Hugging Face's logo

SVECTOR-CORPORATION
/
Spec-2

Image-Text-to-Text
Safetensors
English
spec2
Spec
Spec-2
Model card Files
xet
Community
SVECTOR-OFFICIAL commited on
Commit
33c60bf
·
verified ·
1 Parent(s): 781d09e

Upload 13 files

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. config.json +54 -0
  3. generation_config.json +8 -0
  4. model-00001-of-00004.safetensors +3 -0
  5. model-00002-of-00004.safetensors +3 -0
  6. model-00003-of-00004.safetensors +3 -0
  7. model-00004-of-00004.safetensors +3 -0
  8. model.safetensors.index.json +910 -0
  9. preprocessor_config.json +25 -0
  10. spec2_processor.py +204 -0
  11. spec2_tokenizer.py +258 -0
  12. special_tokens_map.json +39 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_vocab_size": 257152,
3
+ "architectures": [
4
+ "Spec2ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 2,
7
+ "eos_token_id": 1,
8
+ "image_token_index": 257152,
9
+ "model_type": "spec2",
10
+ "num_hidden_layers": 42,
11
+ "pad_token_id": 0,
12
+ "projection_dim": 3584,
13
+ "text_config": {
14
+ "architectures": [
15
+ "Spec2ForCausalLM"
16
+ ],
17
+ "attn_logit_softcapping": 50.0,
18
+ "cache_implementation": "hybrid",
19
+ "eos_token_id": [
20
+ 1,
21
+ 107
22
+ ],
23
+ "final_logit_softcapping": 30.0,
24
+ "hidden_act": "gelu_pytorch_tanh",
25
+ "hidden_activation": "gelu_pytorch_tanh",
26
+ "hidden_size": 3584,
27
+ "intermediate_size": 14336,
28
+ "model_type": "spec2",
29
+ "num_attention_heads": 16,
30
+ "num_hidden_layers": 42,
31
+ "num_image_tokens": 1024,
32
+ "num_key_value_heads": 8,
33
+ "query_pre_attn_scalar": 256,
34
+ "sliding_window": 4096,
35
+ "torch_dtype": "bfloat16",
36
+ "vocab_size": 257216
37
+ },
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.47.0.dev0",
40
+ "vision_config": {
41
+ "hidden_size": 1152,
42
+ "image_size": 448,
43
+ "intermediate_size": 4304,
44
+ "model_type": "spec2_vision_model",
45
+ "num_attention_heads": 16,
46
+ "num_hidden_layers": 27,
47
+ "num_image_tokens": 1024,
48
+ "num_positions": 1024,
49
+ "patch_size": 14,
50
+ "projection_dim": 3584,
51
+ "torch_dtype": "bfloat16",
52
+ "vision_use_head": false
53
+ }
54
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.47.0.dev0"
8
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff25264a99bb491b0def8f2b54dfa1902039eebd73e8e2a10d8bac062b8e602
3
+ size 4954265240
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c88cb9b084c8c4c13bdf7ae8c73fee9642d2a21cc620bd22b7401815b8dc78
3
+ size 4947572960
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7294db3e17bd03b74ba5613f5c22ea0260e7819e7898c68cbb11db686dc14f
3
+ size 4962223472
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faea080b43b56a18b86e4070f3aad6d290e75f3f4860b52367840bac2a7dd9c2
3
+ size 4463107504
model.safetensors.index.json ADDED
@@ -0,0 +1,910 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 19327047136
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
29
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
125
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
126
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
140
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
141
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
142
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
143
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
144
+ "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
145
+ "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
147
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
148
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
149
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
150
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
218
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
219
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
220
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
221
+ "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
222
+ "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
224
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
235
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
247
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
255
+ "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
257
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
258
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
272
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
273
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
274
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
275
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
276
+ "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
277
+ "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
278
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
279
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
280
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
281
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
282
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
283
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
284
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
285
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
286
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
287
+ "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
288
+ "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
289
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
290
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
291
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
292
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
293
+ "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
294
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
295
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
296
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
297
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
298
+ "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
299
+ "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
300
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
301
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
302
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
303
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
304
+ "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
305
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
306
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
307
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
308
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
309
+ "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
310
+ "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
311
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
312
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
313
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
314
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
315
+ "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
316
+ "language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
317
+ "language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
318
+ "language_model.model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
319
+ "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
320
+ "language_model.model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
321
+ "language_model.model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
322
+ "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
323
+ "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
324
+ "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
325
+ "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
326
+ "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
327
+ "language_model.model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
328
+ "language_model.model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
329
+ "language_model.model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
330
+ "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
331
+ "language_model.model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
332
+ "language_model.model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
334
+ "language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
335
+ "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
336
+ "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
337
+ "language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
338
+ "language_model.model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
339
+ "language_model.model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
340
+ "language_model.model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
341
+ "language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
342
+ "language_model.model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
343
+ "language_model.model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
344
+ "language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
345
+ "language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
346
+ "language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
347
+ "language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
348
+ "language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
349
+ "language_model.model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
350
+ "language_model.model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
351
+ "language_model.model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
352
+ "language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
353
+ "language_model.model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
354
+ "language_model.model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
355
+ "language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
356
+ "language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
357
+ "language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
358
+ "language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
359
+ "language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
360
+ "language_model.model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
361
+ "language_model.model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
362
+ "language_model.model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
363
+ "language_model.model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
364
+ "language_model.model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
365
+ "language_model.model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
366
+ "language_model.model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
367
+ "language_model.model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
368
+ "language_model.model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
369
+ "language_model.model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
370
+ "language_model.model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
371
