Hugging Face's logo

Kami-code
/
handsonvlm-13b

Image-Text-to-Text
Transformers
PyTorch
handsonvlm
text-generation
Model card Files
xet
Community
1
Kami-code commited on
Commit
20a302b
·
verified ·
1 Parent(s): 34e4133

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. added_tokens.json +103 -0
  2. config.json +152 -0
  3. generation_config.json +7 -0
  4. pytorch_model-00001-of-00003.bin +3 -0
  5. pytorch_model-00002-of-00003.bin +3 -0
  6. pytorch_model-00003-of-00003.bin +3 -0
  7. pytorch_model.bin.index.json +824 -0
  8. special_tokens_map.json +24 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +35 -0
  11. trainer_state.json +166 -0
  12. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<hand_traj>": 32100,
3
+ "<t0>": 32000,
4
+ "<t10>": 32010,
5
+ "<t11>": 32011,
6
+ "<t12>": 32012,
7
+ "<t13>": 32013,
8
+ "<t14>": 32014,
9
+ "<t15>": 32015,
10
+ "<t16>": 32016,
11
+ "<t17>": 32017,
12
+ "<t18>": 32018,
13
+ "<t19>": 32019,
14
+ "<t1>": 32001,
15
+ "<t20>": 32020,
16
+ "<t21>": 32021,
17
+ "<t22>": 32022,
18
+ "<t23>": 32023,
19
+ "<t24>": 32024,
20
+ "<t25>": 32025,
21
+ "<t26>": 32026,
22
+ "<t27>": 32027,
23
+ "<t28>": 32028,
24
+ "<t29>": 32029,
25
+ "<t2>": 32002,
26
+ "<t30>": 32030,
27
+ "<t31>": 32031,
28
+ "<t32>": 32032,
29
+ "<t33>": 32033,
30
+ "<t34>": 32034,
31
+ "<t35>": 32035,
32
+ "<t36>": 32036,
33
+ "<t37>": 32037,
34
+ "<t38>": 32038,
35
+ "<t39>": 32039,
36
+ "<t3>": 32003,
37
+ "<t40>": 32040,
38
+ "<t41>": 32041,
39
+ "<t42>": 32042,
40
+ "<t43>": 32043,
41
+ "<t44>": 32044,
42
+ "<t45>": 32045,
43
+ "<t46>": 32046,
44
+ "<t47>": 32047,
45
+ "<t48>": 32048,
46
+ "<t49>": 32049,
47
+ "<t4>": 32004,
48
+ "<t50>": 32050,
49
+ "<t51>": 32051,
50
+ "<t52>": 32052,
51
+ "<t53>": 32053,
52
+ "<t54>": 32054,
53
+ "<t55>": 32055,
54
+ "<t56>": 32056,
55
+ "<t57>": 32057,
56
+ "<t58>": 32058,
57
+ "<t59>": 32059,
58
+ "<t5>": 32005,
59
+ "<t60>": 32060,
60
+ "<t61>": 32061,
61
+ "<t62>": 32062,
62
+ "<t63>": 32063,
63
+ "<t64>": 32064,
64
+ "<t65>": 32065,
65
+ "<t66>": 32066,
66
+ "<t67>": 32067,
67
+ "<t68>": 32068,
68
+ "<t69>": 32069,
69
+ "<t6>": 32006,
70
+ "<t70>": 32070,
71
+ "<t71>": 32071,
72
+ "<t72>": 32072,
73
+ "<t73>": 32073,
74
+ "<t74>": 32074,
75
+ "<t75>": 32075,
76
+ "<t76>": 32076,
77
+ "<t77>": 32077,
78
+ "<t78>": 32078,
79
+ "<t79>": 32079,
80
+ "<t7>": 32007,
81
+ "<t80>": 32080,
82
+ "<t81>": 32081,
83
+ "<t82>": 32082,
84
+ "<t83>": 32083,
85
+ "<t84>": 32084,
86
+ "<t85>": 32085,
87
+ "<t86>": 32086,
88
+ "<t87>": 32087,
89
+ "<t88>": 32088,
90
+ "<t89>": 32089,
91
+ "<t8>": 32008,
92
+ "<t90>": 32090,
93
+ "<t91>": 32091,
94
+ "<t92>": 32092,
95
+ "<t93>": 32093,
96
+ "<t94>": 32094,
97
+ "<t95>": 32095,
98
+ "<t96>": 32096,
99
+ "<t97>": 32097,
100
+ "<t98>": 32098,
101
+ "<t99>": 32099,
102
+ "<t9>": 32009
103
+ }
config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/vicuna-v1-3-13b",
3
+ "architectures": [
4
+ "HandsOnVLMForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "fuse_input_mode": "origin",
10
+ "hand_token_id": 32100,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "hoi_lambda": 1.0,
14
+ "image_aspect_ratio": "square",
15
+ "image_grid_pinpoints": null,
16
+ "initializer_range": 0.02,
17
+ "input_type": "video",
18
+ "intermediate_size": 13824,
19
+ "lambda_last_hand": 0.001,
20
+ "lambda_obj": 0.1,
21
+ "lambda_obj_kl": 0.001,
22
+ "lambda_traj": 1,
23
+ "lambda_traj_kl": 0.001,
24
+ "max_position_embeddings": 2048,
25
+ "mm_hidden_size": 1024,
26
+ "mm_use_im_patch_token": false,
27
+ "mm_use_im_start_end": false,
28
+ "mm_vision_select_feature": "patch",
29
+ "mm_vision_select_layer": -2,
30
+ "mm_vision_tower": "openai/clip-vit-large-patch14",
31
+ "model_type": "handsonvlm",
32
+ "num_attention_heads": 40,
33
+ "num_frames": 100,
34
+ "num_hidden_layers": 40,
35
+ "num_key_value_heads": 40,
36
+ "num_time_tokens": 100,
37
+ "pad_token_id": 0,
38
+ "pretraining_tp": 1,
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": null,
41
+ "tie_word_embeddings": false,
42
+ "time_token_ids": [
43
+ 32000,
44
+ 32001,
45
+ 32002,
46
+ 32003,
47
+ 32004,
48
+ 32005,
49
+ 32006,
50
+ 32007,
51
+ 32008,
52
+ 32009,
53
+ 32010,
54
+ 32011,
55
+ 32012,
56
+ 32013,
57
+ 32014,
58
+ 32015,
59
+ 32016,
60
+ 32017,
61
+ 32018,
62
+ 32019,
63
+ 32020,
64
+ 32021,
65
+ 32022,
66
+ 32023,
67
+ 32024,
68
+ 32025,
69
+ 32026,
70
+ 32027,
71
+ 32028,
72
+ 32029,
73
+ 32030,
74
+ 32031,
75
+ 32032,
76
+ 32033,
77
+ 32034,
78
+ 32035,
79
+ 32036,
80
+ 32037,
81
+ 32038,
82
+ 32039,
83
+ 32040,
84
+ 32041,
85
+ 32042,
86
+ 32043,
87
+ 32044,
88
+ 32045,
89
+ 32046,
90
+ 32047,
91
+ 32048,
92
+ 32049,
93
+ 32050,
94
+ 32051,
95
+ 32052,
96
+ 32053,
97
+ 32054,
98
+ 32055,
99
+ 32056,
100
+ 32057,
101
+ 32058,
102
+ 32059,
103
+ 32060,
104
+ 32061,
105
+ 32062,
106
+ 32063,
107
+ 32064,
108
+ 32065,
109
+ 32066,
110
+ 32067,
111
+ 32068,
112
+ 32069,
113
+ 32070,
114
+ 32071,
115
+ 32072,
116
+ 32073,
117
+ 32074,
118
+ 32075,
119
+ 32076,
120
+ 32077,
121
+ 32078,
122
+ 32079,
123
+ 32080,
124
+ 32081,
125
+ 32082,
126
