hf/processor_config.json +0 -4
  40. OpenGVLab--InternVL3-2B-hf/special_tokens_map.json +0 -44
  41. OpenGVLab--InternVL3-2B-hf/tokenizer.json +0 -3
  42. OpenGVLab--InternVL3-2B-hf/tokenizer_config.json +0 -306
  43. OpenGVLab--InternVL3-2B-hf/vocab.json +0 -0
  44. OpenGVLab--InternVL3-38B-AWQ/added_tokens.json +0 -33
  45. OpenGVLab--InternVL3-38B-AWQ/config.json +0 -232
  46. OpenGVLab--InternVL3-38B-AWQ/configuration_intern_vit.py +0 -120
  47. OpenGVLab--InternVL3-38B-AWQ/configuration_internvl_chat.py +0 -97
  48. OpenGVLab--InternVL3-38B-AWQ/generation_config.json +0 -4
  49. OpenGVLab--InternVL3-38B-AWQ/merges.txt +0 -0
  50. OpenGVLab--InternVL3-38B-AWQ/preprocessor_config.json +0 -19
OpenGVLab--InternVL3-14B-hf/added_tokens.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "</box>": 151673,
3
- "</img>": 151666,
4
- "</quad>": 151669,
5
- "</ref>": 151671,
6
- "</tool_call>": 151658,
7
- "<IMG_CONTEXT>": 151667,
8
- "<box>": 151672,
9
- "<img>": 151665,
10
- "<quad>": 151668,
11
- "<ref>": 151670,
12
- "<tool_call>": 151657,
13
- "<video>": 151674,
14
- "<|box_end|>": 151649,
15
- "<|box_start|>": 151648,
16
- "<|endoftext|>": 151643,
17
- "<|file_sep|>": 151664,
18
- "<|fim_middle|>": 151660,
19
- "<|fim_pad|>": 151662,
20
- "<|fim_prefix|>": 151659,
21
- "<|fim_suffix|>": 151661,
22
- "<|im_end|>": 151645,
23
- "<|im_start|>": 151644,
24
- "<|image_pad|>": 151655,
25
- "<|object_ref_end|>": 151647,
26
- "<|object_ref_start|>": 151646,
27
- "<|quad_end|>": 151651,
28
- "<|quad_start|>": 151650,
29
- "<|repo_name|>": 151663,
30
- "<|video_pad|>": 151656,
31
- "<|vision_end|>": 151653,
32
- "<|vision_pad|>": 151654,
33
- "<|vision_start|>": 151652
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/chat_template.jinja DELETED
@@ -1,6 +0,0 @@
1
- {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
- '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
3
- ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
- ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
- '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
- ' }}{% endif %}
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/config.json DELETED
@@ -1,79 +0,0 @@
1
- {
2
- "architectures": [
3
- "InternVLForConditionalGeneration"
4
- ],
5
- "downsample_ratio": 0.5,
6
- "image_seq_length": 256,
7
- "image_token_id": 151667,
8
- "model_type": "internvl",
9
- "projector_hidden_act": "gelu",
10
- "text_config": {
11
- "architectures": [
12
- "Qwen2ForCausalLM"
13
- ],
14
- "attention_dropout": 0.0,
15
- "bos_token_id": 151643,
16
- "eos_token_id": 151645,
17
- "hidden_act": "silu",
18
- "hidden_size": 5120,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 13824,
21
- "max_position_embeddings": 32768,
22
- "max_window_layers": 70,
23
- "model_type": "qwen2",
24
- "num_attention_heads": 40,
25
- "num_hidden_layers": 48,
26
- "num_key_value_heads": 8,
27
- "rms_norm_eps": 1e-06,
28
- "rope_scaling": {
29
- "factor": 2.0,
30
- "rope_type": "dynamic",
31
- "type": "dynamic"
32
- },
33
- "rope_theta": 1000000.0,
34
- "sliding_window": null,
35
- "torch_dtype": "bfloat16",
36
- "use_cache": true,
37
- "use_sliding_window": false,
38
- "vocab_size": 151674
39
- },
40
- "torch_dtype": "bfloat16",
41
- "transformers_version": "4.52.0.dev0",
42
- "vision_config": {
43
- "architectures": [
44
- "InternVisionModel"
45
- ],
46
- "attention_bias": true,
47
- "attention_dropout": 0.0,
48
- "dropout": 0.0,
49
- "hidden_act": "gelu",
50
- "hidden_dropout_prob": 0.0,
51
- "hidden_size": 1024,
52
- "image_size": [
53
- 448,
54
- 448
55
- ],
56
- "initializer_factor": 0.1,
57
- "initializer_range": 1e-10,
58
- "intermediate_size": 4096,
59
- "layer_norm_eps": 1e-06,
60
- "layer_scale_init_value": 0.1,
61
- "model_type": "internvl_vision",
62
- "norm_type": "layer_norm",
63
- "num_attention_heads": 16,
64
- "num_channels": 3,
65
- "num_hidden_layers": 24,
66
- "patch_size": [
67
- 14,
68
- 14
69
- ],
70
- "projection_dropout": 0.0,
71
- "torch_dtype": "bfloat16",
72
- "use_absolute_position_embeddings": true,
73
- "use_mask_token": false,
74
- "use_mean_pooling": true,
75
- "use_qk_norm": false
76
- },
77
- "vision_feature_layer": -1,
78
- "vision_feature_select_strategy": "default"
79
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 151643,
4
- "eos_token_id": 151645,
5
- "transformers_version": "4.52.0.dev0"
6
- }
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
OpenGVLab--InternVL3-14B-hf/model-00001-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:49ef8f4dcae4b3acb3669bc75e2b0dc86ab8e116796c0be04d605dfcabdcb1fa
3
- size 4866745448
 
 
 
 
OpenGVLab--InternVL3-14B-hf/model-00002-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c8138a6afa9b0f0431ebc61db5ccecff2c20afd7fdbdc7b0dfe6f0dff3190d4
3
- size 4954848944
 
 
 
 
OpenGVLab--InternVL3-14B-hf/model-00003-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ebffe790a3b451fb22c848abf6ad4556ed6532ccfa94403e59d47e5a0801580
3
- size 4954849008
 
 
 
 
OpenGVLab--InternVL3-14B-hf/model-00004-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3906e372b683c130d5307443491219390390d2b3a99f40e263a0ec084de2cd9b
3
- size 4954849008
 
 
 
 
OpenGVLab--InternVL3-14B-hf/model-00005-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d045ca960ed219ea9f878e57d9eabaa60e671faa1cc79957da85f2658cf3f8f
3
- size 4954849008
 
 
 
 
OpenGVLab--InternVL3-14B-hf/model-00006-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4dc76a417febb082987fa14b09c7fa03be6345dc0e943bcf5440e5664cf9be3
3
- size 3995360432
 
 
 
 
OpenGVLab--InternVL3-14B-hf/model-00007-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:30e89161e21411d9eea033d5aa287223b0a913f6c59fcabea57a6522bd2183f1
3
- size 1553141904
 
 
 