+ "language_model.model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
372
+ "language_model.model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
373
+ "language_model.model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
374
+ "language_model.model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
375
+ "language_model.model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
376
+ "language_model.model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
377
+ "language_model.model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
378
+ "language_model.model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
379
+ "language_model.model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
380
+ "language_model.model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
381
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
382
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
383
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
384
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
385
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
386
+ "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
387
+ "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
388
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
389
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
390
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
391
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
392
+ "language_model.model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
393
+ "language_model.model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
394
+ "language_model.model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
395
+ "language_model.model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
396
+ "language_model.model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
397
+ "language_model.model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
398
+ "language_model.model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
399
+ "language_model.model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
400
+ "language_model.model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
401
+ "language_model.model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
402
+ "language_model.model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
403
+ "language_model.model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
404
+ "language_model.model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
405
+ "language_model.model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
406
+ "language_model.model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
407
+ "language_model.model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
408
+ "language_model.model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
409
+ "language_model.model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
410
+ "language_model.model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
411
+ "language_model.model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
412
+ "language_model.model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
413
+ "language_model.model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
414
+ "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
415
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
416
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
417
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
418
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
419
+ "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
420
+ "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
421
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
422
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
423
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
424
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
425
+ "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
426
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
427
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
428
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
429
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
430
+ "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
431
+ "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
432
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
433
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
434
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
435
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
436
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
437
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
438
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
439
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
440
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
441
+ "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
442
+ "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
443
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
444
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
445
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
446
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
447
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
448
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
449
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
450
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
451
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
452
+ "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
453
+ "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
454
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
455
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
456
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
457
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
458
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
459
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
460
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
461
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
462
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
463
+ "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
464
+ "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
465
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
466
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
467
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
468
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
469
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
470
+ "multi_modal_projector.linear.bias": "model-00001-of-00004.safetensors",
471
+ "multi_modal_projector.linear.weight": "model-00001-of-00004.safetensors",
472
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
473
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
474
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
689
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
690
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
691
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
692
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
693
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
694
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
695
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
696
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
697
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
698
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
699
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
700
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
701
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
702
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
703
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
704
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
705
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
706
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
707
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
708
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
709
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
710
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
711
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
712
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
713
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
714
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
715
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
716
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
717
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
718
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
719
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
720
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
721
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
722
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
723
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
724
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
725
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
726
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
727
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
728
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
729
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
730
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
731
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
732
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
733
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
734
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
735
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
736
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
737
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
738
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
739
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
740
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
741
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
742
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
743
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
744
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
745
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
746
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
747
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
748
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
749
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
750
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
751
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
752
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
753
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
754
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
755
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
756
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
757
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
758
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
759
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
760
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
