Hugging Face's logo

ys-zong
/
llava-v1.5-13b-Posthoc

Text Generation
Transformers
PyTorch
English
llava
Inference Endpoints
Model card Files Community
ys-zong commited on
Commit
8618ec9
•
0 Parent(s):

posthoc 13b weights

Browse files
Files changed (13) hide show
  1. .gitattributes +35 -0
  2. README.md +16 -0
  3. config.json +45 -0
  4. generation_config.json +8 -0
  5. pytorch_model-00001-of-00003.bin +3 -0
  6. pytorch_model-00002-of-00003.bin +3 -0
  7. pytorch_model-00003-of-00003.bin +3 -0
  8. pytorch_model.bin.index.json +805 -0
  9. special_tokens_map.json +24 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +35 -0
  12. trainer_state.json +541 -0
  13. training_args.bin +3 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ ---
5
+ # VLGuard
6
+ [[Website]](https://ys-zong.github.io/VLGuard) [[Paper]](https://arxiv.org/abs/2402.02207) [[Code]](https://github.com/ys-zong/VLGuard)
7
+
8
+ Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models. (ICML 2024)
9
+
10
+
11
+ ## Weights
12
+ This is the model weights for LLaVA-v1.5-13B Posthoc Fine-tuning. You can use them in exactly the same way as the original [LLaVA](https://github.com/haotian-liu/LLaVA/tree/main).
13
+
14
+ ## Usage
15
+
16
+ Please refer to [Github](https://github.com/ys-zong/VLGuard) for detailed usage.
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "liuhaotian/llava-v1.5-13b",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "freeze_mm_vision_resampler": false,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "image_aspect_ratio": "pad",
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 13824,
15
+ "max_length": 4096,
16
+ "max_position_embeddings": 4096,
17
+ "mm_hidden_size": 1024,
18
+ "mm_projector_lr": null,
19
+ "mm_projector_type": "mlp2x_gelu",
20
+ "mm_resampler_type": null,
21
+ "mm_use_im_patch_token": false,
22
+ "mm_use_im_start_end": false,
23
+ "mm_vision_select_feature": "patch",
24
+ "mm_vision_select_layer": -2,
25
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
26
+ "model_type": "llava",
27
+ "num_attention_heads": 40,
28
+ "num_hidden_layers": 40,
29
+ "num_key_value_heads": 40,
30
+ "pad_token_id": 0,
31
+ "pretraining_tp": 1,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "tie_word_embeddings": false,
35
+ "tokenizer_model_max_length": 2048,
36
+ "tokenizer_padding_side": "right",
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.31.0",
39
+ "tune_mm_mlp_adapter": false,
40
+ "tune_mm_vision_resampler": false,
41
+ "unfreeze_mm_vision_tower": false,
42
+ "use_cache": true,
43
+ "use_mm_proj": true,
44
+ "vocab_size": 32000
45
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.31.0"
8
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcbee6e76d296691f97b40fc60bd7c942bf5c8f449b3ae65ac691cb048ee8e47
3
+ size 9948726510
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c94dc8c896da2ec4e63610da178b697b5ee4bf8aaeeeb7e0c8527159a5bbf9c
3
+ size 9904162976
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd6bff0c508121c4405fe4ce631b4ad6587609738e369b3b11b77059f9374fa
3
+ size 6849082169
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,805 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26701683712
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
408
+ "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
409
+ "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
410
+ "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
411
+ "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
412
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin",
413
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin",
414
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin",
415
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
769
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
770
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
771
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
772
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
773
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
774
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
775
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
776
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
777
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
778
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
779
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
780
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
781
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
782
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
783
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
784
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
785
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
786
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
787
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
788
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
789
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
790
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
791
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
792
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
793
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
794
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
795
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
796
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
797
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
798
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
799
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
800
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin",
801
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin",
802
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin",
803
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin"
804
+ }
805
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,541 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 86,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 6.666666666666667e-06,
13
+ "loss": 0.8559,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 1.3333333333333333e-05,
19
+ "loss": 0.7071,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 2e-05,
25
+ "loss": 0.7514,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.05,
30
+ "learning_rate": 1.9992837548163315e-05,
31
+ "loss": 0.7098,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 1.9971360452796523e-05,
37
+ "loss": 0.6787,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.07,
42
+ "learning_rate": 1.993559947963185e-05,
43
+ "loss": 0.6556,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.08,
48
+ "learning_rate": 1.9885605855918887e-05,
49
+ "loss": 0.69,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.09,
54
+ "learning_rate": 1.9821451197042028e-05,
55
+ "loss": 0.753,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.1,
60
+ "learning_rate": 1.9743227403932135e-05,
61
+ "loss": 0.7316,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.12,
66
+ "learning_rate": 1.9651046531419335e-05,
67
+ "loss": 0.7426,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.13,
72
+ "learning_rate": 1.9545040627715554e-05,
73
+ "loss": 0.7588,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.14,
78
+ "learning_rate": 1.942536154525673e-05,
79
+ "loss": 0.7027,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.15,
84
+ "learning_rate": 1.9292180723175656e-05,
85
+ "loss": 0.6916,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.16,
90
+ "learning_rate": 1.9145688941717074e-05,
91
+ "loss": 0.7475,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.17,
96
+ "learning_rate": 1.8986096048946826e-05,
97
+ "loss": 0.7039,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.19,
102
+ "learning_rate": 1.881363066014649e-05,
103
+ "loss": 0.7715,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.2,
108
+ "learning_rate": 1.862853983032423e-05,
109
+ "loss": 0.6958,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.21,
114
+ "learning_rate": 1.8431088700310846e-05,
115
+ "loss": 0.7214,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.22,
120
+ "learning_rate": 1.8221560116948103e-05,
121
+ "loss": 0.6808,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.23,
126
+ "learning_rate": 1.8000254227913346e-05,
127
+ "loss": 0.653,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.24,
132
+ "learning_rate": 1.7767488051760858e-05,
133
+ "loss": 0.645,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.26,
138
+ "learning_rate": 1.7523595023795814e-05,
139
+ "loss": 0.7061,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.27,
144
+ "learning_rate": 1.7268924518431437e-05,
145
+ "loss": 0.7223,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.28,
150
+ "learning_rate": 1.700384134871351e-05,
151
+ "loss": 0.6489,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.29,
156
+ "learning_rate": 1.672872524372919e-05,
157
+ "loss": 0.6721,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.3,
162
+ "learning_rate": 1.644397030464877e-05,
163
+ "loss": 0.6771,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.31,
168
+ "learning_rate": 1.614998444017954e-05,
169
+ "loss": 0.1781,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.33,
174
+ "learning_rate": 1.5847188782240473e-05,
175
+ "loss": 0.6716,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.34,
180
+ "learning_rate": 1.5536017082694846e-05,
181
+ "loss": 0.7402,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.35,
186
+ "learning_rate": 1.5216915092004847e-05,
187
+ "loss": 0.6907,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.36,
192
+ "learning_rate": 1.4890339920698334e-05,
193
+ "loss": 0.746,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.37,
198
+ "learning_rate": 1.4556759384562418e-05,
199
+ "loss": 0.7715,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.38,
204
+ "learning_rate": 1.421665133450184e-05,
205
+ "loss": 0.6999,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.4,
210
+ "learning_rate": 1.3870502972022175e-05,
211
+ "loss": 0.6374,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.41,
216
+ "learning_rate": 1.351881015131833e-05,
217
+ "loss": 0.6886,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.42,
222
+ "learning_rate": 1.316207666896824e-05,
223
+ "loss": 0.6923,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.43,
228
+ "learning_rate": 1.2800813542249073e-05,
229
+ "loss": 0.648,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.44,
234
+ "learning_rate": 1.2435538277109919e-05,
235
+ "loss": 0.6889,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.45,
240
+ "learning_rate": 1.206677412684953e-05,
241
+ "loss": 0.7149,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.47,
246
+ "learning_rate": 1.1695049342560969e-05,
247
+ "loss": 0.7076,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.48,
252
+ "learning_rate": 1.1320896416417026e-05,
253
+ "loss": 0.7184,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.49,
258
+ "learning_rate": 1.0944851318880314e-05,
259
+ "loss": 0.7535,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.5,
264
+ "learning_rate": 1.0567452730930743e-05,
265
+ "loss": 0.7158,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.51,
270
+ "learning_rate": 1.0189241272410191e-05,
271
+ "loss": 0.7169,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.52,
276
+ "learning_rate": 9.810758727589814e-06,