 
OpenGVLab--InternVL3-14B-hf/model.safetensors.index.json DELETED
@@ -1,1028 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 30234513408
4
- },
5
- "weight_map": {
6
- "language_model.lm_head.weight": "model-00007-of-00007.safetensors",
7
- "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
- "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
- "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
- "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
- "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
- "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
- "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
14
- "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
15
- "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
16
- "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
17
- "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
18
- "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
19
- "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
20
- "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
21
- "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
22
- "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
23
- "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
24
- "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
25
- "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
26
- "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
27
- "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
28
- "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
29
- "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
30
- "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
31
- "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
32
- "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
33
- "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
34
- "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
35
- "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
36
- "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
37
- "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
38
- "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
39
- "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
40
- "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
41
- "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
42
- "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
43
- "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
44
- "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
45
- "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
46
- "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
47
- "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
48
- "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
49
- "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
50
- "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
51
- "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
52
- "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
53
- "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
54
- "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
55
- "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
56
- "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
57
- "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
58
- "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
59
- "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
60
- "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
61
- "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
62
- "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
63
- "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
64
- "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
65
- "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
66
- "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
67
- "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
68
- "language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
69
- "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
70
- "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
71
- "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
72
- "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
73
- "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
74
- "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
75
- "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
76
- "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
77
- "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
78
- "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
79
- "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
80
- "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
81
- "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
82
- "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
83
- "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
84
- "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
85
- "language_model.model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
86
- "language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
87
- "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
88
- "language_model.model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
89
- "language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
90
- "language_model.model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
91
- "language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
92
- "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
93
- "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
94
- "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
95
- "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
96
- "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
97
- "language_model.model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
98
- "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
99
- "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
100
- "language_model.model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
101
- "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
102
- "language_model.model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
103
- "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
104
- "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
105
- "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
106
- "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
107
- "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
108
- "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
109
- "language_model.model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
110
- "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
111
- "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
112
- "language_model.model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
113
- "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
114
- "language_model.model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
115
- "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
116
- "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
117
- "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
118
- "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
119
- "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
120
- "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
121
- "language_model.model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
122
- "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
123
- "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
124
- "language_model.model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
125
- "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
126
- "language_model.model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
127
- "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
128
- "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
129
- "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
130
- "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
131
- "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
132
- "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
133
- "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
134
- "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
135
- "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
136
- "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
137
- "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
138
- "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
139
- "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
140
- "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
141
- "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
142
- "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
143
- "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
144
- "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
145
- "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
146
- "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
147
- "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
148
- "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
149
- "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
150
- "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
151
- "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
152
- "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
153
- "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
154
- "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
155
- "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
156
- "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
157
- "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
158
- "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
159
- "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
160
- "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
161
- "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
162
- "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
163
- "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
164
- "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
165
- "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
166
- "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
167
- "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
168
- "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
169
- "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
170
- "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
171
- "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
172
- "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
173
- "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
174
- "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
175
- "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
176
- "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
177
- "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
178
- "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
179
- "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
180
- "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
181
- "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
182
- "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
183
- "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
184
- "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
185
- "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
186
- "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
187
- "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
188
- "language_model.model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
189
- "language_model.model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
190
- "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
191
- "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
192
- "language_model.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
193
- "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
194
- "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
195
- "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
196
- "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
197
- "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
198
- "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
199
- "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
200
- "language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
201
- "language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
202
- "language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
203
- "language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
204
- "language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
205
- "language_model.model.layers.23.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
206
- "language_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
207
- "language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
208
- "language_model.model.layers.23.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
209
- "language_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
210
- "language_model.model.layers.23.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
211
- "language_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
212
- "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
213
- "language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
214
- "language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
215
- "language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
216
- "language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
217
- "language_model.model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
218
- "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
219
- "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
220
- "language_model.model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
221
- "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
222
- "language_model.model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
223
- "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
224
- "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
225
- "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
226
- "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
227
- "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
228
- "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
229
- "language_model.model.layers.25.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
230
- "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
231
- "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
232
- "language_model.model.layers.25.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
233
- "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
234
- "language_model.model.layers.25.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
235
- "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
236
- "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
237
- "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
238
- "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
239
- "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
240
- "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
241
- "language_model.model.layers.26.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
242
- "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
243
- "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
244
- "language_model.model.layers.26.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
245
- "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
246
- "language_model.model.layers.26.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
247
- "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
248
- "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
249
- "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
250
- "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
251
- "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
252
- "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
253
- "language_model.model.layers.27.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
254
- "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
255
- "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
256
- "language_model.model.layers.27.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
257
- "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
258
- "language_model.model.layers.27.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
259
- "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
260
- "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
261
- "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
262
- "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
263
- "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
264
- "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
265
- "language_model.model.layers.28.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
266
- "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
267
- "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
268
- "language_model.model.layers.28.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
269
- "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
270
- "language_model.model.layers.28.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
271
- "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
272
- "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
273
- "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
274
- "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
275
- "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
276
- "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
277
- "language_model.model.layers.29.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
278
- "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
279
- "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
280
- "language_model.model.layers.29.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
281
- "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
282
- "language_model.model.layers.29.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
283
- "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
284
- "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
285
- "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
286
- "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
287
- "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
288
- "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
289
- "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
290
- "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
291
- "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
292
- "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
293
- "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
294
- "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
295
- "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
296
- "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
297
- "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
298
- "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
299
- "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
300
- "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
301
- "language_model.model.layers.30.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
302
- "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
303
- "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
304
- "language_model.model.layers.30.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
305
- "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
306
- "language_model.model.layers.30.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
307
- "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
308
- "language_model.model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors",
309
- "language_model.model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
310
- "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
311
- "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
312
- "language_model.model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
313
- "language_model.model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
314
- "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
315
- "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
316
- "language_model.model.layers.31.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
317
- "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
318
- "language_model.model.layers.31.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
319
- "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
320
- "language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
321
- "language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
322
- "language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
323
- "language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
324
- "language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
325
- "language_model.model.layers.32.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
326
- "language_model.model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
327
- "language_model.model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
328
- "language_model.model.layers.32.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
329
- "language_model.model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
330
- "language_model.model.layers.32.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
331
- "language_model.model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
332
- "language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
333
- "language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
334
- "language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
335
- "language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
336
- "language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
337
- "language_model.model.layers.33.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
338
- "language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
339
- "language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
340
- "language_model.model.layers.33.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
341
- "language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
342
- "language_model.model.layers.33.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
343
- "language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
344
- "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
345
- "language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
346
- "language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
347
- "language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
348
- "language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
349
- "language_model.model.layers.34.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
350
- "language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
351
- "language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
352
- "language_model.model.layers.34.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
353
- "language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
354
- "language_model.model.layers.34.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
355
- "language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
356
- "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
357
- "language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
358
- "language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
359
- "language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
360
- "language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
361
- "language_model.model.layers.35.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
362
- "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
363
- "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
364
- "language_model.model.layers.35.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
365
- "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
366
- "language_model.model.layers.35.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
367
- "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
368
- "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
369
- "language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
370
- "language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
371
- "language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
372
- "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
373
- "language_model.model.layers.36.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
374
- "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
375
- "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
376
- "language_model.model.layers.36.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
377
- "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
378
- "language_model.model.layers.36.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
379
- "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
380
- "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
381
- "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
382
- "language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
383
- "language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
384
- "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
385
- "language_model.model.layers.37.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
386
- "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
387
- "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
388
- "language_model.model.layers.37.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
389
- "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
390
- "language_model.model.layers.37.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
391
- "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
392
- "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
393
- "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
394
- "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
395
- "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
396
- "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
397
- "language_model.model.layers.38.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
398
- "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
399
- "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
400
- "language_model.model.layers.38.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
401
- "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
402
- "language_model.model.layers.38.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
403
- "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
404
- "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
405
- "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
406
- "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
407
- "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
408
- "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
409
- "language_model.model.layers.39.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
410
- "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
411
- "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
412
- "language_model.model.layers.39.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
413
- "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
414
- "language_model.model.layers.39.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
415
- "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
416
- "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
417
- "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
418
- "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
419
- "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
420
- "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
421
- "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
422
- "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
423
- "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
424
- "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
425
- "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
426
- "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
427
- "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
428
- "language_model.model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors",
429
- "language_model.model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
430
- "language_model.model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
431
- "language_model.model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
432
- "language_model.model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
433
- "language_model.model.layers.40.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
434
- "language_model.model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
435
- "language_model.model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
436
- "language_model.model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
437
- "language_model.model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
438
- "language_model.model.layers.40.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
439
- "language_model.model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
440
- "language_model.model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors",
441
- "language_model.model.layers.41.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
442
- "language_model.model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
443
- "language_model.model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
444
- "language_model.model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
445
- "language_model.model.layers.41.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
446
- "language_model.model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
447
- "language_model.model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
448
- "language_model.model.layers.41.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
449
- "language_model.model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
450
- "language_model.model.layers.41.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
451
- "language_model.model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
452
- "language_model.model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
453
- "language_model.model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
454
- "language_model.model.layers.42.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
455
- "language_model.model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
456
- "language_model.model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
457
- "language_model.model.layers.42.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
458
- "language_model.model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
459
- "language_model.model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
460
- "language_model.model.layers.42.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
461
- "language_model.model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
462
- "language_model.model.layers.42.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
463
- "language_model.model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
464
- "language_model.model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
465
- "language_model.model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
466
- "language_model.model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
467
- "language_model.model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
468
- "language_model.model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
469
- "language_model.model.layers.43.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
470
- "language_model.model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
471
- "language_model.model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
472
- "language_model.model.layers.43.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
473
- "language_model.model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
474
- "language_model.model.layers.43.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
475
- "language_model.model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
476
- "language_model.model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
477
- "language_model.model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
478
- "language_model.model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
479
- "language_model.model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
480
- "language_model.model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
481
- "language_model.model.layers.44.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
482
- "language_model.model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
483
- "language_model.model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
484
- "language_model.model.layers.44.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
485
- "language_model.model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
486
- "language_model.model.layers.44.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
487
- "language_model.model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
488
- "language_model.model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
489
- "language_model.model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
490
- "language_model.model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
491
- "language_model.model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
492
- "language_model.model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
493
- "language_model.model.layers.45.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
494
- "language_model.model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
495
- "language_model.model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
496
- "language_model.model.layers.45.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
497
- "language_model.model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
498
- "language_model.model.layers.45.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
499
- "language_model.model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
500
- "language_model.model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
501
- "language_model.model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
502
- "language_model.model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
503
- "language_model.model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
504
- "language_model.model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
505
- "language_model.model.layers.46.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
506
- "language_model.model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
507
- "language_model.model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
508
- "language_model.model.layers.46.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
509
- "language_model.model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
510
- "language_model.model.layers.46.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
511
- "language_model.model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
512
- "language_model.model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
513
- "language_model.model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
514
- "language_model.model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
515
- "language_model.model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
516
- "language_model.model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
517
- "language_model.model.layers.47.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
518
- "language_model.model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
519
- "language_model.model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
520
- "language_model.model.layers.47.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
521
- "language_model.model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
522
- "language_model.model.layers.47.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
523
- "language_model.model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
524
- "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
525
- "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
526
- "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
527
- "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
528
- "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
529
- "language_model.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
530
- "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
531
- "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
532
- "language_model.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
533
- "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
534
- "language_model.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
535
- "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
536
- "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
537
- "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
538
- "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
539
- "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
540
- "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
541
- "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
542
- "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
543
- "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
544
- "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
545
- "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
546
- "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
547
- "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
548
- "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
549
- "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
550
- "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
551
- "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
552
- "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
553
- "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
554
- "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
555
- "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
556
- "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
557
- "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
558
- "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
559
- "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
560
- "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
561
- "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
562
- "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
563
- "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
564
- "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
565
- "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
566
- "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
567
- "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
568
- "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
569
- "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
570
- "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
571
- "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
572
- "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
573
- "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
574
- "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
575
- "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
576
- "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
577
- "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
578
- "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
579
- "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
580
- "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
581
- "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
582
- "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
583
- "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
584
- "language_model.model.norm.weight": "model-00006-of-00007.safetensors",
585
- "multi_modal_projector.layer_norm.bias": "model-00001-of-00007.safetensors",
586
- "multi_modal_projector.layer_norm.weight": "model-00001-of-00007.safetensors",
587
- "multi_modal_projector.linear_1.bias": "model-00001-of-00007.safetensors",
588
- "multi_modal_projector.linear_1.weight": "model-00001-of-00007.safetensors",
589
- "multi_modal_projector.linear_2.bias": "model-00001-of-00007.safetensors",
590
- "multi_modal_projector.linear_2.weight": "model-00001-of-00007.safetensors",
591
- "vision_tower.embeddings.cls_token": "model-00001-of-00007.safetensors",
592
- "vision_tower.embeddings.patch_embeddings.projection.bias": "model-00001-of-00007.safetensors",
593
- "vision_tower.embeddings.patch_embeddings.projection.weight": "model-00001-of-00007.safetensors",
594
- "vision_tower.embeddings.position_embeddings": "model-00001-of-00007.safetensors",
595
- "vision_tower.encoder.layer.0.attention.k_proj.bias": "model-00001-of-00007.safetensors",
596
- "vision_tower.encoder.layer.0.attention.k_proj.weight": "model-00001-of-00007.safetensors",
597
- "vision_tower.encoder.layer.0.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
598
- "vision_tower.encoder.layer.0.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
599
- "vision_tower.encoder.layer.0.attention.q_proj.bias": "model-00001-of-00007.safetensors",
600
- "vision_tower.encoder.layer.0.attention.q_proj.weight": "model-00001-of-00007.safetensors",
601
- "vision_tower.encoder.layer.0.attention.v_proj.bias": "model-00001-of-00007.safetensors",