761
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
762
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
763
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
764
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
769
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
770
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
771
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
772
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
773
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
774
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
775
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
776
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
777
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
778
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
779
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
780
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
781
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
782
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
783
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
784
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
785
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
786
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
787
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
788
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
789
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
790
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
791
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
792
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
793
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
794
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
795
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
796
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
797
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
798
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
799
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
800
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
801
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
802
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
803
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
804
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
805
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
806
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
807
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
808
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
809
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
810
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
811
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
812
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
813
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
814
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
815
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
816
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
817
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
818
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
819
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
820
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
821
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
822
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
823
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
824
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
825
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
826
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
827
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
828
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
829
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
830
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
831
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
832
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
833
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
834
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
835
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
836
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
837
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
838
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
839
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
840
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
841
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
842
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
843
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
844
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
845
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
846
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
847
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
848
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
849
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
850
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
851
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
852
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
853
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
854
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
855
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
856
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
857
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
858
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
859
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
860
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
861
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
862
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
863
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
864
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
865
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
866
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
867
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
868
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
869
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
870
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
871
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
872
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
873
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
874
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
875
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
876
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
877
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
878
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
879
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
880
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
881
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
882
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
883
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
884
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
885
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
886
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
887
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
888
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
889
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
890
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
891
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
892
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
893
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
894
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
895
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
896
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
897
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
898
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
899
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
900
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
901
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
902
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
903
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
904
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
905
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
906
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
907
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
908
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
909
+ }
910
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "image_processor_type": "Spec2ImageProcessor",
17
+ "image_seq_length": 1024,
18
+ "processor_class": "Spec2Processor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 448,
23
+ "width": 448
24
+ }
25
+ }
spec2_processor.py ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright 2025 SVECTOR AI and The Spec-2 Authors. All rights reserved.
2
+ #
3
+ # Licensed under the Apache License, Version 2.0 (the "License");
4
+ # you may not use this file except in compliance with the License.
5
+ # You may obtain a copy of the License at
6
+ #
7
+ # http://www.apache.org/licenses/LICENSE-2.0
8
+ #
9
+ # Unless required by applicable law or agreed to in writing, software
10
+ # distributed under the License is distributed on an "AS IS" BASIS,
11
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12
+ # See the License for the specific language governing permissions and
13
+ # limitations under the License.
14
+
15
+ from typing import Dict, List, Optional, Union
16
+
17
+ import numpy as np
18
+ import PIL.Image
19
+ import torch
20
+ from transformers import ProcessorMixin
21
+ from transformers.image_utils import PILImageResampling, is_vision_available
22
+
23
+ from .image_processor import Spec2ImageProcessor
24
+ from .tokenizer import Spec2Tokenizer
25
+
26
+
27
+ if is_vision_available():
28
+ from PIL import Image
29
+
30
+
31
+ class Spec2Processor(ProcessorMixin):
32
+ """
33
+ Constructs a Spec2 processor which combines a Spec2 image processor and a Spec2 tokenizer into a single processor.
34
+
35
+ The processor can be used to prepare inputs for the model by processing text and images appropriately.
36
+
37
+ Args:
38
+ image_processor (`Spec2ImageProcessor`):
39
+ An instance of `Spec2ImageProcessor`.
40
+ tokenizer (`Spec2Tokenizer`):
41
+ An instance of `Spec2Tokenizer`.
42
+ """
43
+
44
+ attributes = ["image_processor", "tokenizer"]
45
+ image_processor_class = "Spec2ImageProcessor"
46
+ tokenizer_class = "Spec2Tokenizer"
47
+
48
+ def __init__(self, image_processor, tokenizer):
49
+ if not is_vision_available():
50
+ raise ImportError("Vision libraries are not available. Make sure to install PIL and Pillow: pip install Pillow")
51
+
52
+ self.image_processor = image_processor
53
+ self.tokenizer = tokenizer
54
+ self.image_token = self.tokenizer.image_token
55
+ self.image_token_id = self.tokenizer.image_token_id
56
+
57
+ def __call__(
58
+ self,
59
+ text=None,
60
+ images=None,
61
+ return_tensors=None,
62
+ **kwargs
63
+ ):
64
+ """
65
+ Process text and images for the model.