+ 32083,
127
+ 32084,
128
+ 32085,
129
+ 32086,
130
+ 32087,
131
+ 32088,
132
+ 32089,
133
+ 32090,
134
+ 32091,
135
+ 32092,
136
+ 32093,
137
+ 32094,
138
+ 32095,
139
+ 32096,
140
+ 32097,
141
+ 32098,
142
+ 32099
143
+ ],
144
+ "torch_dtype": "bfloat16",
145
+ "traj_decoder": "CVAE",
146
+ "transformers_version": "4.31.0",
147
+ "tune_mm_mlp_adapter": false,
148
+ "use_cache": false,
149
+ "use_mm_proj": true,
150
+ "video_compress_mode": "temporal_spatial_pool",
151
+ "vocab_size": 32101
152
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.31.0"
7
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8368f2d72e051b839faaea121e1642a91b7b3d20ae21ac9b7ec29783014cd902
3
+ size 9949966340
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b5304ffe0e77b035791472e1610867e0351909eb40c963ea277d0167cb98ae
3
+ size 9904163463
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9180605377eee3d791ca2cff3da4a4cc798f543732c6caa2e1c9c187e586ae12
3
+ size 6807414506
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,824 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26661248452
4
+ },
5
+ "weight_map": {
6
+ "bbox_to_feature.0.bias": "pytorch_model-00003-of-00003.bin",
7
+ "bbox_to_feature.0.weight": "pytorch_model-00003-of-00003.bin",
8
+ "bbox_to_feature.2.bias": "pytorch_model-00003-of-00003.bin",
9
+ "bbox_to_feature.2.weight": "pytorch_model-00003-of-00003.bin",
10
+ "downproject.bias": "pytorch_model-00003-of-00003.bin",
11
+ "downproject.weight": "pytorch_model-00003-of-00003.bin",
12
+ "feat_fusion.0.bias": "pytorch_model-00003-of-00003.bin",
13
+ "feat_fusion.0.weight": "pytorch_model-00003-of-00003.bin",
14
+ "hand_traj_decoder.hand_traj_decoder.cvae.dec_MLP.0.bias": "pytorch_model-00003-of-00003.bin",
15
+ "hand_traj_decoder.hand_traj_decoder.cvae.dec_MLP.0.weight": "pytorch_model-00003-of-00003.bin",
16
+ "hand_traj_decoder.hand_traj_decoder.cvae.dec_MLP.2.bias": "pytorch_model-00003-of-00003.bin",
17
+ "hand_traj_decoder.hand_traj_decoder.cvae.dec_MLP.2.weight": "pytorch_model-00003-of-00003.bin",
18
+ "hand_traj_decoder.hand_traj_decoder.cvae.enc_MLP.0.bias": "pytorch_model-00003-of-00003.bin",
19
+ "hand_traj_decoder.hand_traj_decoder.cvae.enc_MLP.0.weight": "pytorch_model-00003-of-00003.bin",
20
+ "hand_traj_decoder.hand_traj_decoder.cvae.linear_log_var.bias": "pytorch_model-00003-of-00003.bin",
21
+ "hand_traj_decoder.hand_traj_decoder.cvae.linear_log_var.weight": "pytorch_model-00003-of-00003.bin",
22
+ "hand_traj_decoder.hand_traj_decoder.cvae.linear_means.bias": "pytorch_model-00003-of-00003.bin",
23
+ "hand_traj_decoder.hand_traj_decoder.cvae.linear_means.weight": "pytorch_model-00003-of-00003.bin",
24
+ "hand_traj_positional_embedding.bias": "pytorch_model-00003-of-00003.bin",
25
+ "hand_traj_positional_embedding.weight": "pytorch_model-00003-of-00003.bin",
26
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
27
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
72
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
73
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
74
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
75
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
76
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
77
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
78
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
79
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
80
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
81
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
82
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
83
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
84
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
85
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
86
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
87
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
88
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
89
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
90
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
91
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
92
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
93
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
94
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
95
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
96
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
97
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
98
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
104
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
106
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
149
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
150
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
151
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
152
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
153
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
154
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
155
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
156
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
157
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
158
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
239
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
240
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
241
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
242
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
243
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
244
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
245
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
246
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
247
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
248
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
249
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
250
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
253
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
259
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
260
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
261
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
263
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
264
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
265
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
266
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
267
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
268
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
269
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
270
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
271
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
272
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
273
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
274
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
275
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
276
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
277
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
278
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
288
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
290
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
291
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
292
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
294
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
312
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
315
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
316
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
318
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
320
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
322
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
324
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
326
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
327
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
328
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
332
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
333
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
334
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
336
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
337
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
338
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
339
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
340
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
341
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
342
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
343
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
344
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
345
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
346
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
347
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
348
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
349
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
350
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
351
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
352
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
353
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
354
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
355
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
356
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
357
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
358
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
359
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
360
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
361
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
362
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
363
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
364
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
365
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
366
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
367
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
368
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
369
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
370
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
371
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
372
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
373
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
374
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
375
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
376
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
378
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
380
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
381
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
382
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
383
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
384
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
385
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
386
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
387
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
388
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
389
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
390
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
391
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
392
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
393
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
394
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
395
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
396
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
397
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
398
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
399
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
400
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
401
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
402
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
403
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
404
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
405
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
406
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
408
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
409
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
410
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
411
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
412
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
413
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
414
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
415
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
416
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
417
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
418
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
419
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
420
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
421
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
422
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
423
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
424
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
425
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
426
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
427
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
428
+ "model.mm_projector.bias": "pytorch_model-00003-of-00003.bin",
429
+ "model.mm_projector.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin",
431
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin",
432
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin",
433
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
769
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
770
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
771
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
772
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
773
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
774
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
775
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
776
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
777
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
778
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
779
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
780
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
781
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
782
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
783
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
784
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
785
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
786
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
787
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
788
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
789
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
790
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
791
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
792
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
793
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
794
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
795
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
796
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
797
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
798
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
799
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
800
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
801
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
802
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
803
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
804
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
805
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
806
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
807
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
808
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
809
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
810
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
811
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
812
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
813
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
814
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
815
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
816
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
817
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
818
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin",
819
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin",
820
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin",
821
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin",
822
+ "time_embedding": "pytorch_model-00001-of-00003.bin"
823
+ }
824
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
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": true,
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": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
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": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 25.0,
5
+ "global_step": 9450,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.665198237885463e-05,
13
+ "loss": 9.873,
14
+ "step": 378
15
+ },
16
+ {
17
+ "epoch": 2.0,
18
+ "learning_rate": 1.9979082546575355e-05,
19
+ "loss": 2.5441,
20
+ "step": 756
21
+ },
22
+ {
23
+ "epoch": 3.0,
24
+ "learning_rate": 1.989409994368087e-05,
25
+ "loss": 1.9226,
26
+ "step": 1134
27
+ },
28
+ {
29
+ "epoch": 4.0,
30
+ "learning_rate": 1.9744283913135673e-05,
31
+ "loss": 1.6855,
32
+ "step": 1512
33
+ },
34
+ {
35
+ "epoch": 5.0,
36
+ "learning_rate": 1.953061615987832e-05,
37
+ "loss": 1.5525,
38
+ "step": 1890
39
+ },
40
+ {
41
+ "epoch": 6.0,
42
+ "learning_rate": 1.9254496792347266e-05,
43
+ "loss": 1.4545,
44
+ "step": 2268
45
+ },
46
+ {
47
+ "epoch": 7.0,
48
+ "learning_rate": 1.8917735147939518e-05,
49
+ "loss": 1.3937,
50
+ "step": 2646
51
+ },
52
+ {
53
+ "epoch": 8.0,
54
+ "learning_rate": 1.852253793689982e-05,
55
+ "loss": 1.3153,
56
+ "step": 3024
57
+ },
58
+ {
59
+ "epoch": 9.0,
60
+ "learning_rate": 1.8071494782330375e-05,
61
+ "loss": 1.2177,
62
+ "step": 3402
63
+ },
64
+ {
65
+ "epoch": 10.0,
66
+ "learning_rate": 1.7567561251073607e-05,
67
+ "loss": 1.1404,
68
+ "step": 3780
69
+ },
70
+ {
71
+ "epoch": 11.0,
72
+ "learning_rate": 1.7014039486662075e-05,
73
+ "loss": 1.0829,
74
+ "step": 4158
75
+ },
76
+ {
77
+ "epoch": 12.0,
78
+ "learning_rate": 1.6414556571242747e-05,
79
+ "loss": 0.9988,
80
+ "step": 4536
81
+ },
82
+ {
83
+ "epoch": 13.0,
84
+ "learning_rate": 1.5773040758264232e-05,
85
+ "loss": 0.9398,
86
+ "step": 4914
87
+ },
88
+ {
89
+ "epoch": 14.0,
90
+ "learning_rate": 1.50936957316679e-05,
91
+ "loss": 0.8877,
92
+ "step": 5292
93
+ },
94
+ {
95
+ "epoch": 15.0,
96
+ "learning_rate": 1.4380973060255608e-05,
97
+ "loss": 0.8544,
98
+ "step": 5670
99
+ },
100
+ {
101
+ "epoch": 16.0,
102
+ "learning_rate": 1.36395430277333e-05,
103
+ "loss": 0.7904,
104
+ "step": 6048
105
+ },
106
+ {
107
+ "epoch": 17.0,
108
+ "learning_rate": 1.2874264029573555e-05,
109
+ "loss": 0.7554,
110
+ "step": 6426
111
+ },
112
+ {
113
+ "epoch": 18.0,
114
+ "learning_rate": 1.2090150737231307e-05,
115
+ "loss": 0.7142,
116
+ "step": 6804
117
+ },
118
+ {
119
+ "epoch": 19.0,
120
+ "learning_rate": 1.1292341238324266e-05,
121
+ "loss": 0.6749,
122
+ "step": 7182
123
+ },
124
+ {
125
+ "epoch": 20.0,
126
+ "learning_rate": 1.0486063368099783e-05,
127
+ "loss": 0.6421,
128
+ "step": 7560
129
+ },
130
+ {
131
+ "epoch": 21.0,
132
+ "learning_rate": 9.67660045280918e-06,
133
+ "loss": 0.6075,
134
+ "step": 7938
135
+ },
136
+ {
137
+ "epoch": 22.0,
138
+ "learning_rate": 8.86925668946412e-06,
139
+ "loss": 0.5757,
140
+ "step": 8316
141
+ },
142
+ {
143
+ "epoch": 23.0,
144
+ "learning_rate": 8.069322388832444e-06,
145
+ "loss": 0.5459,
146
+ "step": 8694
147
+ },
148
+ {
149
+ "epoch": 24.0,
150
+ "learning_rate": 7.282039309426844e-06,
151
+ "loss": 0.5311,
152
+ "step": 9072
153
+ },
154
+ {
155
+ "epoch": 25.0,
156
+ "learning_rate": 6.51256630964373e-06,
157
+ "loss": 0.516,
158
+ "step": 9450
159
+ }
160
+ ],
161
+ "max_steps": 15120,
162
+ "num_train_epochs": 40,
163
+ "total_flos": 1794560967573504.0,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3edd2999c5b29b9741087daf49d61142e2d2dc3c080f3bd42e4d8e616ae7e77c
3
+ size 6712