277
+ "loss": 0.631,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.53,
282
+ "learning_rate": 9.43254726906926e-06,
283
+ "loss": 0.6797,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.55,
288
+ "learning_rate": 9.055148681119688e-06,
289
+ "loss": 0.7235,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.56,
294
+ "learning_rate": 8.67910358358298e-06,
295
+ "loss": 0.7368,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.57,
300
+ "learning_rate": 8.304950657439034e-06,
301
+ "loss": 0.6947,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.58,
306
+ "learning_rate": 7.93322587315047e-06,
307
+ "loss": 0.6969,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.59,
312
+ "learning_rate": 7.564461722890082e-06,
313
+ "loss": 0.7425,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.6,
318
+ "learning_rate": 7.199186457750931e-06,
319
+ "loss": 0.641,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.62,
324
+ "learning_rate": 6.837923331031761e-06,
325
+ "loss": 0.1685,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.63,
330
+ "learning_rate": 6.48118984868167e-06,
331
+ "loss": 0.684,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.64,
336
+ "learning_rate": 6.129497027977829e-06,
337
+ "loss": 0.1894,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.65,
342
+ "learning_rate": 5.78334866549816e-06,
343
+ "loss": 0.6861,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.66,
348
+ "learning_rate": 5.443240615437586e-06,
349
+ "loss": 0.6837,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.67,
354
+ "learning_rate": 5.109660079301668e-06,
355
+ "loss": 0.7266,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.69,
360
+ "learning_rate": 4.783084907995156e-06,
361
+ "loss": 0.665,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.7,
366
+ "learning_rate": 4.463982917305155e-06,
367
+ "loss": 0.655,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.71,
372
+ "learning_rate": 4.152811217759529e-06,
373
+ "loss": 0.6949,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.72,
378
+ "learning_rate": 3.850015559820465e-06,
379
+ "loss": 0.6858,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.73,
384
+ "learning_rate": 3.5560296953512296e-06,
385
+ "loss": 0.6224,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.74,
390
+ "learning_rate": 3.2712747562708115e-06,
391
+ "loss": 0.6903,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.76,
396
+ "learning_rate": 2.9961586512864947e-06,
397
+ "loss": 0.7373,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.77,
402
+ "learning_rate": 2.7310754815685627e-06,
403
+ "loss": 0.6265,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.78,
408
+ "learning_rate": 2.4764049762041874e-06,
409
+ "loss": 0.7343,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.79,
414
+ "learning_rate": 2.2325119482391466e-06,
415
+ "loss": 0.6524,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.8,
420
+ "learning_rate": 1.9997457720866554e-06,
421
+ "loss": 0.7026,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.81,
426
+ "learning_rate": 1.7784398830519002e-06,
427
+ "loss": 0.6995,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.83,
432
+ "learning_rate": 1.5689112996891576e-06,
433
+ "loss": 0.6672,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.84,
438
+ "learning_rate": 1.3714601696757713e-06,
439
+ "loss": 0.7158,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.85,
444
+ "learning_rate": 1.1863693398535115e-06,
445
+ "loss": 0.6767,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.86,
450
+ "learning_rate": 1.01390395105318e-06,
451
+ "loss": 0.7041,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.87,
456
+ "learning_rate": 8.543110582829272e-07,
457
+ "loss": 0.6582,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.88,
462
+ "learning_rate": 7.078192768243486e-07,
463
+ "loss": 0.7415,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.9,
468
+ "learning_rate": 5.746384547432738e-07,
469
+ "loss": 0.7245,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.91,
474
+ "learning_rate": 4.549593722844492e-07,
475
+ "loss": 0.1694,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.92,
480
+ "learning_rate": 3.4895346858066723e-07,
481
+ "loss": 0.6716,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.93,
486
+ "learning_rate": 2.5677259606786686e-07,
487
+ "loss": 0.7095,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.94,
492
+ "learning_rate": 1.7854880295797406e-07,
493
+ "loss": 0.6823,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.95,
498
+ "learning_rate": 1.1439414408111471e-07,
499
+ "loss": 0.7316,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.97,
504
+ "learning_rate": 6.440052036815081e-08,
505
+ "loss": 0.6417,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.98,
510
+ "learning_rate": 2.86395472034795e-08,
511
+ "loss": 0.6386,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.99,
516
+ "learning_rate": 7.162451836685291e-09,
517
+ "loss": 0.6541,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 1.0,
522
+ "learning_rate": 0.0,
523
+ "loss": 0.1686,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 1.0,
528
+ "step": 86,
529
+ "total_flos": 204478356652032.0,
530
+ "train_loss": 0.6681410723993945,
531
+ "train_runtime": 2105.2364,
532
+ "train_samples_per_second": 5.225,
533
+ "train_steps_per_second": 0.041
534
+ }
535
+ ],
536
+ "max_steps": 86,
537
+ "num_train_epochs": 1,
538
+ "total_flos": 204478356652032.0,
539
+ "trial_name": null,
540
+ "trial_params": null
541
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b365463ba0bd195bfd11aba99f37650802609ac8481dd94a7b67a84f846224d1
3
+ size 6139