66
+
67
+ Args:
68
+ text (`str`, `List[str]`, `List[List[str]]`):
69
+ The text to be processed. Can be a string, a list of strings or a list of lists of strings.
70
+ images (`PIL.Image.Image`, `List[PIL.Image.Image]`, `torch.Tensor`, `List[torch.Tensor]`):
71
+ The images to be processed. Can be a PIL Image, a list of PIL Images, a tensor or a list of tensors.
72
+ return_tensors (`str`, optional):
73
+ The type of tensors to return. Can be one of: 'pt' (PyTorch), 'tf' (TensorFlow), 'np' (NumPy).
74
+
75
+ Returns:
76
+ A dictionary containing the processed inputs with keys like 'input_ids', 'attention_mask', 'pixel_values', etc.
77
+ """
78
+ encoding = {}
79
+
80
+ # Process text inputs
81
+ if text is not None:
82
+ text_inputs = self._process_text(text, **kwargs)
83
+ encoding.update(text_inputs)
84
+
85
+ # Process image inputs
86
+ if images is not None:
87
+ image_features = self._process_images(images, **kwargs)
88
+ encoding.update(image_features)
89
+
90
+ # Handle multimodal case - if we have both text and images
91
+ if text is not None and images is not None:
92
+ encoding = self._merge_text_and_image_features(encoding, **kwargs)
93
+
94
+ # Convert to tensors if requested
95
+ if return_tensors is not None:
96
+ encoding = self._convert_to_tensors(encoding, return_tensors=return_tensors)
97
+
98
+ return encoding
99
+
100
+ def _process_text(self, text, **kwargs):
101
+ """Process text inputs."""
102
+ if isinstance(text, str):
103
+ # Check if text already contains image token
104
+ if self.image_token not in text:
105
+ # For single text with images, we add the image token at the end
106
+ text = f"{text} {self.image_token}"
107
+ elif isinstance(text, list):
108
+ # For a list of texts, add image token if not already present
109
+ if all(isinstance(t, str) for t in text):
110
+ text = [f"{t} {self.image_token}" if self.image_token not in t else t for t in text]
111
+
112
+ # Tokenize text
113
+ text_encoding = self.tokenizer(text, return_tensors=None, **kwargs)
114
+ return text_encoding
115
+
116
+ def _process_images(self, images, **kwargs):
117
+ """Process image inputs."""
118
+ # Convert single image to list
119
+ if not isinstance(images, list):
120
+ images = [images]
121
+
122
+ # Process images with image processor
123
+ image_features = self.image_processor(images, return_tensors=None, **kwargs)
124
+ return image_features
125
+
126
+ def _merge_text_and_image_features(self, encoding, **kwargs):
127
+ """Merge text and image features for multimodal inputs."""
128
+ # This function handles the specific logic for merging text tokens with image embeddings
129
+ # For Spec-2, we maintain the tokens order and ensure image token is properly placed
130
+
131
+ input_ids = encoding.get("input_ids", [])
132
+ pixel_values = encoding.get("pixel_values", [])
133
+
134
+ if isinstance(input_ids[0], list): # batch case
135
+ batch_size = len(input_ids)
136
+ merged_encoding = {
137
+ "input_ids": input_ids,
138
+ "pixel_values": pixel_values,
139
+ "image_token_indices": []
140
+ }
141
+
142
+ # For each item in the batch, find the position of the image token
143
+ for i, ids in enumerate(input_ids):
144
+ image_token_indices = [j for j, id_val in enumerate(ids) if id_val == self.image_token_id]
145
+ if image_token_indices:
146
+ merged_encoding["image_token_indices"].append(image_token_indices[0])
147
+ else:
148
+ # If no image token found, append it at the end
149
+ input_ids[i].append(self.image_token_id)
150
+ merged_encoding["image_token_indices"].append(len(input_ids[i]) - 1)
151
+
152
+ # Update attention masks if present
153
+ if "attention_mask" in encoding:
154
+ merged_encoding["attention_mask"] = encoding["attention_mask"]
155
+
156
+ else: # single item case
157
+ image_token_indices = [i for i, id_val in enumerate(input_ids) if id_val == self.image_token_id]
158
+ if image_token_indices:
159
+ image_token_index = image_token_indices[0]
160
+ else:
161
+ # If no image token found, append it at the end
162
+ input_ids.append(self.image_token_id)
163
+ image_token_index = len(input_ids) - 1
164
+
165
+ merged_encoding = {
166
+ "input_ids": input_ids,
167
+ "pixel_values": pixel_values[0] if pixel_values else None,
168
+ "image_token_index": image_token_index
169
+ }
170
+
171
+ # Update attention mask if present
172
+ if "attention_mask" in encoding:
173
+ merged_encoding["attention_mask"] = encoding["attention_mask"]
174
+
175
+ return merged_encoding
176
+
177
+ def _convert_to_tensors(self, encoding, return_tensors="pt"):
178
+ """Convert processed features to tensors."""