602
- "vision_tower.encoder.layer.0.attention.v_proj.weight": "model-00001-of-00007.safetensors",
603
- "vision_tower.encoder.layer.0.lambda_1": "model-00001-of-00007.safetensors",
604
- "vision_tower.encoder.layer.0.lambda_2": "model-00001-of-00007.safetensors",
605
- "vision_tower.encoder.layer.0.layernorm_after.bias": "model-00001-of-00007.safetensors",
606
- "vision_tower.encoder.layer.0.layernorm_after.weight": "model-00001-of-00007.safetensors",
607
- "vision_tower.encoder.layer.0.layernorm_before.bias": "model-00001-of-00007.safetensors",
608
- "vision_tower.encoder.layer.0.layernorm_before.weight": "model-00001-of-00007.safetensors",
609
- "vision_tower.encoder.layer.0.mlp.fc1.bias": "model-00001-of-00007.safetensors",
610
- "vision_tower.encoder.layer.0.mlp.fc1.weight": "model-00001-of-00007.safetensors",
611
- "vision_tower.encoder.layer.0.mlp.fc2.bias": "model-00001-of-00007.safetensors",
612
- "vision_tower.encoder.layer.0.mlp.fc2.weight": "model-00001-of-00007.safetensors",
613
- "vision_tower.encoder.layer.1.attention.k_proj.bias": "model-00001-of-00007.safetensors",
614
- "vision_tower.encoder.layer.1.attention.k_proj.weight": "model-00001-of-00007.safetensors",
615
- "vision_tower.encoder.layer.1.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
616
- "vision_tower.encoder.layer.1.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
617
- "vision_tower.encoder.layer.1.attention.q_proj.bias": "model-00001-of-00007.safetensors",
618
- "vision_tower.encoder.layer.1.attention.q_proj.weight": "model-00001-of-00007.safetensors",
619
- "vision_tower.encoder.layer.1.attention.v_proj.bias": "model-00001-of-00007.safetensors",
620
- "vision_tower.encoder.layer.1.attention.v_proj.weight": "model-00001-of-00007.safetensors",
621
- "vision_tower.encoder.layer.1.lambda_1": "model-00001-of-00007.safetensors",
622
- "vision_tower.encoder.layer.1.lambda_2": "model-00001-of-00007.safetensors",
623
- "vision_tower.encoder.layer.1.layernorm_after.bias": "model-00001-of-00007.safetensors",
624
- "vision_tower.encoder.layer.1.layernorm_after.weight": "model-00001-of-00007.safetensors",
625
- "vision_tower.encoder.layer.1.layernorm_before.bias": "model-00001-of-00007.safetensors",
626
- "vision_tower.encoder.layer.1.layernorm_before.weight": "model-00001-of-00007.safetensors",
627
- "vision_tower.encoder.layer.1.mlp.fc1.bias": "model-00001-of-00007.safetensors",
628
- "vision_tower.encoder.layer.1.mlp.fc1.weight": "model-00001-of-00007.safetensors",
629
- "vision_tower.encoder.layer.1.mlp.fc2.bias": "model-00001-of-00007.safetensors",
630
- "vision_tower.encoder.layer.1.mlp.fc2.weight": "model-00001-of-00007.safetensors",
631
- "vision_tower.encoder.layer.10.attention.k_proj.bias": "model-00001-of-00007.safetensors",
632
- "vision_tower.encoder.layer.10.attention.k_proj.weight": "model-00001-of-00007.safetensors",
633
- "vision_tower.encoder.layer.10.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
634
- "vision_tower.encoder.layer.10.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
635
- "vision_tower.encoder.layer.10.attention.q_proj.bias": "model-00001-of-00007.safetensors",
636
- "vision_tower.encoder.layer.10.attention.q_proj.weight": "model-00001-of-00007.safetensors",
637
- "vision_tower.encoder.layer.10.attention.v_proj.bias": "model-00001-of-00007.safetensors",
638
- "vision_tower.encoder.layer.10.attention.v_proj.weight": "model-00001-of-00007.safetensors",
639
- "vision_tower.encoder.layer.10.lambda_1": "model-00001-of-00007.safetensors",
640
- "vision_tower.encoder.layer.10.lambda_2": "model-00001-of-00007.safetensors",
641
- "vision_tower.encoder.layer.10.layernorm_after.bias": "model-00001-of-00007.safetensors",
642
- "vision_tower.encoder.layer.10.layernorm_after.weight": "model-00001-of-00007.safetensors",
643
- "vision_tower.encoder.layer.10.layernorm_before.bias": "model-00001-of-00007.safetensors",
644
- "vision_tower.encoder.layer.10.layernorm_before.weight": "model-00001-of-00007.safetensors",
645
- "vision_tower.encoder.layer.10.mlp.fc1.bias": "model-00001-of-00007.safetensors",
646
- "vision_tower.encoder.layer.10.mlp.fc1.weight": "model-00001-of-00007.safetensors",
647
- "vision_tower.encoder.layer.10.mlp.fc2.bias": "model-00001-of-00007.safetensors",
648
- "vision_tower.encoder.layer.10.mlp.fc2.weight": "model-00001-of-00007.safetensors",
649
- "vision_tower.encoder.layer.11.attention.k_proj.bias": "model-00001-of-00007.safetensors",
650
- "vision_tower.encoder.layer.11.attention.k_proj.weight": "model-00001-of-00007.safetensors",
651
- "vision_tower.encoder.layer.11.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
652
- "vision_tower.encoder.layer.11.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
653
- "vision_tower.encoder.layer.11.attention.q_proj.bias": "model-00001-of-00007.safetensors",
654
- "vision_tower.encoder.layer.11.attention.q_proj.weight": "model-00001-of-00007.safetensors",
655
- "vision_tower.encoder.layer.11.attention.v_proj.bias": "model-00001-of-00007.safetensors",
656
- "vision_tower.encoder.layer.11.attention.v_proj.weight": "model-00001-of-00007.safetensors",
657
- "vision_tower.encoder.layer.11.lambda_1": "model-00001-of-00007.safetensors",
658
- "vision_tower.encoder.layer.11.lambda_2": "model-00001-of-00007.safetensors",
659
- "vision_tower.encoder.layer.11.layernorm_after.bias": "model-00001-of-00007.safetensors",
660
- "vision_tower.encoder.layer.11.layernorm_after.weight": "model-00001-of-00007.safetensors",
661
- "vision_tower.encoder.layer.11.layernorm_before.bias": "model-00001-of-00007.safetensors",
662
- "vision_tower.encoder.layer.11.layernorm_before.weight": "model-00001-of-00007.safetensors",
663
- "vision_tower.encoder.layer.11.mlp.fc1.bias": "model-00001-of-00007.safetensors",
664
- "vision_tower.encoder.layer.11.mlp.fc1.weight": "model-00001-of-00007.safetensors",
665
- "vision_tower.encoder.layer.11.mlp.fc2.bias": "model-00001-of-00007.safetensors",
666
- "vision_tower.encoder.layer.11.mlp.fc2.weight": "model-00001-of-00007.safetensors",
667
- "vision_tower.encoder.layer.12.attention.k_proj.bias": "model-00001-of-00007.safetensors",
668
- "vision_tower.encoder.layer.12.attention.k_proj.weight": "model-00001-of-00007.safetensors",
669
- "vision_tower.encoder.layer.12.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
670
- "vision_tower.encoder.layer.12.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
671
- "vision_tower.encoder.layer.12.attention.q_proj.bias": "model-00001-of-00007.safetensors",
672
- "vision_tower.encoder.layer.12.attention.q_proj.weight": "model-00001-of-00007.safetensors",
673
- "vision_tower.encoder.layer.12.attention.v_proj.bias": "model-00001-of-00007.safetensors",
674
- "vision_tower.encoder.layer.12.attention.v_proj.weight": "model-00001-of-00007.safetensors",
675
- "vision_tower.encoder.layer.12.lambda_1": "model-00001-of-00007.safetensors",
676
- "vision_tower.encoder.layer.12.lambda_2": "model-00001-of-00007.safetensors",
677
- "vision_tower.encoder.layer.12.layernorm_after.bias": "model-00001-of-00007.safetensors",
678
- "vision_tower.encoder.layer.12.layernorm_after.weight": "model-00001-of-00007.safetensors",
679
- "vision_tower.encoder.layer.12.layernorm_before.bias": "model-00001-of-00007.safetensors",
680
- "vision_tower.encoder.layer.12.layernorm_before.weight": "model-00001-of-00007.safetensors",
681
- "vision_tower.encoder.layer.12.mlp.fc1.bias": "model-00001-of-00007.safetensors",
682
- "vision_tower.encoder.layer.12.mlp.fc1.weight": "model-00001-of-00007.safetensors",
683
- "vision_tower.encoder.layer.12.mlp.fc2.bias": "model-00001-of-00007.safetensors",
684
- "vision_tower.encoder.layer.12.mlp.fc2.weight": "model-00001-of-00007.safetensors",
685
- "vision_tower.encoder.layer.13.attention.k_proj.bias": "model-00001-of-00007.safetensors",
686
- "vision_tower.encoder.layer.13.attention.k_proj.weight": "model-00001-of-00007.safetensors",
687
- "vision_tower.encoder.layer.13.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
688
- "vision_tower.encoder.layer.13.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
689
- "vision_tower.encoder.layer.13.attention.q_proj.bias": "model-00001-of-00007.safetensors",
690
- "vision_tower.encoder.layer.13.attention.q_proj.weight": "model-00001-of-00007.safetensors",
691
- "vision_tower.encoder.layer.13.attention.v_proj.bias": "model-00001-of-00007.safetensors",
692
- "vision_tower.encoder.layer.13.attention.v_proj.weight": "model-00001-of-00007.safetensors",
693
- "vision_tower.encoder.layer.13.lambda_1": "model-00001-of-00007.safetensors",
694
- "vision_tower.encoder.layer.13.lambda_2": "model-00001-of-00007.safetensors",
695
- "vision_tower.encoder.layer.13.layernorm_after.bias": "model-00001-of-00007.safetensors",
696
- "vision_tower.encoder.layer.13.layernorm_after.weight": "model-00001-of-00007.safetensors",
697
- "vision_tower.encoder.layer.13.layernorm_before.bias": "model-00001-of-00007.safetensors",
698
- "vision_tower.encoder.layer.13.layernorm_before.weight": "model-00001-of-00007.safetensors",
699
- "vision_tower.encoder.layer.13.mlp.fc1.bias": "model-00001-of-00007.safetensors",
700
- "vision_tower.encoder.layer.13.mlp.fc1.weight": "model-00001-of-00007.safetensors",
701
- "vision_tower.encoder.layer.13.mlp.fc2.bias": "model-00001-of-00007.safetensors",
702
- "vision_tower.encoder.layer.13.mlp.fc2.weight": "model-00001-of-00007.safetensors",
703
- "vision_tower.encoder.layer.14.attention.k_proj.bias": "model-00001-of-00007.safetensors",
704
- "vision_tower.encoder.layer.14.attention.k_proj.weight": "model-00001-of-00007.safetensors",
705
- "vision_tower.encoder.layer.14.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
706
- "vision_tower.encoder.layer.14.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
707
- "vision_tower.encoder.layer.14.attention.q_proj.bias": "model-00001-of-00007.safetensors",
708
- "vision_tower.encoder.layer.14.attention.q_proj.weight": "model-00001-of-00007.safetensors",
709
- "vision_tower.encoder.layer.14.attention.v_proj.bias": "model-00001-of-00007.safetensors",
710
- "vision_tower.encoder.layer.14.attention.v_proj.weight": "model-00001-of-00007.safetensors",
711
- "vision_tower.encoder.layer.14.lambda_1": "model-00001-of-00007.safetensors",
712
- "vision_tower.encoder.layer.14.lambda_2": "model-00001-of-00007.safetensors",
713
- "vision_tower.encoder.layer.14.layernorm_after.bias": "model-00001-of-00007.safetensors",
714
- "vision_tower.encoder.layer.14.layernorm_after.weight": "model-00001-of-00007.safetensors",
715
- "vision_tower.encoder.layer.14.layernorm_before.bias": "model-00001-of-00007.safetensors",
716
- "vision_tower.encoder.layer.14.layernorm_before.weight": "model-00001-of-00007.safetensors",
717
- "vision_tower.encoder.layer.14.mlp.fc1.bias": "model-00001-of-00007.safetensors",
718
- "vision_tower.encoder.layer.14.mlp.fc1.weight": "model-00001-of-00007.safetensors",
719
- "vision_tower.encoder.layer.14.mlp.fc2.bias": "model-00001-of-00007.safetensors",
720
- "vision_tower.encoder.layer.14.mlp.fc2.weight": "model-00001-of-00007.safetensors",
721
- "vision_tower.encoder.layer.15.attention.k_proj.bias": "model-00001-of-00007.safetensors",
722
- "vision_tower.encoder.layer.15.attention.k_proj.weight": "model-00001-of-00007.safetensors",
723
- "vision_tower.encoder.layer.15.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
724
- "vision_tower.encoder.layer.15.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
725
- "vision_tower.encoder.layer.15.attention.q_proj.bias": "model-00001-of-00007.safetensors",
726
- "vision_tower.encoder.layer.15.attention.q_proj.weight": "model-00001-of-00007.safetensors",
727
- "vision_tower.encoder.layer.15.attention.v_proj.bias": "model-00001-of-00007.safetensors",
728
- "vision_tower.encoder.layer.15.attention.v_proj.weight": "model-00001-of-00007.safetensors",
729
- "vision_tower.encoder.layer.15.lambda_1": "model-00001-of-00007.safetensors",
730
- "vision_tower.encoder.layer.15.lambda_2": "model-00001-of-00007.safetensors",
731
- "vision_tower.encoder.layer.15.layernorm_after.bias": "model-00001-of-00007.safetensors",
732
- "vision_tower.encoder.layer.15.layernorm_after.weight": "model-00001-of-00007.safetensors",
733
- "vision_tower.encoder.layer.15.layernorm_before.bias": "model-00001-of-00007.safetensors",
734
- "vision_tower.encoder.layer.15.layernorm_before.weight": "model-00001-of-00007.safetensors",
735
- "vision_tower.encoder.layer.15.mlp.fc1.bias": "model-00001-of-00007.safetensors",
736
- "vision_tower.encoder.layer.15.mlp.fc1.weight": "model-00001-of-00007.safetensors",
737
- "vision_tower.encoder.layer.15.mlp.fc2.bias": "model-00001-of-00007.safetensors",
738
- "vision_tower.encoder.layer.15.mlp.fc2.weight": "model-00001-of-00007.safetensors",
739
- "vision_tower.encoder.layer.16.attention.k_proj.bias": "model-00001-of-00007.safetensors",
740
- "vision_tower.encoder.layer.16.attention.k_proj.weight": "model-00001-of-00007.safetensors",
741
- "vision_tower.encoder.layer.16.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
742
- "vision_tower.encoder.layer.16.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
743
- "vision_tower.encoder.layer.16.attention.q_proj.bias": "model-00001-of-00007.safetensors",
744
- "vision_tower.encoder.layer.16.attention.q_proj.weight": "model-00001-of-00007.safetensors",
745
- "vision_tower.encoder.layer.16.attention.v_proj.bias": "model-00001-of-00007.safetensors",
746
- "vision_tower.encoder.layer.16.attention.v_proj.weight": "model-00001-of-00007.safetensors",
747
- "vision_tower.encoder.layer.16.lambda_1": "model-00001-of-00007.safetensors",
748
- "vision_tower.encoder.layer.16.lambda_2": "model-00001-of-00007.safetensors",
749
- "vision_tower.encoder.layer.16.layernorm_after.bias": "model-00001-of-00007.safetensors",
750
- "vision_tower.encoder.layer.16.layernorm_after.weight": "model-00001-of-00007.safetensors",
751
- "vision_tower.encoder.layer.16.layernorm_before.bias": "model-00001-of-00007.safetensors",
752
- "vision_tower.encoder.layer.16.layernorm_before.weight": "model-00001-of-00007.safetensors",
753
- "vision_tower.encoder.layer.16.mlp.fc1.bias": "model-00001-of-00007.safetensors",
754
- "vision_tower.encoder.layer.16.mlp.fc1.weight": "model-00001-of-00007.safetensors",
755
- "vision_tower.encoder.layer.16.mlp.fc2.bias": "model-00001-of-00007.safetensors",
756
- "vision_tower.encoder.layer.16.mlp.fc2.weight": "model-00001-of-00007.safetensors",
757
- "vision_tower.encoder.layer.17.attention.k_proj.bias": "model-00001-of-00007.safetensors",
758
- "vision_tower.encoder.layer.17.attention.k_proj.weight": "model-00001-of-00007.safetensors",
759
- "vision_tower.encoder.layer.17.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
760
- "vision_tower.encoder.layer.17.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
761
- "vision_tower.encoder.layer.17.attention.q_proj.bias": "model-00001-of-00007.safetensors",
762
- "vision_tower.encoder.layer.17.attention.q_proj.weight": "model-00001-of-00007.safetensors",
763
- "vision_tower.encoder.layer.17.attention.v_proj.bias": "model-00001-of-00007.safetensors",
764
- "vision_tower.encoder.layer.17.attention.v_proj.weight": "model-00001-of-00007.safetensors",
765
- "vision_tower.encoder.layer.17.lambda_1": "model-00001-of-00007.safetensors",
766
- "vision_tower.encoder.layer.17.lambda_2": "model-00001-of-00007.safetensors",
767
- "vision_tower.encoder.layer.17.layernorm_after.bias": "model-00001-of-00007.safetensors",
768
- "vision_tower.encoder.layer.17.layernorm_after.weight": "model-00001-of-00007.safetensors",
769
- "vision_tower.encoder.layer.17.layernorm_before.bias": "model-00001-of-00007.safetensors",
770
- "vision_tower.encoder.layer.17.layernorm_before.weight": "model-00001-of-00007.safetensors",
771
- "vision_tower.encoder.layer.17.mlp.fc1.bias": "model-00001-of-00007.safetensors",
772
- "vision_tower.encoder.layer.17.mlp.fc1.weight": "model-00001-of-00007.safetensors",
773
- "vision_tower.encoder.layer.17.mlp.fc2.bias": "model-00001-of-00007.safetensors",
774
- "vision_tower.encoder.layer.17.mlp.fc2.weight": "model-00001-of-00007.safetensors",
775
- "vision_tower.encoder.layer.18.attention.k_proj.bias": "model-00001-of-00007.safetensors",
776
- "vision_tower.encoder.layer.18.attention.k_proj.weight": "model-00001-of-00007.safetensors",
777
- "vision_tower.encoder.layer.18.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
778
- "vision_tower.encoder.layer.18.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
779
- "vision_tower.encoder.layer.18.attention.q_proj.bias": "model-00001-of-00007.safetensors",
780
- "vision_tower.encoder.layer.18.attention.q_proj.weight": "model-00001-of-00007.safetensors",
781
- "vision_tower.encoder.layer.18.attention.v_proj.bias": "model-00001-of-00007.safetensors",
782
- "vision_tower.encoder.layer.18.attention.v_proj.weight": "model-00001-of-00007.safetensors",
783
- "vision_tower.encoder.layer.18.lambda_1": "model-00001-of-00007.safetensors",
784
- "vision_tower.encoder.layer.18.lambda_2": "model-00001-of-00007.safetensors",
785
- "vision_tower.encoder.layer.18.layernorm_after.bias": "model-00001-of-00007.safetensors",
786
- "vision_tower.encoder.layer.18.layernorm_after.weight": "model-00001-of-00007.safetensors",
787
- "vision_tower.encoder.layer.18.layernorm_before.bias": "model-00001-of-00007.safetensors",
788
- "vision_tower.encoder.layer.18.layernorm_before.weight": "model-00001-of-00007.safetensors",
789
- "vision_tower.encoder.layer.18.mlp.fc1.bias": "model-00001-of-00007.safetensors",
790
- "vision_tower.encoder.layer.18.mlp.fc1.weight": "model-00001-of-00007.safetensors",
791
- "vision_tower.encoder.layer.18.mlp.fc2.bias": "model-00001-of-00007.safetensors",
792
- "vision_tower.encoder.layer.18.mlp.fc2.weight": "model-00001-of-00007.safetensors",
793
- "vision_tower.encoder.layer.19.attention.k_proj.bias": "model-00001-of-00007.safetensors",
794
- "vision_tower.encoder.layer.19.attention.k_proj.weight": "model-00001-of-00007.safetensors",
795
- "vision_tower.encoder.layer.19.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
796
- "vision_tower.encoder.layer.19.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
797
- "vision_tower.encoder.layer.19.attention.q_proj.bias": "model-00001-of-00007.safetensors",
798
- "vision_tower.encoder.layer.19.attention.q_proj.weight": "model-00001-of-00007.safetensors",
799
- "vision_tower.encoder.layer.19.attention.v_proj.bias": "model-00001-of-00007.safetensors",
800
- "vision_tower.encoder.layer.19.attention.v_proj.weight": "model-00001-of-00007.safetensors",
801
- "vision_tower.encoder.layer.19.lambda_1": "model-00001-of-00007.safetensors",
802
- "vision_tower.encoder.layer.19.lambda_2": "model-00001-of-00007.safetensors",
803
- "vision_tower.encoder.layer.19.layernorm_after.bias": "model-00001-of-00007.safetensors",
804
- "vision_tower.encoder.layer.19.layernorm_after.weight": "model-00001-of-00007.safetensors",
805
- "vision_tower.encoder.layer.19.layernorm_before.bias": "model-00001-of-00007.safetensors",
806
- "vision_tower.encoder.layer.19.layernorm_before.weight": "model-00001-of-00007.safetensors",
807
- "vision_tower.encoder.layer.19.mlp.fc1.bias": "model-00001-of-00007.safetensors",
808
- "vision_tower.encoder.layer.19.mlp.fc1.weight": "model-00001-of-00007.safetensors",
809
- "vision_tower.encoder.layer.19.mlp.fc2.bias": "model-00001-of-00007.safetensors",
810
- "vision_tower.encoder.layer.19.mlp.fc2.weight": "model-00001-of-00007.safetensors",
811
- "vision_tower.encoder.layer.2.attention.k_proj.bias": "model-00001-of-00007.safetensors",
812
- "vision_tower.encoder.layer.2.attention.k_proj.weight": "model-00001-of-00007.safetensors",
813
- "vision_tower.encoder.layer.2.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
814
- "vision_tower.encoder.layer.2.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
815
- "vision_tower.encoder.layer.2.attention.q_proj.bias": "model-00001-of-00007.safetensors",
816
- "vision_tower.encoder.layer.2.attention.q_proj.weight": "model-00001-of-00007.safetensors",
817
- "vision_tower.encoder.layer.2.attention.v_proj.bias": "model-00001-of-00007.safetensors",
818
- "vision_tower.encoder.layer.2.attention.v_proj.weight": "model-00001-of-00007.safetensors",
819
- "vision_tower.encoder.layer.2.lambda_1": "model-00001-of-00007.safetensors",
820
- "vision_tower.encoder.layer.2.lambda_2": "model-00001-of-00007.safetensors",
821
- "vision_tower.encoder.layer.2.layernorm_after.bias": "model-00001-of-00007.safetensors",
822
- "vision_tower.encoder.layer.2.layernorm_after.weight": "model-00001-of-00007.safetensors",
823
- "vision_tower.encoder.layer.2.layernorm_before.bias": "model-00001-of-00007.safetensors",
824
- "vision_tower.encoder.layer.2.layernorm_before.weight": "model-00001-of-00007.safetensors",
825
- "vision_tower.encoder.layer.2.mlp.fc1.bias": "model-00001-of-00007.safetensors",
826
- "vision_tower.encoder.layer.2.mlp.fc1.weight": "model-00001-of-00007.safetensors",
827
- "vision_tower.encoder.layer.2.mlp.fc2.bias": "model-00001-of-00007.safetensors",
828
- "vision_tower.encoder.layer.2.mlp.fc2.weight": "model-00001-of-00007.safetensors",
829
- "vision_tower.encoder.layer.20.attention.k_proj.bias": "model-00001-of-00007.safetensors",
830
- "vision_tower.encoder.layer.20.attention.k_proj.weight": "model-00001-of-00007.safetensors",
831
- "vision_tower.encoder.layer.20.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
832
- "vision_tower.encoder.layer.20.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
833
- "vision_tower.encoder.layer.20.attention.q_proj.bias": "model-00001-of-00007.safetensors",
834
- "vision_tower.encoder.layer.20.attention.q_proj.weight": "model-00001-of-00007.safetensors",
835
- "vision_tower.encoder.layer.20.attention.v_proj.bias": "model-00001-of-00007.safetensors",
836
- "vision_tower.encoder.layer.20.attention.v_proj.weight": "model-00001-of-00007.safetensors",
837
- "vision_tower.encoder.layer.20.lambda_1": "model-00001-of-00007.safetensors",
838
- "vision_tower.encoder.layer.20.lambda_2": "model-00001-of-00007.safetensors",
839
- "vision_tower.encoder.layer.20.layernorm_after.bias": "model-00001-of-00007.safetensors",
840
- "vision_tower.encoder.layer.20.layernorm_after.weight": "model-00001-of-00007.safetensors",
841
- "vision_tower.encoder.layer.20.layernorm_before.bias": "model-00001-of-00007.safetensors",
842
- "vision_tower.encoder.layer.20.layernorm_before.weight": "model-00001-of-00007.safetensors",
843
- "vision_tower.encoder.layer.20.mlp.fc1.bias": "model-00001-of-00007.safetensors",
844
- "vision_tower.encoder.layer.20.mlp.fc1.weight": "model-00001-of-00007.safetensors",
845
- "vision_tower.encoder.layer.20.mlp.fc2.bias": "model-00001-of-00007.safetensors",
846
- "vision_tower.encoder.layer.20.mlp.fc2.weight": "model-00001-of-00007.safetensors",
847
- "vision_tower.encoder.layer.21.attention.k_proj.bias": "model-00001-of-00007.safetensors",
848
- "vision_tower.encoder.layer.21.attention.k_proj.weight": "model-00001-of-00007.safetensors",
849
- "vision_tower.encoder.layer.21.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
850
- "vision_tower.encoder.layer.21.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
851
- "vision_tower.encoder.layer.21.attention.q_proj.bias": "model-00001-of-00007.safetensors",
852
- "vision_tower.encoder.layer.21.attention.q_proj.weight": "model-00001-of-00007.safetensors",
853
- "vision_tower.encoder.layer.21.attention.v_proj.bias": "model-00001-of-00007.safetensors",
854
- "vision_tower.encoder.layer.21.attention.v_proj.weight": "model-00001-of-00007.safetensors",
855
- "vision_tower.encoder.layer.21.lambda_1": "model-00001-of-00007.safetensors",
856
- "vision_tower.encoder.layer.21.lambda_2": "model-00001-of-00007.safetensors",
857
- "vision_tower.encoder.layer.21.layernorm_after.bias": "model-00001-of-00007.safetensors",
858
- "vision_tower.encoder.layer.21.layernorm_after.weight": "model-00001-of-00007.safetensors",
859
- "vision_tower.encoder.layer.21.layernorm_before.bias": "model-00001-of-00007.safetensors",
860
- "vision_tower.encoder.layer.21.layernorm_before.weight": "model-00001-of-00007.safetensors",
861
- "vision_tower.encoder.layer.21.mlp.fc1.bias": "model-00001-of-00007.safetensors",
862
- "vision_tower.encoder.layer.21.mlp.fc1.weight": "model-00001-of-00007.safetensors",
863
- "vision_tower.encoder.layer.21.mlp.fc2.bias": "model-00001-of-00007.safetensors",
864
- "vision_tower.encoder.layer.21.mlp.fc2.weight": "model-00001-of-00007.safetensors",
865
- "vision_tower.encoder.layer.22.attention.k_proj.bias": "model-00001-of-00007.safetensors",
866
- "vision_tower.encoder.layer.22.attention.k_proj.weight": "model-00001-of-00007.safetensors",
867
- "vision_tower.encoder.layer.22.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
868
- "vision_tower.encoder.layer.22.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
869
- "vision_tower.encoder.layer.22.attention.q_proj.bias": "model-00001-of-00007.safetensors",
870
- "vision_tower.encoder.layer.22.attention.q_proj.weight": "model-00001-of-00007.safetensors",
871
- "vision_tower.encoder.layer.22.attention.v_proj.bias": "model-00001-of-00007.safetensors",
872
- "vision_tower.encoder.layer.22.attention.v_proj.weight": "model-00001-of-00007.safetensors",
873
- "vision_tower.encoder.layer.22.lambda_1": "model-00001-of-00007.safetensors",
874
- "vision_tower.encoder.layer.22.lambda_2": "model-00001-of-00007.safetensors",
875
- "vision_tower.encoder.layer.22.layernorm_after.bias": "model-00001-of-00007.safetensors",
876
- "vision_tower.encoder.layer.22.layernorm_after.weight": "model-00001-of-00007.safetensors",
877
- "vision_tower.encoder.layer.22.layernorm_before.bias": "model-00001-of-00007.safetensors",
878
- "vision_tower.encoder.layer.22.layernorm_before.weight": "model-00001-of-00007.safetensors",
879
- "vision_tower.encoder.layer.22.mlp.fc1.bias": "model-00001-of-00007.safetensors",
880
- "vision_tower.encoder.layer.22.mlp.fc1.weight": "model-00001-of-00007.safetensors",
881
- "vision_tower.encoder.layer.22.mlp.fc2.bias": "model-00001-of-00007.safetensors",
882
- "vision_tower.encoder.layer.22.mlp.fc2.weight": "model-00001-of-00007.safetensors",
883
- "vision_tower.encoder.layer.23.attention.k_proj.bias": "model-00001-of-00007.safetensors",
884
- "vision_tower.encoder.layer.23.attention.k_proj.weight": "model-00001-of-00007.safetensors",
885
- "vision_tower.encoder.layer.23.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
886
- "vision_tower.encoder.layer.23.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
887
- "vision_tower.encoder.layer.23.attention.q_proj.bias": "model-00001-of-00007.safetensors",
888
- "vision_tower.encoder.layer.23.attention.q_proj.weight": "model-00001-of-00007.safetensors",
889
- "vision_tower.encoder.layer.23.attention.v_proj.bias": "model-00001-of-00007.safetensors",
890
- "vision_tower.encoder.layer.23.attention.v_proj.weight": "model-00001-of-00007.safetensors",
891
- "vision_tower.encoder.layer.23.lambda_1": "model-00001-of-00007.safetensors",
892
- "vision_tower.encoder.layer.23.lambda_2": "model-00001-of-00007.safetensors",
893
- "vision_tower.encoder.layer.23.layernorm_after.bias": "model-00001-of-00007.safetensors",
894
- "vision_tower.encoder.layer.23.layernorm_after.weight": "model-00001-of-00007.safetensors",
895
- "vision_tower.encoder.layer.23.layernorm_before.bias": "model-00001-of-00007.safetensors",
896
- "vision_tower.encoder.layer.23.layernorm_before.weight": "model-00001-of-00007.safetensors",
897
- "vision_tower.encoder.layer.23.mlp.fc1.bias": "model-00001-of-00007.safetensors",
898
- "vision_tower.encoder.layer.23.mlp.fc1.weight": "model-00001-of-00007.safetensors",
899
- "vision_tower.encoder.layer.23.mlp.fc2.bias": "model-00001-of-00007.safetensors",
900
- "vision_tower.encoder.layer.23.mlp.fc2.weight": "model-00001-of-00007.safetensors",
901
- "vision_tower.encoder.layer.3.attention.k_proj.bias": "model-00001-of-00007.safetensors",
902
- "vision_tower.encoder.layer.3.attention.k_proj.weight": "model-00001-of-00007.safetensors",
903
- "vision_tower.encoder.layer.3.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
904
- "vision_tower.encoder.layer.3.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
905
- "vision_tower.encoder.layer.3.attention.q_proj.bias": "model-00001-of-00007.safetensors",
906
- "vision_tower.encoder.layer.3.attention.q_proj.weight": "model-00001-of-00007.safetensors",
907
- "vision_tower.encoder.layer.3.attention.v_proj.bias": "model-00001-of-00007.safetensors",
908
- "vision_tower.encoder.layer.3.attention.v_proj.weight": "model-00001-of-00007.safetensors",
909
- "vision_tower.encoder.layer.3.lambda_1": "model-00001-of-00007.safetensors",
910
- "vision_tower.encoder.layer.3.lambda_2": "model-00001-of-00007.safetensors",
911
- "vision_tower.encoder.layer.3.layernorm_after.bias": "model-00001-of-00007.safetensors",
912
- "vision_tower.encoder.layer.3.layernorm_after.weight": "model-00001-of-00007.safetensors",
913
- "vision_tower.encoder.layer.3.layernorm_before.bias": "model-00001-of-00007.safetensors",
914
- "vision_tower.encoder.layer.3.layernorm_before.weight": "model-00001-of-00007.safetensors",
915
- "vision_tower.encoder.layer.3.mlp.fc1.bias": "model-00001-of-00007.safetensors",
916
- "vision_tower.encoder.layer.3.mlp.fc1.weight": "model-00001-of-00007.safetensors",
917
- "vision_tower.encoder.layer.3.mlp.fc2.bias": "model-00001-of-00007.safetensors",
918
- "vision_tower.encoder.layer.3.mlp.fc2.weight": "model-00001-of-00007.safetensors",
919
- "vision_tower.encoder.layer.4.attention.k_proj.bias": "model-00001-of-00007.safetensors",
920
- "vision_tower.encoder.layer.4.attention.k_proj.weight": "model-00001-of-00007.safetensors",
921
- "vision_tower.encoder.layer.4.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
922
- "vision_tower.encoder.layer.4.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
923
- "vision_tower.encoder.layer.4.attention.q_proj.bias": "model-00001-of-00007.safetensors",
924
- "vision_tower.encoder.layer.4.attention.q_proj.weight": "model-00001-of-00007.safetensors",
925
- "vision_tower.encoder.layer.4.attention.v_proj.bias": "model-00001-of-00007.safetensors",
926
- "vision_tower.encoder.layer.4.attention.v_proj.weight": "model-00001-of-00007.safetensors",
927
- "vision_tower.encoder.layer.4.lambda_1": "model-00001-of-00007.safetensors",
928
- "vision_tower.encoder.layer.4.lambda_2": "model-00001-of-00007.safetensors",
929
- "vision_tower.encoder.layer.4.layernorm_after.bias": "model-00001-of-00007.safetensors",
930
- "vision_tower.encoder.layer.4.layernorm_after.weight": "model-00001-of-00007.safetensors",
931
- "vision_tower.encoder.layer.4.layernorm_before.bias": "model-00001-of-00007.safetensors",
932
- "vision_tower.encoder.layer.4.layernorm_before.weight": "model-00001-of-00007.safetensors",
933
- "vision_tower.encoder.layer.4.mlp.fc1.bias": "model-00001-of-00007.safetensors",
934
- "vision_tower.encoder.layer.4.mlp.fc1.weight": "model-00001-of-00007.safetensors",
935
- "vision_tower.encoder.layer.4.mlp.fc2.bias": "model-00001-of-00007.safetensors",
936
- "vision_tower.encoder.layer.4.mlp.fc2.weight": "model-00001-of-00007.safetensors",
937
- "vision_tower.encoder.layer.5.attention.k_proj.bias": "model-00001-of-00007.safetensors",
938
- "vision_tower.encoder.layer.5.attention.k_proj.weight": "model-00001-of-00007.safetensors",
939
- "vision_tower.encoder.layer.5.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
940
- "vision_tower.encoder.layer.5.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
941
- "vision_tower.encoder.layer.5.attention.q_proj.bias": "model-00001-of-00007.safetensors",
942
- "vision_tower.encoder.layer.5.attention.q_proj.weight": "model-00001-of-00007.safetensors",
943
- "vision_tower.encoder.layer.5.attention.v_proj.bias": "model-00001-of-00007.safetensors",
944
- "vision_tower.encoder.layer.5.attention.v_proj.weight": "model-00001-of-00007.safetensors",
945
- "vision_tower.encoder.layer.5.lambda_1": "model-00001-of-00007.safetensors",
946
- "vision_tower.encoder.layer.5.lambda_2": "model-00001-of-00007.safetensors",
947
- "vision_tower.encoder.layer.5.layernorm_after.bias": "model-00001-of-00007.safetensors",
948
- "vision_tower.encoder.layer.5.layernorm_after.weight": "model-00001-of-00007.safetensors",
949
- "vision_tower.encoder.layer.5.layernorm_before.bias": "model-00001-of-00007.safetensors",
950
- "vision_tower.encoder.layer.5.layernorm_before.weight": "model-00001-of-00007.safetensors",
951
- "vision_tower.encoder.layer.5.mlp.fc1.bias": "model-00001-of-00007.safetensors",
952
- "vision_tower.encoder.layer.5.mlp.fc1.weight": "model-00001-of-00007.safetensors",
953
- "vision_tower.encoder.layer.5.mlp.fc2.bias": "model-00001-of-00007.safetensors",
954
- "vision_tower.encoder.layer.5.mlp.fc2.weight": "model-00001-of-00007.safetensors",
955
- "vision_tower.encoder.layer.6.attention.k_proj.bias": "model-00001-of-00007.safetensors",
956
- "vision_tower.encoder.layer.6.attention.k_proj.weight": "model-00001-of-00007.safetensors",
957
- "vision_tower.encoder.layer.6.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
958
- "vision_tower.encoder.layer.6.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
959
- "vision_tower.encoder.layer.6.attention.q_proj.bias": "model-00001-of-00007.safetensors",
960
- "vision_tower.encoder.layer.6.attention.q_proj.weight": "model-00001-of-00007.safetensors",
961
- "vision_tower.encoder.layer.6.attention.v_proj.bias": "model-00001-of-00007.safetensors",
962
- "vision_tower.encoder.layer.6.attention.v_proj.weight": "model-00001-of-00007.safetensors",
963
- "vision_tower.encoder.layer.6.lambda_1": "model-00001-of-00007.safetensors",
964
- "vision_tower.encoder.layer.6.lambda_2": "model-00001-of-00007.safetensors",
965
- "vision_tower.encoder.layer.6.layernorm_after.bias": "model-00001-of-00007.safetensors",
966
- "vision_tower.encoder.layer.6.layernorm_after.weight": "model-00001-of-00007.safetensors",
967
- "vision_tower.encoder.layer.6.layernorm_before.bias": "model-00001-of-00007.safetensors",
968
- "vision_tower.encoder.layer.6.layernorm_before.weight": "model-00001-of-00007.safetensors",
969
- "vision_tower.encoder.layer.6.mlp.fc1.bias": "model-00001-of-00007.safetensors",
970
- "vision_tower.encoder.layer.6.mlp.fc1.weight": "model-00001-of-00007.safetensors",
971
- "vision_tower.encoder.layer.6.mlp.fc2.bias": "model-00001-of-00007.safetensors",
972
- "vision_tower.encoder.layer.6.mlp.fc2.weight": "model-00001-of-00007.safetensors",
973
- "vision_tower.encoder.layer.7.attention.k_proj.bias": "model-00001-of-00007.safetensors",
974
- "vision_tower.encoder.layer.7.attention.k_proj.weight": "model-00001-of-00007.safetensors",
975
- "vision_tower.encoder.layer.7.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
976
- "vision_tower.encoder.layer.7.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
977
- "vision_tower.encoder.layer.7.attention.q_proj.bias": "model-00001-of-00007.safetensors",
978
- "vision_tower.encoder.layer.7.attention.q_proj.weight": "model-00001-of-00007.safetensors",
979
- "vision_tower.encoder.layer.7.attention.v_proj.bias": "model-00001-of-00007.safetensors",
980
- "vision_tower.encoder.layer.7.attention.v_proj.weight": "model-00001-of-00007.safetensors",
981
- "vision_tower.encoder.layer.7.lambda_1": "model-00001-of-00007.safetensors",
982
- "vision_tower.encoder.layer.7.lambda_2": "model-00001-of-00007.safetensors",
983
- "vision_tower.encoder.layer.7.layernorm_after.bias": "model-00001-of-00007.safetensors",
984
- "vision_tower.encoder.layer.7.layernorm_after.weight": "model-00001-of-00007.safetensors",
985
- "vision_tower.encoder.layer.7.layernorm_before.bias": "model-00001-of-00007.safetensors",
986
- "vision_tower.encoder.layer.7.layernorm_before.weight": "model-00001-of-00007.safetensors",
987
- "vision_tower.encoder.layer.7.mlp.fc1.bias": "model-00001-of-00007.safetensors",
988
- "vision_tower.encoder.layer.7.mlp.fc1.weight": "model-00001-of-00007.safetensors",
989
- "vision_tower.encoder.layer.7.mlp.fc2.bias": "model-00001-of-00007.safetensors",
990
- "vision_tower.encoder.layer.7.mlp.fc2.weight": "model-00001-of-00007.safetensors",
991
- "vision_tower.encoder.layer.8.attention.k_proj.bias": "model-00001-of-00007.safetensors",
992
- "vision_tower.encoder.layer.8.attention.k_proj.weight": "model-00001-of-00007.safetensors",
993
- "vision_tower.encoder.layer.8.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
994
- "vision_tower.encoder.layer.8.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
995
- "vision_tower.encoder.layer.8.attention.q_proj.bias": "model-00001-of-00007.safetensors",
996
- "vision_tower.encoder.layer.8.attention.q_proj.weight": "model-00001-of-00007.safetensors",
997
- "vision_tower.encoder.layer.8.attention.v_proj.bias": "model-00001-of-00007.safetensors",
998
- "vision_tower.encoder.layer.8.attention.v_proj.weight": "model-00001-of-00007.safetensors",
999
- "vision_tower.encoder.layer.8.lambda_1": "model-00001-of-00007.safetensors",
1000
- "vision_tower.encoder.layer.8.lambda_2": "model-00001-of-00007.safetensors",
1001
- "vision_tower.encoder.layer.8.layernorm_after.bias": "model-00001-of-00007.safetensors",
1002
- "vision_tower.encoder.layer.8.layernorm_after.weight": "model-00001-of-00007.safetensors",
1003
- "vision_tower.encoder.layer.8.layernorm_before.bias": "model-00001-of-00007.safetensors",
1004
- "vision_tower.encoder.layer.8.layernorm_before.weight": "model-00001-of-00007.safetensors",
1005
- "vision_tower.encoder.layer.8.mlp.fc1.bias": "model-00001-of-00007.safetensors",
1006
- "vision_tower.encoder.layer.8.mlp.fc1.weight": "model-00001-of-00007.safetensors",
1007
- "vision_tower.encoder.layer.8.mlp.fc2.bias": "model-00001-of-00007.safetensors",
1008
- "vision_tower.encoder.layer.8.mlp.fc2.weight": "model-00001-of-00007.safetensors",
1009
- "vision_tower.encoder.layer.9.attention.k_proj.bias": "model-00001-of-00007.safetensors",
1010
- "vision_tower.encoder.layer.9.attention.k_proj.weight": "model-00001-of-00007.safetensors",
1011
- "vision_tower.encoder.layer.9.attention.projection_layer.bias": "model-00001-of-00007.safetensors",
1012
- "vision_tower.encoder.layer.9.attention.projection_layer.weight": "model-00001-of-00007.safetensors",
1013
- "vision_tower.encoder.layer.9.attention.q_proj.bias": "model-00001-of-00007.safetensors",
1014
- "vision_tower.encoder.layer.9.attention.q_proj.weight": "model-00001-of-00007.safetensors",
1015
- "vision_tower.encoder.layer.9.attention.v_proj.bias": "model-00001-of-00007.safetensors",
1016
- "vision_tower.encoder.layer.9.attention.v_proj.weight": "model-00001-of-00007.safetensors",
1017
- "vision_tower.encoder.layer.9.lambda_1": "model-00001-of-00007.safetensors",
1018
- "vision_tower.encoder.layer.9.lambda_2": "model-00001-of-00007.safetensors",
1019
- "vision_tower.encoder.layer.9.layernorm_after.bias": "model-00001-of-00007.safetensors",
1020
- "vision_tower.encoder.layer.9.layernorm_after.weight": "model-00001-of-00007.safetensors",
1021
- "vision_tower.encoder.layer.9.layernorm_before.bias": "model-00001-of-00007.safetensors",
1022
- "vision_tower.encoder.layer.9.layernorm_before.weight": "model-00001-of-00007.safetensors",
1023
- "vision_tower.encoder.layer.9.mlp.fc1.bias": "model-00001-of-00007.safetensors",
1024
- "vision_tower.encoder.layer.9.mlp.fc1.weight": "model-00001-of-00007.safetensors",
1025
- "vision_tower.encoder.layer.9.mlp.fc2.bias": "model-00001-of-00007.safetensors",
1026
- "vision_tower.encoder.layer.9.mlp.fc2.weight": "model-00001-of-00007.safetensors"
1027
- }
1028
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/preprocessor_config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "crop_size": null,
3
- "crop_to_patches": false,
4
- "data_format": "channels_first",
5
- "default_to_square": true,
6
- "device": null,
7
- "do_center_crop": null,
8
- "do_convert_rgb": true,
9
- "do_normalize": true,
10
- "do_rescale": true,
11
- "do_resize": true,
12
- "image_mean": [
13
- 0.485,
14
- 0.456,
15
- 0.406
16
- ],
17
- "image_processor_type": "GotOcr2ImageProcessorFast",
18
- "image_std": [
19
- 0.229,
20
- 0.224,
21
- 0.225
22
- ],
23
- "input_data_format": null,
24
- "max_patches": 12,
25
- "min_patches": 1,
26
- "processor_class": "InternVLProcessor",
27
- "resample": 3,
28
- "rescale_factor": 0.00392156862745098,
29
- "return_tensors": null,
30
- "size": {
31
- "height": 448,
32
- "width": 448
33
- }
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/processor_config.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "image_seq_length": 256,
3
- "processor_class": "InternVLProcessor"
4
- }
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/special_tokens_map.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>",
16
- "<img>",
17
- "</img>",
18
- "<IMG_CONTEXT>",
19
- "<quad>",
20
- "</quad>",
21
- "<ref>",
22
- "</ref>",
23
- "<box>",
24
- "</box>"
25
- ],
26
- "context_image_token": "<IMG_CONTEXT>",
27
- "end_image_token": "</img>",
28
- "eos_token": {
29
- "content": "<|im_end|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- },
35
- "pad_token": {
36
- "content": "<|endoftext|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false
41
- },
42
- "start_image_token": "<img>",
43
- "video_token": "<video>"
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cc80b7e20adf8bf6f6ca442bf1abfac8056bb3b7d3e0b11c9d497d3e79398c9
3
- size 11423732
 