179
+ # Convert all features to tensors of the requested type
180
+ for key, value in encoding.items():
181
+ if key in ["pixel_values", "input_ids", "attention_mask"]:
182
+ if return_tensors == "pt":
183
+ if isinstance(value, list) and all(isinstance(v, list) for v in value):
184
+ # For batched inputs
185
+ encoding[key] = torch.tensor(value)
186
+ elif isinstance(value, list):
187
+ # For single inputs
188
+ encoding[key] = torch.tensor([value])
189
+ elif isinstance(value, np.ndarray):
190
+ encoding[key] = torch.tensor(value)
191
+ elif return_tensors == "np":
192
+ if isinstance(value, list):
193
+ encoding[key] = np.array(value)
194
+ elif isinstance(value, torch.Tensor):
195
+ encoding[key] = value.numpy()
196
+ # Add other tensor types (tf, etc.) as needed
197
+
198
+ return encoding
199
+
200
+ @property
201
+ def model_input_names(self):
202
+ tokenizer_input_names = self.tokenizer.model_input_names
203
+ image_processor_input_names = self.image_processor.model_input_names
204
+ return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))
spec2_tokenizer.py ADDED
@@ -0,0 +1,258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+ # coding=utf-8
3
+ # Copyright 2023 The Spec-2 Authors
4
+ # Licensed under the Apache License, Version 2.0 (the "License")
5
+
6
+ """Tokenizer for Spec-2 model"""
7
+
8
+ import json
9
+ import os
10
+ from typing import Dict, List, Optional, Tuple, Union
11
+
12
+ import regex as re
13
+ from transformers import PreTrainedTokenizer
14
+ from transformers.utils import is_sentencepiece_available, logging
15
+
16
+ if is_sentencepiece_available():
17
+ import sentencepiece as spm
18
+ else:
19
+ raise ImportError(
20
+ "You need to install sentencepiece to use Spec2Tokenizer: https://github.com/google/sentencepiece"
21
+ "pip install sentencepiece"
22
+ )
23
+
24
+ logger = logging.get_logger(__name__)
25
+
26
+
27
+ class Spec2Tokenizer(PreTrainedTokenizer):
28
+ """
29
+ Construct a Spec-2 tokenizer based on SentencePiece.
30
+
31
+ This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
32
+ this superclass for more information regarding those methods.
33
+
34
+ Args:
35
+ vocab_file (`str`):
36
+ Path to the vocabulary file generated by SentencePiece.
37
+ additional_special_tokens (`List[str]`, *optional*):
38
+ Additional special tokens used by the tokenizer.
39
+ bos_token (`str`, *optional*, defaults to `"<bos>"`):
40
+ The beginning of sequence token that was used during pretraining.
41
+ eos_token (`str`, *optional*, defaults to `"<eos>"`):
42
+ The end of sequence token.
43
+ unk_token (`str`, *optional*, defaults to `"<unk>"`):
44
+ The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
45
+ token instead.
46
+ pad_token (`str`, *optional*, defaults to `"<pad>"`):
47
+ The token used for padding, for example when batching sequences of different lengths.
48
+ sp_model_kwargs (`dict`, *optional*):
49
+ Arguments to be passed to the SentencePiece model initialization method.
50
+ clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
51
+ Whether or not to clean up the tokenization spaces.
52
+ use_default_system_prompt (`bool`, *optional*, defaults to `False`):
53
+ Whether or not to use the default system prompt.
54
+ """
55
+
56
+ vocab_files_names = {"vocab_file": "tokenizer.model"}
57
+ model_input_names = ["input_ids", "attention_mask"]
58
+
59
+ def __init__(
60
+ self,
61
+ vocab_file,
62
+ additional_special_tokens=None,
63
+ bos_token="<bos>",
64
+ eos_token="<eos>",
65
+ unk_token="<unk>",
66
+ pad_token="<pad>",
67
+ sp_model_kwargs: Optional[Dict[str, str]] = None,
68
+ clean_up_tokenization_spaces=True,
69
+ use_default_system_prompt=False,
70
+ **kwargs,
71
+ ):
72
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
73
+ self.vocab_file = vocab_file
74
+
75
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
76
+ self.sp_model.Load(vocab_file)
77
+
78
+ # Mapping special tokens
79
+ self.special_tokens_map = {
80
+ "bos_token": bos_token,
81
+ "eos_token": eos_token,
82
+ "unk_token": unk_token,
83
+ "pad_token": pad_token,
84
+ }
85
+
86
+ # Add additional special tokens
87
+ self._additional_special_tokens = []
88
+ if additional_special_tokens:
89
+ self._additional_special_tokens = list(additional_special_tokens)
90
+
91
+ self.use_default_system_prompt = use_default_system_prompt
92
+
93
+ self.clean_up_tokenization_spaces = clean_up_tokenization_spaces
94
+
95
+ # Dictionary to store the token ids for special tokens
96
+ self.special_token_ids = {}
97
+ for token_name, token in self.special_tokens_map.items():
98
+ token_id = self.sp_model.piece_to_id(token)
99
+ self.special_token_ids[token_name] = token_id
100
+ setattr(self, f"{token_name}_id", token_id)
101
+
102
+ # Load additional special token mappings if available
103
+ self.vocab_mapping = {}
104
+ vocab_mapping_file = os.path.join(os.path.dirname(vocab_file), "tokenizer_config.json")
105
+ if os.path.exists(vocab_mapping_file):
106
+ with open(vocab_mapping_file, "r", encoding="utf-8") as f:
107
+ config = json.load(f)
108
+ if "vocab_mapping" in config:
109
+ self.vocab_mapping = config["vocab_mapping"]
110
+
111
+ # Initialize PreTrainedTokenizer
112
+ super().__init__(
113
+ bos_token=bos_token,
114
+ eos_token=eos_token,
115
+ unk_token=unk_token,
116
+ pad_token=pad_token,
117
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
118
+ additional_special_tokens=self._additional_special_tokens,
119
+ **kwargs,
120
+ )
121
+
122
+ @property
123
+ def vocab_size(self):
124
+ """Return the size of vocabulary."""
125
+ return self.sp_model.get_piece_size()
126
+
127
+ def get_vocab(self):
128
+ """Return vocab as a dict."""
129
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
130
+ vocab.update(self.added_tokens_encoder)
131
+ return vocab
132
+
133
+ def _tokenize(self, text):
134
+ """Tokenize a string."""
135
+ return self.sp_model.encode(text, out_type=str)
136
+
137
+ def _convert_token_to_id(self, token):
138
+ """Convert a token to an id using the vocab."""
139
+ return self.sp_model.piece_to_id(token)
140
+
141
+ def _convert_id_to_token(self, index):
142
+ """Convert an id to a token using the vocab."""
143
+ if index in self.added_tokens_decoder:
144
+ return self.added_tokens_decoder[index]
145
+ if index >= self.sp_model.get_piece_size():
146
+ for token_id_str, info in self.vocab_mapping.items():
147
+ if int(token_id_str) == index:
148
+ return info["content"]
149
+ return self.unk_token
150
+ token = self.sp_model.id_to_piece(index)
151
+ return token
152
+
153
+ def convert_tokens_to_string(self, tokens):
154
+ """Convert a list of tokens to a string."""
155
+ text = self.sp_model.decode(tokens)
156
+ if self.clean_up_tokenization_spaces:
157
+ text = self.clean_up_tokenization(text)
158
+ return text
159
+
160
+ def save_vocabulary(self, save_directory, filename_prefix=None):
161
+ """Save the vocabulary to a directory."""