 
 
 
OpenGVLab--InternVL3-14B-hf/tokenizer_config.json DELETED
@@ -1,306 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<img>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "151666": {
190
- "content": "</img>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "151667": {
198
- "content": "<IMG_CONTEXT>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "151668": {
206
- "content": "<quad>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "151669": {
214
- "content": "</quad>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "151670": {
222
- "content": "<ref>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "151671": {
230
- "content": "</ref>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "151672": {
238
- "content": "<box>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "151673": {
246
- "content": "</box>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "151674": {
254
- "content": "<video>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": true
260
- }
261
- },
262
- "additional_special_tokens": [
263
- "<|im_start|>",
264
- "<|im_end|>",
265
- "<|object_ref_start|>",
266
- "<|object_ref_end|>",
267
- "<|box_start|>",
268
- "<|box_end|>",
269
- "<|quad_start|>",
270
- "<|quad_end|>",
271
- "<|vision_start|>",
272
- "<|vision_end|>",
273
- "<|vision_pad|>",
274
- "<|image_pad|>",
275
- "<|video_pad|>",
276
- "<img>",
277
- "</img>",
278
- "<IMG_CONTEXT>",
279
- "<quad>",
280
- "</quad>",
281
- "<ref>",
282
- "</ref>",
283
- "<box>",
284
- "</box>"
285
- ],
286
- "bos_token": null,
287
- "clean_up_tokenization_spaces": false,
288
- "context_image_token": "<IMG_CONTEXT>",
289
- "end_image_token": "</img>",
290
- "eos_token": "<|im_end|>",
291
- "errors": "replace",
292
- "extra_special_tokens": {
293
- "context_image_token": "<IMG_CONTEXT>",
294
- "end_image_token": "</img>",
295
- "start_image_token": "<img>",
296
- "video_token": "<video>"
297
- },
298
- "model_max_length": 8192,
299
- "pad_token": "<|endoftext|>",
300
- "return_token_type_ids": false,
301
- "split_special_tokens": false,
302
- "start_image_token": "<img>",
303
- "tokenizer_class": "Qwen2Tokenizer",
304
- "unk_token": null,
305
- "video_token": "<video>"
306
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-14B-hf/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
OpenGVLab--InternVL3-1B-hf/added_tokens.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "</box>": 151673,
3
- "</img>": 151666,
4
- "</quad>": 151669,
5
- "</ref>": 151671,
6
- "</tool_call>": 151658,
7
- "<IMG_CONTEXT>": 151667,
8
- "<box>": 151672,
9
- "<img>": 151665,
10
- "<quad>": 151668,
11
- "<ref>": 151670,
12
- "<tool_call>": 151657,
13
- "<video>": 151674,
14
- "<|box_end|>": 151649,
15
- "<|box_start|>": 151648,
16
- "<|endoftext|>": 151643,
17
- "<|file_sep|>": 151664,
18
- "<|fim_middle|>": 151660,
19
- "<|fim_pad|>": 151662,
20
- "<|fim_prefix|>": 151659,
21
- "<|fim_suffix|>": 151661,
22
- "<|im_end|>": 151645,
23
- "<|im_start|>": 151644,
24
- "<|image_pad|>": 151655,
25
- "<|object_ref_end|>": 151647,
26
- "<|object_ref_start|>": 151646,
27
- "<|quad_end|>": 151651,
28
- "<|quad_start|>": 151650,
29
- "<|repo_name|>": 151663,
30
- "<|video_pad|>": 151656,
31
- "<|vision_end|>": 151653,
32
- "<|vision_pad|>": 151654,
33
- "<|vision_start|>": 151652
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/chat_template.jinja DELETED
@@ -1,6 +0,0 @@
1
- {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
- '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
3
- ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
- ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
- '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
- ' }}{% endif %}
 
 
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/config.json DELETED
@@ -1,79 +0,0 @@
1
- {
2
- "architectures": [
3
- "InternVLForConditionalGeneration"
4
- ],
5
- "downsample_ratio": 0.5,
6
- "image_seq_length": 256,
7
- "image_token_id": 151667,
8
- "model_type": "internvl",
9
- "projector_hidden_act": "gelu",
10
- "text_config": {
11
- "architectures": [
12
- "Qwen2ForCausalLM"
13
- ],
14
- "attention_dropout": 0.0,
15
- "bos_token_id": 151643,
16
- "eos_token_id": 151645,
17
- "hidden_act": "silu",
18
- "hidden_size": 896,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 4864,
21
- "max_position_embeddings": 32768,
22
- "max_window_layers": 70,
23
- "model_type": "qwen2",
24
- "num_attention_heads": 14,
25
- "num_hidden_layers": 24,
26
- "num_key_value_heads": 2,
27
- "rms_norm_eps": 1e-06,
28
- "rope_scaling": {
29
- "factor": 2.0,
30
- "rope_type": "dynamic",
31
- "type": "dynamic"
32
- },
33
- "rope_theta": 1000000.0,
34
- "sliding_window": null,
35
- "torch_dtype": "bfloat16",
36
- "use_cache": true,
37
- "use_sliding_window": false,
38
- "vocab_size": 151674
39
- },
40
- "torch_dtype": "bfloat16",
41
- "transformers_version": "4.52.0.dev0",
42
- "vision_config": {
43
- "architectures": [
44
- "InternVisionModel"
45
- ],
46
- "attention_bias": true,
47
- "attention_dropout": 0.0,
48
- "dropout": 0.0,
49
- "hidden_act": "gelu",
50
- "hidden_dropout_prob": 0.0,
51
- "hidden_size": 1024,
52
- "image_size": [
53
- 448,
54
- 448
55
- ],
56
- "initializer_factor": 0.1,
57
- "initializer_range": 1e-10,
58
- "intermediate_size": 4096,
59
- "layer_norm_eps": 1e-06,
60
- "layer_scale_init_value": 0.1,
61
- "model_type": "internvl_vision",
62
- "norm_type": "layer_norm",
63
- "num_attention_heads": 16,
64
- "num_channels": 3,
65
- "num_hidden_layers": 24,
66
- "patch_size": [
67
- 14,
68
- 14
69
- ],
70
- "projection_dropout": 0.0,
71
- "torch_dtype": "bfloat16",
72
- "use_absolute_position_embeddings": true,
73
- "use_mask_token": false,
74
- "use_mean_pooling": true,
75
- "use_qk_norm": false
76
- },
77
- "vision_feature_layer": -1,
78
- "vision_feature_select_strategy": "default"
79
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 151643,
4
- "eos_token_id": 151645,
5
- "transformers_version": "4.52.0.dev0"
6
- }
 
 
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
OpenGVLab--InternVL3-1B-hf/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdf8d51c7db5e31938300642b1bebce7f28592a2adefafc931cb8c21a8395517
3
- size 1876478048
 
 
 
 
OpenGVLab--InternVL3-1B-hf/preprocessor_config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "crop_size": null,
3
- "crop_to_patches": false,
4
- "data_format": "channels_first",
5
- "default_to_square": true,
6
- "device": null,
7
- "do_center_crop": null,
8
- "do_convert_rgb": true,
9
- "do_normalize": true,
10
- "do_rescale": true,
11
- "do_resize": true,
12
- "image_mean": [
13
- 0.485,
14
- 0.456,
15
- 0.406
16
- ],
17
- "image_processor_type": "GotOcr2ImageProcessorFast",
18
- "image_std": [
19
- 0.229,
20
- 0.224,
21
- 0.225
22
- ],
23
- "input_data_format": null,
24
- "max_patches": 12,
25
- "min_patches": 1,
26
- "processor_class": "InternVLProcessor",
27
- "resample": 3,
28
- "rescale_factor": 0.00392156862745098,
29
- "return_tensors": null,
30
- "size": {
31
- "height": 448,
32
- "width": 448
33
- }
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/processor_config.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "image_seq_length": 256,
3
- "processor_class": "InternVLProcessor"
4
- }
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/special_tokens_map.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>",
16
- "<img>",
17
- "</img>",
18
- "<IMG_CONTEXT>",
19
- "<quad>",
20
- "</quad>",
21
- "<ref>",
22
- "</ref>",
23
- "<box>",
24
- "</box>"
25
- ],
26
- "context_image_token": "<IMG_CONTEXT>",
27
- "end_image_token": "</img>",
28
- "eos_token": {
29
- "content": "<|im_end|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- },
35
- "pad_token": {
36
- "content": "<|endoftext|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false
41
- },
42
- "start_image_token": "<img>",
43
- "video_token": "<video>"
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cc80b7e20adf8bf6f6ca442bf1abfac8056bb3b7d3e0b11c9d497d3e79398c9
3
- size 11423732
 
 
 
 
OpenGVLab--InternVL3-1B-hf/tokenizer_config.json DELETED
@@ -1,306 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<img>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "151666": {
190
- "content": "</img>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "151667": {
198
- "content": "<IMG_CONTEXT>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "151668": {
206
- "content": "<quad>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "151669": {
214
- "content": "</quad>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "151670": {
222
- "content": "<ref>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "151671": {
230
- "content": "</ref>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "151672": {
238
- "content": "<box>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "151673": {
246
- "content": "</box>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "151674": {
254
- "content": "<video>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": true
260
- }
261
- },
262
- "additional_special_tokens": [
263
- "<|im_start|>",
264
- "<|im_end|>",
265
- "<|object_ref_start|>",
266
- "<|object_ref_end|>",
267
- "<|box_start|>",
268
- "<|box_end|>",
269
- "<|quad_start|>",
270
- "<|quad_end|>",
271
- "<|vision_start|>",
272
- "<|vision_end|>",
273
- "<|vision_pad|>",
274
- "<|image_pad|>",
275
- "<|video_pad|>",
276
- "<img>",
277
- "</img>",
278
- "<IMG_CONTEXT>",
279
- "<quad>",
280
- "</quad>",
281
- "<ref>",
282
- "</ref>",
283
- "<box>",
284
- "</box>"
285
- ],
286
- "bos_token": null,
287
- "clean_up_tokenization_spaces": false,
288
- "context_image_token": "<IMG_CONTEXT>",
289
- "end_image_token": "</img>",
290
- "eos_token": "<|im_end|>",
291
- "errors": "replace",
292
- "extra_special_tokens": {
293
- "context_image_token": "<IMG_CONTEXT>",
294
- "end_image_token": "</img>",
295
- "start_image_token": "<img>",
296
- "video_token": "<video>"
297
- },
298
- "model_max_length": 8192,
299
- "pad_token": "<|endoftext|>",
300
- "return_token_type_ids": false,
301
- "split_special_tokens": false,
302
- "start_image_token": "<img>",
303
- "tokenizer_class": "Qwen2Tokenizer",
304
- "unk_token": null,
305
- "video_token": "<video>"
306
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-1B-hf/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
OpenGVLab--InternVL3-2B-hf/added_tokens.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "</box>": 151673,
3
- "</img>": 151666,
4
- "</quad>": 151669,
5
- "</ref>": 151671,
6
- "</tool_call>": 151658,
7
- "<IMG_CONTEXT>": 151667,
8
- "<box>": 151672,
9
- "<img>": 151665,
10
- "<quad>": 151668,
11
- "<ref>": 151670,
12
- "<tool_call>": 151657,
13
- "<video>": 151674,
14
- "<|box_end|>": 151649,
15
- "<|box_start|>": 151648,
16
- "<|endoftext|>": 151643,
17
- "<|file_sep|>": 151664,
18
- "<|fim_middle|>": 151660,
19
- "<|fim_pad|>": 151662,
20
- "<|fim_prefix|>": 151659,
21
- "<|fim_suffix|>": 151661,
22
- "<|im_end|>": 151645,
23
- "<|im_start|>": 151644,
24
- "<|image_pad|>": 151655,
25
- "<|object_ref_end|>": 151647,
26
- "<|object_ref_start|>": 151646,
27
- "<|quad_end|>": 151651,
28
- "<|quad_start|>": 151650,
29
- "<|repo_name|>": 151663,
30
- "<|video_pad|>": 151656,
31
- "<|vision_end|>": 151653,
32
- "<|vision_pad|>": 151654,
33
- "<|vision_start|>": 151652
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/chat_template.jinja DELETED
@@ -1,6 +0,0 @@
1
- {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
- '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
3
- ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
- ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
- '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
- ' }}{% endif %}
 
 
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/config.json DELETED
@@ -1,79 +0,0 @@
1
- {
2
- "architectures": [
3
- "InternVLForConditionalGeneration"
4
- ],
5
- "downsample_ratio": 0.5,
6
- "image_seq_length": 256,
7
- "image_token_id": 151667,
8
- "model_type": "internvl",
9
- "projector_hidden_act": "gelu",
10
- "text_config": {
11
- "architectures": [
12
- "Qwen2ForCausalLM"
13
- ],
14
- "attention_dropout": 0.0,
15
- "bos_token_id": 151643,
16
- "eos_token_id": 151645,
17
- "hidden_act": "silu",
18
- "hidden_size": 1536,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 8960,
21
- "max_position_embeddings": 32768,
22
- "max_window_layers": 70,
23
- "model_type": "qwen2",
24
- "num_attention_heads": 12,
25
- "num_hidden_layers": 28,
26
- "num_key_value_heads": 2,
27
- "rms_norm_eps": 1e-06,
28
- "rope_scaling": {
29
- "factor": 2.0,
30
- "rope_type": "dynamic",
31
- "type": "dynamic"
32
- },
33
- "rope_theta": 1000000.0,
34
- "sliding_window": null,
35
- "torch_dtype": "bfloat16",
36
- "use_cache": true,
37
- "use_sliding_window": false,
38
- "vocab_size": 151674
39
- },
40
- "torch_dtype": "bfloat16",
41
- "transformers_version": "4.52.0.dev0",
42
- "vision_config": {
43
- "architectures": [
44
- "InternVisionModel"
45
- ],
46
- "attention_bias": true,
47
- "attention_dropout": 0.0,
48
- "dropout": 0.0,
49
- "hidden_act": "gelu",
50
- "hidden_dropout_prob": 0.0,
51
- "hidden_size": 1024,
52
- "image_size": [
53
- 448,
54
- 448
55
- ],
56
- "initializer_factor": 0.1,
57
- "initializer_range": 1e-10,
58
- "intermediate_size": 4096,
59
- "layer_norm_eps": 1e-06,
60
- "layer_scale_init_value": 0.1,
61
- "model_type": "internvl_vision",
62
- "norm_type": "layer_norm",
63
- "num_attention_heads": 16,
64
- "num_channels": 3,
65
- "num_hidden_layers": 24,
66
- "patch_size": [
67
- 14,
68
- 14
69
- ],
70
- "projection_dropout": 0.0,
71
- "torch_dtype": "bfloat16",
72
- "use_absolute_position_embeddings": true,
73
- "use_mask_token": false,
74
- "use_mean_pooling": true,
75
- "use_qk_norm": false
76
- },
77
- "vision_feature_layer": -1,
78
- "vision_feature_select_strategy": "default"
79
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 151643,
4
- "eos_token_id": 151645,
5
- "transformers_version": "4.52.0.dev0"
6
- }
 
 
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
OpenGVLab--InternVL3-2B-hf/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e2c302719a13916a4d276e60fad4fb1c92a57b39dd2ad51af5a63dcf7a16f4a
3
- size 4178013768
 
 
 
 
OpenGVLab--InternVL3-2B-hf/preprocessor_config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "crop_size": null,
3
- "crop_to_patches": false,
4
- "data_format": "channels_first",
5
- "default_to_square": true,
6
- "device": null,
7
- "do_center_crop": null,
8
- "do_convert_rgb": true,
9
- "do_normalize": true,
10
- "do_rescale": true,
11
- "do_resize": true,
12
- "image_mean": [
13
- 0.485,
14
- 0.456,
15
- 0.406
16
- ],
17
- "image_processor_type": "GotOcr2ImageProcessorFast",
18
- "image_std": [
19
- 0.229,
20
- 0.224,
21
- 0.225
22
- ],
23
- "input_data_format": null,
24
- "max_patches": 12,
25
- "min_patches": 1,
26
- "processor_class": "InternVLProcessor",
27
- "resample": 3,
28
- "rescale_factor": 0.00392156862745098,
29
- "return_tensors": null,
30
- "size": {
31
- "height": 448,
32
- "width": 448
33
- }
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/processor_config.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "image_seq_length": 256,
3
- "processor_class": "InternVLProcessor"
4
- }
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/special_tokens_map.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>",
16
- "<img>",
17
- "</img>",
18
- "<IMG_CONTEXT>",
19
- "<quad>",
20
- "</quad>",
21
- "<ref>",
22
- "</ref>",
23
- "<box>",
24
- "</box>"
25
- ],
26
- "context_image_token": "<IMG_CONTEXT>",
27
- "end_image_token": "</img>",
28
- "eos_token": {
29
- "content": "<|im_end|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- },
35
- "pad_token": {
36
- "content": "<|endoftext|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false
41
- },
42
- "start_image_token": "<img>",
43
- "video_token": "<video>"
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cc80b7e20adf8bf6f6ca442bf1abfac8056bb3b7d3e0b11c9d497d3e79398c9
3
- size 11423732
 
 
 
 
OpenGVLab--InternVL3-2B-hf/tokenizer_config.json DELETED
@@ -1,306 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<img>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "151666": {
190
- "content": "</img>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "151667": {
198
- "content": "<IMG_CONTEXT>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "151668": {
206
- "content": "<quad>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "151669": {
214
- "content": "</quad>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "151670": {
222
- "content": "<ref>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "151671": {
230
- "content": "</ref>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "151672": {
238
- "content": "<box>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "151673": {
246
- "content": "</box>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "151674": {
254
- "content": "<video>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": true
260
- }
261
- },
262
- "additional_special_tokens": [
263
- "<|im_start|>",
264
- "<|im_end|>",
265
- "<|object_ref_start|>",
266
- "<|object_ref_end|>",
267
- "<|box_start|>",
268
- "<|box_end|>",
269
- "<|quad_start|>",
270
- "<|quad_end|>",
271
- "<|vision_start|>",
272
- "<|vision_end|>",
273
- "<|vision_pad|>",
274
- "<|image_pad|>",
275
- "<|video_pad|>",
276
- "<img>",
277
- "</img>",
278
- "<IMG_CONTEXT>",
279
- "<quad>",
280
- "</quad>",
281
- "<ref>",
282
- "</ref>",
283
- "<box>",
284
- "</box>"
285
- ],
286
- "bos_token": null,
287
- "clean_up_tokenization_spaces": false,
288
- "context_image_token": "<IMG_CONTEXT>",
289
- "end_image_token": "</img>",
290
- "eos_token": "<|im_end|>",
291
- "errors": "replace",
292
- "extra_special_tokens": {
293
- "context_image_token": "<IMG_CONTEXT>",
294
- "end_image_token": "</img>",
295
- "start_image_token": "<img>",
296
- "video_token": "<video>"
297
- },
298
- "model_max_length": 8192,
299
- "pad_token": "<|endoftext|>",
300
- "return_token_type_ids": false,
301
- "split_special_tokens": false,
302
- "start_image_token": "<img>",
303
- "tokenizer_class": "Qwen2Tokenizer",
304
- "unk_token": null,
305
- "video_token": "<video>"
306
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-2B-hf/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
OpenGVLab--InternVL3-38B-AWQ/added_tokens.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "</box>": 151673,
3
- "</img>": 151666,
4
- "</quad>": 151669,
5
- "</ref>": 151671,
6
- "</tool_call>": 151658,
7
- "<IMG_CONTEXT>": 151667,
8
- "<box>": 151672,
9
- "<img>": 151665,
10
- "<quad>": 151668,
11
- "<ref>": 151670,
12
- "<tool_call>": 151657,
13
- "<|box_end|>": 151649,
14
- "<|box_start|>": 151648,
15
- "<|endoftext|>": 151643,
16
- "<|file_sep|>": 151664,
17
- "<|fim_middle|>": 151660,
18
- "<|fim_pad|>": 151662,
19
- "<|fim_prefix|>": 151659,
20
- "<|fim_suffix|>": 151661,
21
- "<|im_end|>": 151645,
22
- "<|im_start|>": 151644,
23
- "<|image_pad|>": 151655,
24
- "<|object_ref_end|>": 151647,
25
- "<|object_ref_start|>": 151646,
26
- "<|quad_end|>": 151651,
27
- "<|quad_start|>": 151650,
28
- "<|repo_name|>": 151663,
29
- "<|video_pad|>": 151656,
30
- "<|vision_end|>": 151653,
31
- "<|vision_pad|>": 151654,
32
- "<|vision_start|>": 151652
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-38B-AWQ/config.json DELETED
@@ -1,232 +0,0 @@
1
- {
2
- "_commit_hash": null,
3
- "_name_or_path": "/mnt/petrelfs/share_data/wangweiyun/share_internvl/InternVL3-38B",
4
- "architectures": [
5
- "InternVLChatModel"
6
- ],
7
- "auto_map": {
8
- "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
- "AutoModel": "modeling_internvl_chat.InternVLChatModel",
10
- "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
11
- },
12
- "downsample_ratio": 0.5,
13
- "dynamic_image_size": true,
14
- "force_image_size": 448,
15
- "hidden_size": 5120,
16
- "image_fold": null,
17
- "llm_config": {
18
- "_attn_implementation_autoset": true,
19
- "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
20
- "add_cross_attention": false,
21
- "architectures": [
22
- "Qwen2ForCausalLM"
23
- ],
24
- "attention_dropout": 0.0,
25
- "attn_implementation": "eager",
26
- "bad_words_ids": null,
27
- "begin_suppress_tokens": null,
28
- "bos_token_id": 151643,
29
- "chunk_size_feed_forward": 0,
30
- "cross_attention_hidden_size": null,
31
- "decoder_start_token_id": null,
32
- "diversity_penalty": 0.0,
33
- "do_sample": false,
34
- "early_stopping": false,
35
- "encoder_no_repeat_ngram_size": 0,
36
- "eos_token_id": 151643,
37
- "exponential_decay_length_penalty": null,
38
- "finetuning_task": null,
39
- "forced_bos_token_id": null,
40
- "forced_eos_token_id": null,
41
- "hidden_act": "silu",
42
- "hidden_size": 5120,
43
- "id2label": {
44
- "0": "LABEL_0",
45
- "1": "LABEL_1"
46
- },
47
- "initializer_range": 0.02,
48
- "intermediate_size": 27648,
49
- "is_decoder": false,
50
- "is_encoder_decoder": false,
51
- "label2id": {
52
- "LABEL_0": 0,
53
- "LABEL_1": 1
54
- },
55
- "length_penalty": 1.0,
56
- "max_length": 20,
57
- "max_position_embeddings": 32768,
58
- "max_window_layers": 70,
59
- "min_length": 0,
60
- "model_type": "qwen2",
61
- "moe_config": null,
62
- "no_repeat_ngram_size": 0,
63
- "num_attention_heads": 40,
64
- "num_beam_groups": 1,
65
- "num_beams": 1,
66
- "num_hidden_layers": 64,
67
- "num_key_value_heads": 8,
68
- "num_return_sequences": 1,
69
- "output_attentions": false,
70
- "output_hidden_states": false,
71
- "output_scores": false,
72
- "pad_token_id": null,
73
- "prefix": null,
74
- "problem_type": null,
75
- "pruned_heads": {},
76
- "quantization_config": {
77
- "bits": 4,
78
- "group_size": 128,
79
- "quant_method": "awq",
80
- "version": "gemm",
81
- "zero_point": true
82
- },
83
- "remove_invalid_values": false,
84
- "repetition_penalty": 1.0,
85
- "return_dict": true,
86
- "return_dict_in_generate": false,
87
- "rms_norm_eps": 1e-06,
88
- "rope_scaling": {
89
- "factor": 2.0,
90
- "rope_type": "dynamic",
91
- "type": "dynamic"
92
- },
93
- "rope_theta": 1000000.0,
94
- "sep_token_id": null,
95
- "sliding_window": null,
96
- "suppress_tokens": null,
97
- "task_specific_params": null,
98
- "temperature": 1.0,
99
- "tf_legacy_loss": false,
100
- "tie_encoder_decoder": false,
101
- "tie_word_embeddings": false,
102
- "tokenizer_class": null,
103
- "top_k": 50,
104
- "top_p": 1.0,
105
- "torch_dtype": "bfloat16",
106
- "torchscript": false,
107
- "transformers_version": "4.45.1",
108
- "typical_p": 1.0,
109
- "use_bfloat16": true,
110
- "use_cache": false,
111
- "use_sliding_window": false,
112
- "vocab_size": 151674
113
- },
114
- "max_dynamic_patch": 12,
115
- "min_dynamic_patch": 1,
116
- "model_type": "internvl_chat",
117
- "pad2square": false,
118
- "ps_version": "v2",
119
- "select_layer": -1,
120
- "system_message": null,
121
- "template": "internvl2_5",
122
- "tie_word_embeddings": false,
123
- "torch_dtype": "float16",
124
- "transformers_version": null,
125
- "use_backbone_lora": 0,
126
- "use_llm_lora": 0,
127
- "use_thumbnail": true,
128
- "vision_config": {
129
- "_attn_implementation_autoset": true,
130
- "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
131
- "add_cross_attention": false,
132
- "architectures": [
133
- "InternVisionModel"
134
- ],
135
- "attention_dropout": 0.0,
136
- "auto_map": {
137
- "AutoConfig": "configuration_intern_vit.InternVisionConfig",
138
- "AutoModel": "modeling_intern_vit.InternVisionModel"
139
- },
140
- "bad_words_ids": null,
141
- "begin_suppress_tokens": null,
142
- "bos_token_id": null,
143
- "capacity_factor": 1.2,
144
- "chunk_size_feed_forward": 0,
145
- "cross_attention_hidden_size": null,
146
- "decoder_start_token_id": null,
147
- "diversity_penalty": 0.0,
148
- "do_sample": false,
149
- "drop_path_rate": 0.4,
150
- "dropout": 0.0,
151
- "early_stopping": false,
152
- "encoder_no_repeat_ngram_size": 0,
153
- "eos_token_id": null,
154
- "eval_capacity_factor": 1.4,
155
- "exponential_decay_length_penalty": null,
156
- "finetuning_task": null,
157
- "forced_bos_token_id": null,
158
- "forced_eos_token_id": null,
159
- "hidden_act": "gelu",
160
- "hidden_size": 3200,
161
- "id2label": {
162
- "0": "LABEL_0",
163
- "1": "LABEL_1"
164
- },
165
- "image_size": 448,
166
- "initializer_factor": 0.1,
167
- "initializer_range": 1e-10,
168
- "intermediate_size": 12800,
169
- "is_decoder": false,
170
- "is_encoder_decoder": false,
171
- "label2id": {
172
- "LABEL_0": 0,
173
- "LABEL_1": 1
174
- },
175
- "laux_allreduce": "all_nodes",
176
- "layer_norm_eps": 1e-06,
177
- "length_penalty": 1.0,
178
- "max_length": 20,
179
- "min_length": 0,
180
- "model_type": "intern_vit_6b",
181
- "moe_coeff_ratio": 0.5,
182
- "moe_intermediate_size": 768,
183
- "moe_output_scale": 4.0,
184
- "no_repeat_ngram_size": 0,
185
- "noisy_gate_policy": "RSample_before",
186
- "norm_type": "rms_norm",
187
- "num_attention_heads": 25,
188
- "num_beam_groups": 1,
189
- "num_beams": 1,
190
- "num_channels": 3,
191
- "num_experts": 8,
192
- "num_hidden_layers": 45,
193
- "num_return_sequences": 1,
194
- "num_routed_experts": 4,
195
- "num_shared_experts": 4,
196
- "output_attentions": false,
197
- "output_hidden_states": false,
198
- "output_scores": false,
199
- "pad_token_id": null,
200
- "patch_size": 14,
201
- "prefix": null,
202
- "problem_type": null,
203
- "pruned_heads": {},
204
- "qk_normalization": true,
205
- "qkv_bias": false,
206
- "remove_invalid_values": false,
207
- "repetition_penalty": 1.0,
208
- "return_dict": true,
209
- "return_dict_in_generate": false,
210
- "sep_token_id": null,
211
- "shared_expert_intermediate_size": 3072,
212
- "suppress_tokens": null,
213
- "task_specific_params": null,
214
- "temperature": 1.0,
215
- "tf_legacy_loss": false,
216
- "tie_encoder_decoder": false,
217
- "tie_word_embeddings": true,
218
- "tokenizer_class": null,
219
- "top_k": 50,
220
- "top_p": 1.0,
221
- "torch_dtype": "bfloat16",
222
- "torchscript": false,
223
- "transformers_version": "4.45.1",
224
- "typical_p": 1.0,
225
- "use_bfloat16": true,
226
- "use_flash_attn": true,
227
- "use_moe": false,
228
- "use_residual": true,
229
- "use_rts": false,
230
- "use_weighted_residual": false
231
- }
232
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-38B-AWQ/configuration_intern_vit.py DELETED
@@ -1,120 +0,0 @@
1
- # --------------------------------------------------------
2
- # InternVL
3
- # Copyright (c) 2024 OpenGVLab
4
- # Licensed under The MIT License [see LICENSE for details]
5
- # --------------------------------------------------------
6
-
7
- import os
8
- from typing import Union
9
-
10
- from transformers.configuration_utils import PretrainedConfig
11
- from transformers.utils import logging
12
-
13
- logger = logging.get_logger(__name__)
14
-
15
-
16
- class InternVisionConfig(PretrainedConfig):
17
- r"""
18
- This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
19
- instantiate a vision encoder according to the specified arguments, defining the model architecture.
20
-
21
- Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
22
- documentation from [`PretrainedConfig`] for more information.
23
-
24
- Args:
25
- num_channels (`int`, *optional*, defaults to 3):
26
- Number of color channels in the input images (e.g., 3 for RGB).
27
- patch_size (`int`, *optional*, defaults to 14):
28
- The size (resolution) of each patch.
29
- image_size (`int`, *optional*, defaults to 224):
30
- The size (resolution) of each image.
31
- qkv_bias (`bool`, *optional*, defaults to `False`):
32
- Whether to add a bias to the queries and values in the self-attention layers.
33
- hidden_size (`int`, *optional*, defaults to 3200):
34
- Dimensionality of the encoder layers and the pooler layer.
35
- num_attention_heads (`int`, *optional*, defaults to 25):
36
- Number of attention heads for each attention layer in the Transformer encoder.
37
- intermediate_size (`int`, *optional*, defaults to 12800):
38
- Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
39
- qk_normalization (`bool`, *optional*, defaults to `True`):
40
- Whether to normalize the queries and keys in the self-attention layers.
41
- num_hidden_layers (`int`, *optional*, defaults to 48):
42
- Number of hidden layers in the Transformer encoder.
43
- use_flash_attn (`bool`, *optional*, defaults to `True`):
44
- Whether to use flash attention mechanism.
45
- hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
46
- The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
47
- `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
48
- layer_norm_eps (`float`, *optional*, defaults to 1e-6):
49
- The epsilon used by the layer normalization layers.
50
- dropout (`float`, *optional*, defaults to 0.0):
51
- The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
52
- drop_path_rate (`float`, *optional*, defaults to 0.0):
53
- Dropout rate for stochastic depth.
54
- attention_dropout (`float`, *optional*, defaults to 0.0):
55
- The dropout ratio for the attention probabilities.
56
- initializer_range (`float`, *optional*, defaults to 0.02):
57
- The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
58
- initializer_factor (`float`, *optional*, defaults to 0.1):
59
- A factor for layer scale.
60
- """
61
-
62
- model_type = 'intern_vit_6b'
63
-
64
- def __init__(
65
- self,
66
- num_channels=3,
67
- patch_size=14,
68
- image_size=224,
69
- qkv_bias=False,
70
- hidden_size=3200,
71
- num_attention_heads=25,
72
- intermediate_size=12800,
73
- qk_normalization=True,
74
- num_hidden_layers=48,
75
- use_flash_attn=True,
76
- hidden_act='gelu',
77
- norm_type='rms_norm',
78
- layer_norm_eps=1e-6,
79
- dropout=0.0,
80
- drop_path_rate=0.0,
81
- attention_dropout=0.0,
82
- initializer_range=0.02,
83
- initializer_factor=0.1,
84
- **kwargs,
85
- ):
86
- super().__init__(**kwargs)
87
-
88
- self.hidden_size = hidden_size
89
- self.intermediate_size = intermediate_size
90
- self.dropout = dropout
91
- self.drop_path_rate = drop_path_rate
92
- self.num_hidden_layers = num_hidden_layers
93
- self.num_attention_heads = num_attention_heads
94
- self.num_channels = num_channels
95
- self.patch_size = patch_size
96
- self.image_size = image_size
97
- self.initializer_range = initializer_range
98
- self.initializer_factor = initializer_factor
99
- self.attention_dropout = attention_dropout
100
- self.layer_norm_eps = layer_norm_eps
101
- self.hidden_act = hidden_act
102
- self.norm_type = norm_type
103
- self.qkv_bias = qkv_bias
104
- self.qk_normalization = qk_normalization
105
- self.use_flash_attn = use_flash_attn
106
-
107
- @classmethod
108
- def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
109
- config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
110
-
111
- if 'vision_config' in config_dict:
112
- config_dict = config_dict['vision_config']
113
-
114
- if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
115
- logger.warning(
116
- f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
117
- f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
118
- )
119
-
120
- return cls.from_dict(config_dict, **kwargs)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-38B-AWQ/configuration_internvl_chat.py DELETED
@@ -1,97 +0,0 @@
1
- # --------------------------------------------------------
2
- # InternVL
3
- # Copyright (c) 2024 OpenGVLab
4
- # Licensed under The MIT License [see LICENSE for details]
5
- # --------------------------------------------------------
6
-
7
- import copy
8
-
9
- from transformers import AutoConfig, LlamaConfig, Qwen2Config
10
- from transformers.configuration_utils import PretrainedConfig
11
- from transformers.utils import logging
12
-
13
- from .configuration_intern_vit import InternVisionConfig
14
-
15
- logger = logging.get_logger(__name__)
16
-
17
-
18
- class InternVLChatConfig(PretrainedConfig):
19
- model_type = 'internvl_chat'
20
- is_composition = True
21
-
22
- def __init__(
23
- self,
24
- vision_config=None,
25
- llm_config=None,
26
- use_backbone_lora=0,
27
- use_llm_lora=0,
28
- select_layer=-1,
29
- force_image_size=None,
30
- downsample_ratio=0.5,
31
- template=None,
32
- dynamic_image_size=False,
33
- use_thumbnail=False,
34
- ps_version='v1',
35
- min_dynamic_patch=1,
36
- max_dynamic_patch=6,
37
- **kwargs):
38
- super().__init__(**kwargs)
39
-
40
- if vision_config is None:
41
- vision_config = {'architectures': ['InternVisionModel']}
42
- logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
43
-
44
- if llm_config is None:
45
- llm_config = {'architectures': ['Qwen2ForCausalLM']}
46
- logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
47
-
48
- self.vision_config = InternVisionConfig(**vision_config)
49
- if llm_config.get('architectures')[0] == 'LlamaForCausalLM':
50
- self.llm_config = LlamaConfig(**llm_config)
51
- elif llm_config.get('architectures')[0] == 'Qwen2ForCausalLM':
52
- self.llm_config = Qwen2Config(**llm_config)
53
- else:
54
- raise ValueError('Unsupported architecture: {}'.format(llm_config.get('architectures')[0]))
55
- self.use_backbone_lora = use_backbone_lora
56
- self.use_llm_lora = use_llm_lora
57
- self.select_layer = select_layer
58
- self.force_image_size = force_image_size
59
- self.downsample_ratio = downsample_ratio
60
- self.template = template
61
- self.dynamic_image_size = dynamic_image_size
62
- self.use_thumbnail = use_thumbnail
63
- self.ps_version = ps_version # pixel shuffle version
64
- self.min_dynamic_patch = min_dynamic_patch
65
- self.max_dynamic_patch = max_dynamic_patch
66
- # By default, we use tie_word_embeddings=False for models of all sizes.
67
- self.tie_word_embeddings = self.llm_config.tie_word_embeddings
68
-
69
- logger.info(f'vision_select_layer: {self.select_layer}')
70
- logger.info(f'ps_version: {self.ps_version}')
71
- logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
72
- logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
73
-
74
- def to_dict(self):
75
- """
76
- Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
77
-
78
- Returns:
79
- `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
80
- """
81
- output = copy.deepcopy(self.__dict__)
82
- output['vision_config'] = self.vision_config.to_dict()
83
- output['llm_config'] = self.llm_config.to_dict()
84
- output['model_type'] = self.__class__.model_type
85
- output['use_backbone_lora'] = self.use_backbone_lora
86
- output['use_llm_lora'] = self.use_llm_lora
87
- output['select_layer'] = self.select_layer
88
- output['force_image_size'] = self.force_image_size
89
- output['downsample_ratio'] = self.downsample_ratio
90
- output['template'] = self.template
91
- output['dynamic_image_size'] = self.dynamic_image_size
92
- output['use_thumbnail'] = self.use_thumbnail
93
- output['ps_version'] = self.ps_version
94
- output['min_dynamic_patch'] = self.min_dynamic_patch
95
- output['max_dynamic_patch'] = self.max_dynamic_patch
96
-
97
- return output
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
OpenGVLab--InternVL3-38B-AWQ/generation_config.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "transformers_version": "4.48.3"
4
- }
 
 
 
 
 
OpenGVLab--InternVL3-38B-AWQ/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
OpenGVLab--InternVL3-38B-AWQ/preprocessor_config.json DELETED
@@ -1,19 +0,0 @@
1
- {
2
- "crop_size": 448,
3
- "do_center_crop": true,
4
- "do_normalize": true,
5
- "do_resize": true,
6
- "feature_extractor_type": "CLIPFeatureExtractor",
7
- "image_mean": [
8
- 0.485,
9
- 0.456,
10
- 0.406
11
- ],
12
- "image_std": [
13
- 0.229,
14
- 0.224,
15
- 0.225
16
- ],
17
- "resample": 3,
18
- "size": 448
19
- }