162
+ if not os.path.isdir(save_directory):
163
+ logger.error(f"Vocabulary path ({save_directory}) should be a directory")
164
+ return
165
+
166
+ out_vocab_file = os.path.join(
167
+ save_directory, (filename_prefix + "-" if filename_prefix else "") + self.vocab_files_names["vocab_file"]
168
+ )
169
+
170
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
171
+ import shutil
172
+ shutil.copyfile(self.vocab_file, out_vocab_file)
173
+ elif not os.path.isfile(self.vocab_file):
174
+ with open(out_vocab_file, "wb") as fi:
175
+ content = self.sp_model.serialized_model_proto()
176
+ fi.write(content)
177
+
178
+ # Save tokenizer config with vocab mapping
179
+ config_file = os.path.join(save_directory, "tokenizer_config.json")
180
+ tokenizer_config = {
181
+ "vocab_file": self.vocab_files_names["vocab_file"],
182
+ "bos_token": self.bos_token,
183
+ "eos_token": self.eos_token,
184
+ "unk_token": self.unk_token,
185
+ "pad_token": self.pad_token,
186
+ "additional_special_tokens": self._additional_special_tokens,
187
+ "clean_up_tokenization_spaces": self.clean_up_tokenization_spaces,
188
+ "use_default_system_prompt": self.use_default_system_prompt,
189
+ "sp_model_kwargs": self.sp_model_kwargs,
190
+ "tokenizer_class": "Spec2Tokenizer",
191
+ "vocab_mapping": self.vocab_mapping
192
+ }
193
+
194
+ with open(config_file, "w", encoding="utf-8") as f:
195
+ json.dump(tokenizer_config, f, indent=2)
196
+
197
+ return (out_vocab_file, config_file)
198
+
199
+ def build_inputs_with_special_tokens(
200
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
201
+ ) -> List[int]:
202
+ """Build model inputs from a sequence by appending eos_token_id."""
203
+ if token_ids_1 is None:
204
+ return [self.bos_token_id] + token_ids_0 + [self.eos_token_id]
205
+ return [self.bos_token_id] + token_ids_0 + [self.eos_token_id] + token_ids_1 + [self.eos_token_id]
206
+
207
+ def get_special_tokens_mask(
208
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
209
+ ) -> List[int]:
210
+ """
211
+ Retrieve sequence ids from a token list that has no special tokens added.
212
+ """
213
+ if already_has_special_tokens:
214
+ return super().get_special_tokens_mask(
215
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
216
+ )
217
+
218
+ if token_ids_1 is None:
219
+ return [1] + ([0] * len(token_ids_0)) + [1]
220
+ return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
221
+
222
+ def create_token_type_ids_from_sequences(
223
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
224
+ ) -> List[int]:
225
+ """
226
+ Create a mask from the two sequences.
227
+ """
228
+ eos = [self.eos_token_id]
229
+ bos = [self.bos_token_id]
230
+
231
+ if token_ids_1 is None:
232
+ return len(bos + token_ids_0 + eos) * [0]
233
+ return len(bos + token_ids_0 + eos + token_ids_1 + eos) * [0]
234
+
235
+ def prepare_for_model(
236
+ self,
237
+ ids: List[int],
238
+ pair_ids: Optional[List[int]] = None,
239
+ add_special_tokens: bool = True,
240
+ **kwargs
241
+ ):
242
+ """
243
+ Prepare inputs for the model.
244
+ """
245
+ return super().prepare_for_model(
246
+ ids, pair_ids, add_special_tokens=add_special_tokens, **kwargs
247
+ )
248
+
249
+ def prepare_seq2seq_batch(
250
+ self,
251
+ src_texts: Union[str, List[str]],
252
+ tgt_texts: Optional[Union[str, List[str]]] = None,
253
+ **kwargs
254
+ ):
255
+ """
256
+ Prepare a batch for sequence-to-sequence tasks.
257
+ """
258
+ return super().prepare_seq2seq_batch(src_texts, tgt_texts, **kwargs)
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<bos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<eos>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<pad>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172fab587d68c56b63eb3620057c62dfd15e503079ff7fce584692e3fd5bf4da
3
+ size 34600820
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff