Hugging Face's logo

PLB
/
GR00T-N1-so100-wc

Safetensors
gr00t_n1
Model card Files
xet
 Community
1
PLB commited on
Commit
bea895f
·
verified ·
1 Parent(s): f981645

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +65 -0
  2. experiment_cfg/metadata.json +195 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +809 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. trainer_state.json +558 -0
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/azureuser/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
3
+ "action_dim": 32,
4
+ "action_head_cfg": {
5
+ "action_dim": 32,
6
+ "action_horizon": 16,
7
+ "add_pos_embed": true,
8
+ "diffusion_model_cfg": {
9
+ "attention_head_dim": 48,
10
+ "dropout": 0.2,
11
+ "final_dropout": true,
12
+ "interleave_self_attention": true,
13
+ "norm_type": "ada_norm",
14
+ "num_attention_heads": 32,
15
+ "num_layers": 16,
16
+ "output_dim": 1024,
17
+ "positional_embeddings": null
18
+ },
19
+ "freeze_decode_layer": false,
20
+ "hidden_size": 1024,
21
+ "input_embedding_dim": 1536,
22
+ "load_pretrained_det_decode_layer_path": null,
23
+ "max_action_dim": 32,
24
+ "max_state_dim": 64,
25
+ "model_dtype": "float32",
26
+ "noise_beta_alpha": 1.5,
27
+ "noise_beta_beta": 1.0,
28
+ "noise_s": 0.999,
29
+ "num_inference_timesteps": 16,
30
+ "num_timestep_buckets": 1000,
31
+ "tune_diffusion_model": true,
32
+ "tune_projector": true
33
+ },
34
+ "action_horizon": 16,
35
+ "architectures": [
36
+ "GR00T_N1"
37
+ ],
38
+ "attn_implementation": null,
39
+ "backbone_cfg": {
40
+ "allow_reshape_visual": true,
41
+ "load_pretrained_det_eagle_path": null,
42
+ "model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
43
+ "processor_cfg": {
44
+ "max_input_tiles": 1,
45
+ "model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
46
+ "model_spec": {
47
+ "num_image_token": 64,
48
+ "template": "qwen2-chat"
49
+ }
50
+ },
51
+ "projector_dim": 2048,
52
+ "remove_llm": false,
53
+ "reproject_vision": false,
54
+ "scale_image_resolution": 1,
55
+ "select_layer": 12,
56
+ "tune_llm": false,
57
+ "tune_visual": true
58
+ },
59
+ "compute_dtype": "bfloat16",
60
+ "hidden_size": 1536,
61
+ "model_dtype": "float32",
62
+ "model_type": "gr00t_n1",
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.45.2"
65
+ }
experiment_cfg/metadata.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "new_embodiment": {
3
+ "statistics": {
4
+ "state": {
5
+ "single_arm": {
6
+ "max": [
7
+ 1.3118739128112793,
8
+ 1.322614312171936,
9
+ 1.4100725650787354,
10
+ 1.5589051246643066,
11
+ 0.4357569217681885
12
+ ],
13
+ "min": [
14
+ -1.4438284635543823,
15
+ -1.5742486715316772,
16
+ -1.0356898307800293,
17
+ -1.6509664058685303,
18
+ -0.25163426995277405
19
+ ],
20
+ "mean": [
21
+ -0.10010052472352982,
22
+ -0.11802323162555695,
23
+ 0.4649488031864166,
24
+ -0.00825109239667654,
25
+ 0.09833338111639023
26
+ ],
27
+ "std": [
28
+ 0.5810577273368835,
29
+ 0.5973959565162659,
30
+ 0.47856447100639343,
31
+ 0.4736618101596832,
32
+ 0.09819493442773819
33
+ ],
34
+ "q01": [
35
+ -1.3209418785572051,
36
+ -1.5464921724796294,
37
+ -0.793261706829071,
38
+ -1.1446291208267212,
39
+ -0.16264167428016663
40
+ ],
41
+ "q99": [
42
+ 1.2518958580493924,
43
+ 1.1569039821624756,
44
+ 1.3913841509819027,
45
+ 1.1523009538650513,
46
+ 0.32835206389427185
47
+ ]
48
+ },
49
+ "gripper": {
50
+ "max": [
51
+ 1.7399590015411377
52
+ ],
53
+ "min": [
54
+ 0.04909937083721161
55
+ ],
56
+ "mean": [
57
+ 1.1425409317016602
58
+ ],
59
+ "std": [
60
+ 0.718782901763916
61
+ ],
62
+ "q01": [
63
+ 0.05063372850418091
64
+ ],
65
+ "q99": [
66
+ 1.7382865679264066
67
+ ]
68
+ }
69
+ },
70
+ "action": {
71
+ "single_arm": {
72
+ "max": [
73
+ 1.3118739128112793,
74
+ 1.322614312171936,
75
+ 1.4100725650787354,
76
+ 1.5589051246643066,
77
+ 0.4357569217681885
78
+ ],
79
+ "min": [
80
+ -1.4438284635543823,
81
+ -1.5742486715316772,
82
+ -1.0356898307800293,
83
+ -1.6509664058685303,
84
+ -0.25163426995277405
85
+ ],
86
+ "mean": [
87
+ -0.10026898235082626,
88
+ -0.11829467862844467,
89
+ 0.46463051438331604,
90
+ -0.007809753064066172,
91
+ 0.09879428893327713
92
+ ],
93
+ "std": [
94
+ 0.5810325145721436,
95
+ 0.5974081158638,
96
+ 0.47892773151397705,
97
+ 0.47373121976852417,
98
+ 0.09806974232196808
99
+ ],
100
+ "q01": [
101
+ -1.3209418785572051,
102
+ -1.5464921724796294,
103
+ -0.793261706829071,
104
+ -1.1446291208267212,
105
+ -0.16264167428016663
106
+ ],
107
+ "q99": [
108
+ 1.2518958580493924,
109
+ 1.1569039821624756,
110
+ 1.3913841509819027,
111
+ 1.1523009538650513,
112
+ 0.32835206389427185
113
+ ]
114
+ },
115
+ "gripper": {
116
+ "max": [
117
+ 1.7399590015411377
118
+ ],
119
+ "min": [
120
+ 0.04909937083721161
121
+ ],
122
+ "mean": [
123
+ 1.142529845237732
124
+ ],
125
+ "std": [
126
+ 0.7187808752059937
127
+ ],
128
+ "q01": [
129
+ 0.05063372850418091
130
+ ],
131
+ "q99": [
132
+ 1.7368903160095215
133
+ ]
134
+ }
135
+ }
136
+ },
137
+ "modalities": {
138
+ "video": {
139
+ "cam_context": {
140
+ "resolution": [
141
+ 320,
142
+ 240
143
+ ],
144
+ "channels": 3,
145
+ "fps": 30.0
146
+ },
147
+ "cam_wrist": {
148
+ "resolution": [
149
+ 320,
150
+ 240
151
+ ],
152
+ "channels": 3,
153
+ "fps": 30.0
154
+ }
155
+ },
156
+ "state": {
157
+ "single_arm": {
158
+ "absolute": true,
159
+ "rotation_type": null,
160
+ "shape": [
161
+ 5
162
+ ],
163
+ "continuous": true
164
+ },
165
+ "gripper": {
166
+ "absolute": true,
167
+ "rotation_type": null,
168
+ "shape": [
169
+ 1
170
+ ],
171
+ "continuous": true
172
+ }
173
+ },
174
+ "action": {
175
+ "single_arm": {
176
+ "absolute": true,
177
+ "rotation_type": null,
178
+ "shape": [
179
+ 5
180
+ ],
181
+ "continuous": true
182
+ },
183
+ "gripper": {
184
+ "absolute": true,
185
+ "rotation_type": null,
186
+ "shape": [
187
+ 1
188
+ ],
189
+ "continuous": true
190
+ }
191
+ }
192
+ },
193
+ "embodiment_tag": "new_embodiment"
194
+ }
195
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b5363f5bc43c010f4c13876afb1c1dff53ff71a76a27d426fd2dff409f4212
3
+ size 4938446392
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b627ebafc35515121aea4f7675c19214a45c06b2d70ae6c77caedca0b14634e5
3
+ size 3821736024
model.safetensors.index.json ADDED
@@ -0,0 +1,809 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8760067008
4
+ },
5
+ "weight_map": {
6
+ "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
7
+ "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
8
+ "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
9
+ "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
10
+ "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
11
+ "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
12
+ "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
13
+ "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
14
+ "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
15
+ "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
16
+ "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
17
+ "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
18
+ "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
19
+ "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
20
+ "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
21
+ "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
22
+ "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
23
+ "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
24
+ "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
25
+ "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
26
+ "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
27
+ "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
28
+ "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
29
+ "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
30
+ "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
31
+ "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
32
+ "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
33
+ "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
34
+ "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
35
+ "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
36
+ "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
37
+ "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
38
+ "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
39
+ "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
40
+ "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
41
+ "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
42
+ "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
43
+ "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
44
+ "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
45
+ "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
46
+ "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
47
+ "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
48
+ "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
49
+ "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
50
+ "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
51
+ "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
52
+ "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
53
+ "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
54
+ "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
55
+ "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
56
+ "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
57
+ "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
58
+ "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
59
+ "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
60
+ "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
61
+ "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
62
+ "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
63
+ "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
64
+ "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
65
+ "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
66
+ "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
67
+ "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
68
+ "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
69
+ "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
70
+ "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
71
+ "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
72
+ "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
73
+ "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
74
+ "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
75
+ "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
76
+ "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
77
+ "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
78
+ "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
79
+ "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
80
+ "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
81
+ "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
82
+ "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
83
+ "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
84
+ "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
85
+ "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
86
+ "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
87
+ "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
88
+ "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
89
+ "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
90
+ "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
91
+ "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
92
+ "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
93
+ "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
94
+ "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
95
+ "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
96
+ "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
97
+ "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
98
+ "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
99
+ "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
100
+ "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
101
+ "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
102
+ "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
103
+ "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
104
+ "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
105
+ "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
106
+ "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
107
+ "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
108
+ "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
109
+ "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
110
+ "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
111
+ "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
112
+ "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
113
+ "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
114
+ "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
115
+ "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
116
+ "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
117
+ "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
118
+ "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
119
+ "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
120
+ "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
121
+ "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
122
+ "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
123
+ "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
124
+ "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
125
+ "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
126
+ "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
127
+ "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
128
+ "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
129
+ "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
130
+ "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
131
+ "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
132
+ "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
133
+ "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
134
+ "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
135
+ "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
136
+ "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
137
+ "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
138
+ "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
139
+ "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
140
+ "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
141
+ "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
142
+ "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
143
+ "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
144
+ "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
145
+ "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
146
+ "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
147
+ "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
148
+ "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
149
+ "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
150
+ "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
151
+ "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
152
+ "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
153
+ "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
154
+ "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
155
+ "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
156
+ "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
157
+ "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
158
+ "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
159
+ "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
160
+ "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
161
+ "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
162
+ "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
163
+ "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
164
+ "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
165
+ "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
166
+ "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
167
+ "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
168
+ "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
169
+ "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
170
+ "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
171
+ "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
172
+ "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
173
+ "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
174
+ "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
175
+ "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
176
+ "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
177
+ "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
178
+ "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
179
+ "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
180
+ "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
181
+ "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
182
+ "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
183
+ "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
184
+ "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
185
+ "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
186
+ "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
187
+ "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
188
+ "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
189
+ "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
190
+ "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
191
+ "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
192
+ "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
193
+ "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
194
+ "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
195
+ "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
196
+ "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
197
+ "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
198
+ "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
199
+ "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
200
+ "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
201
+ "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
202
+ "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
203
+ "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
204
+ "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
205
+ "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
206
+ "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
207
+ "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
208
+ "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
209
+ "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
210
+ "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
211
+ "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
212
+ "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
213
+ "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
214
+ "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
215
+ "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
216
+ "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
217
+ "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
218
+ "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
219
+ "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
220
+ "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
221
+ "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
222
+ "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
223
+ "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
224
+ "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
225
+ "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
226
+ "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
227
+ "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
228
+ "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
229
+ "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
230
+ "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
231
+ "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
232
+ "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
233
+ "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
234
+ "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
235
+ "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
236
+ "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
237
+ "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
238
+ "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
239
+ "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
240
+ "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
241
+ "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
242
+ "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
243
+ "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
244
+ "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
245
+ "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
246
+ "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
247
+ "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
248
+ "action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
249
+ "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
250
+ "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
251
+ "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
252
+ "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
253
+ "backbone.linear.bias": "model-00002-of-00002.safetensors",
254
+ "backbone.linear.weight": "model-00002-of-00002.safetensors",
255
+ "backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
256
+ "backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
257
+ "backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
258
+ "backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
259
+ "backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
260
+ "backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
262
+ "backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
263
+ "backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
264
+ "backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
265
+ "backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
267
+ "backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
268
+ "backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
269
+ "backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
271
+ "backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
272
+ "backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
273
+ "backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
274
+ "backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
275
+ "backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
276
+ "backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
277
+ "backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
278
+ "backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
279
+ "backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
282
+ "backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
283
+ "backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
289
+ "backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
290
+ "backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
291
+ "backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
292
+ "backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
294
+ "backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
295
+ "backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
296
+ "backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
297
+ "backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
298
+ "backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
299
+ "backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
300
+ "backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
301
+ "backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
302
+ "backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
303
+ "backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
304
+ "backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
305
+ "backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
306
+ "backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
307
+ "backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
308
+ "backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
309
+ "backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
310
+ "backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
311
+ "backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
312
+ "backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
313
+ "backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
314
+ "backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
315
+ "backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
320
+ "backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
321
+ "backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
322
+ "backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
323
+ "backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
324
+ "backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
325
+ "backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
326
+ "backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
327
+ "backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
328
+ "backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
329
+ "backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
330
+ "backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
331
+ "backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
332
+ "backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
333
+ "backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
334
+ "backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
335
+ "backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
336
+ "backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
337
+ "backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
339
+ "backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
340
+ "backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
341
+ "backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
343
+ "backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
344
+ "backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
345
+ "backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
346
+ "backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
347
+ "backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
348
+ "backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
349
+ "backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
350
+ "backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
351
+ "backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
352
+ "backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
353
+ "backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
354
+ "backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
355
+ "backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
356
+ "backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
357
+ "backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
358
+ "backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
359
+ "backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
360
+ "backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
361
+ "backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
362
+ "backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
363
+ "backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
364
+ "backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
365
+ "backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
366
+ "backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
367
+ "backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
368
+ "backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
369
+ "backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
370
+ "backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
371
+ "backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
372
+ "backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
373
+ "backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
374
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
375
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
376
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
377
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
378
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
379
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
380
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
381
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
382
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
383
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
384
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
385
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
386
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
387
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
388
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
389
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
390
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
391
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
392
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
393
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
394
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
395
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
396
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
397
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
398
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
399
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
401
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
402
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
403
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
404
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
405
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
406
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
407
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
408
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
409
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
410
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
411
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
412
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
413
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
414
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
415
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
416
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
417
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
418
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
419
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
420
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
421
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
422
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
423
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
424
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
425
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
426
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
427
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
428
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
429
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
430
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
431
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
432
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
433
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
434
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
435
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
436
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
437
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
438
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
439
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
440
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
441
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
442
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
443
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
444
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
445
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
446
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
447
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
448
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
449
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
450
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
451
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
452
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
453
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
454
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
455
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
456
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
457
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
458
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
459
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
460
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
461
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
462
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
463
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
464
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
465
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
466
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
467
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
468
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
469
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
470
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
471
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
472
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
473
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
474
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
475
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
476
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
477
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
478
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
479
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
480
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
481
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
482
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
483
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
484
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
485
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
486
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
487
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
488
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
489
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
490
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
491
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
492
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
493
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
494
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
495
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
496
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
497
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
498
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
499
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
500
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
501
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
502
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
503
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
504
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
505
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
506
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
507
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
508
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
509
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
510
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
511
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
512
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
513
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
514
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
515
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
516
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
517
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
518
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
519
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
520
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
521
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
522
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
523
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
524
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
525
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
526
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
527
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
528
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
529
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
530
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
531
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
532
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
533
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
534
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
535
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
536
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
537
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
538
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
539
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
540
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
541
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
542
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
543
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
544
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
545
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
546
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
547
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
548
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
549
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
550
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
551
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
552
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
553
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
554
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
555
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
556
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
557
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
558
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
559
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
560
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
561
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
562
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
563
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
564
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
565
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
566
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
567
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
568
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
569
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
570
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
571
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
572
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
573
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
574
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
575
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
576
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
577
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
578
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
579
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
580
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
581
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
582
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
583
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
584
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
585
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
586
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
587
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
588
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
589
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
590
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
591
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
592
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
593
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
594
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
595
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
596
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
597
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
598
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
599
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
600
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
601
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
602
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
603
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
604
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
605
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
606
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
607
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
608
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
609
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
610
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
611
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
612
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
613
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
614
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
615
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
616
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
617
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
618
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
619
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
620
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
621
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
622
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
623
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
624
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
625
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
626
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
627
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
628
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
629
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
630
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
631
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
632
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
633
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
634
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
635
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
636
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
637
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
638
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
639
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
640
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
641
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
642
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
643
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
644
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
645
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
646
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
647
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
648
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
649
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
650
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
651
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
652
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
653
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
654
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
655
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
656
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
657
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
658
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
659
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
660
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
661
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
662
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
663
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
664
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
665
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
666
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
667
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
668
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
669
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
670
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
671
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
672
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
673
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
674
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
675
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
676
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
677
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
678
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
679
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
680
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
681
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
682
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
683
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
684
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
685
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
686
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
687
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
688
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
689
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
690
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
691
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
692
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
693
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
694
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
695
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
696
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
697
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
698
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
699
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
700
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
701
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
702
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
703
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
704
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
705
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
706
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
707
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
708
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
709
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
710
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
711
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
712
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
713
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
714
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
715
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
716
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
717
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
718
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
719
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
720
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
721
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
722
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
723
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
724
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
725
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
726
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
727
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
728
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
729
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
730
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
731
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
732
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
733
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
734
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
735
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
736
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
737
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
738
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
739
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
740
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
741
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
742
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
743
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
744
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
745
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
746
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
747
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
748
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
749
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
750
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
751
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
752
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
753
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
754
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
755
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
756
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
757
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
758
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
759
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
760
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
761
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
762
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
763
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
764
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
765
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
766
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
767
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
768
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
769
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
770
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
771
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
772
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
773
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
774
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
775
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
776
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
777
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
778
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
779
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
780
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
781
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
782
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
783
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
784
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
785
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
786
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
787
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
788
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
789
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
790
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
791
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
792
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
793
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
794
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
795
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
796
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
797
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
798
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
799
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
800
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
801
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
802
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
803
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
804
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
805
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
806
+ "backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
807
+ "backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
808
+ }
809
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51566f6f1ce25666039cf9571e7ce3e12157226f2f706f6ea55e2036907306c0
3
+ size 10272357262
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be101452376a49a0f1b73cadd6f5d327efcc28a7b30d1cadd2dac6f1ab454233
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f8c6fa7eadbbf7fdb07c900e18e4e3363fd7e99294d872637f2906a84153a8
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,558 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.136986301369863,
5
+ "eval_steps": 500,
6
+ "global_step": 750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0684931506849315,
13
+ "grad_norm": 6.335273265838623,
14
+ "learning_rate": 8.000000000000001e-06,
15
+ "loss": 0.954,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.136986301369863,
20
+ "grad_norm": 2.381432056427002,
21
+ "learning_rate": 1.6000000000000003e-05,
22
+ "loss": 0.7291,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.2054794520547945,
27
+ "grad_norm": 2.1213607788085938,
28
+ "learning_rate": 2.4e-05,
29
+ "loss": 0.3867,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.273972602739726,
34
+ "grad_norm": 1.0599077939987183,
35
+ "learning_rate": 3.2000000000000005e-05,
36
+ "loss": 0.2747,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.3424657534246575,
41
+ "grad_norm": 1.1717661619186401,
42
+ "learning_rate": 4e-05,
43
+ "loss": 0.2013,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.410958904109589,
48
+ "grad_norm": 1.1004457473754883,
49
+ "learning_rate": 4.8e-05,
50
+ "loss": 0.1569,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.4794520547945205,
55
+ "grad_norm": 1.0647892951965332,
56
+ "learning_rate": 5.6000000000000006e-05,
57
+ "loss": 0.1391,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.547945205479452,
62
+ "grad_norm": 0.9715467095375061,
63
+ "learning_rate": 6.400000000000001e-05,
64
+ "loss": 0.1181,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.6164383561643836,
69
+ "grad_norm": 0.8772512674331665,
70
+ "learning_rate": 7.2e-05,
71
+ "loss": 0.1051,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.684931506849315,
76
+ "grad_norm": 1.2750014066696167,
77
+ "learning_rate": 8e-05,
78
+ "loss": 0.0947,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.7534246575342466,
83
+ "grad_norm": 0.6222656965255737,
84
+ "learning_rate": 8.800000000000001e-05,
85
+ "loss": 0.0978,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.821917808219178,
90
+ "grad_norm": 0.6259370446205139,
91
+ "learning_rate": 9.6e-05,
92
+ "loss": 0.0781,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.8904109589041096,
97
+ "grad_norm": 0.6297749876976013,
98
+ "learning_rate": 9.999890641901125e-05,
99
+ "loss": 0.0738,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.958904109589041,
104
+ "grad_norm": 0.4628015160560608,
105
+ "learning_rate": 9.999015805811965e-05,
106
+ "loss": 0.0748,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.0273972602739727,
111
+ "grad_norm": 0.6147599816322327,
112
+ "learning_rate": 9.997266286704631e-05,
113
+ "loss": 0.0641,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.095890410958904,
118
+ "grad_norm": 0.5399206280708313,
119
+ "learning_rate": 9.994642390694308e-05,
120
+ "loss": 0.0662,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.1643835616438356,
125
+ "grad_norm": 0.44403907656669617,
126
+ "learning_rate": 9.991144576886823e-05,
127
+ "loss": 0.0592,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 1.2328767123287672,
132
+ "grad_norm": 0.571832537651062,
133
+ "learning_rate": 9.986773457298311e-05,
134
+ "loss": 0.0556,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.3013698630136985,
139
+ "grad_norm": 0.561576247215271,
140
+ "learning_rate": 9.981529796748134e-05,
141
+ "loss": 0.0596,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.36986301369863,
146
+ "grad_norm": 0.4030166268348694,
147
+ "learning_rate": 9.975414512725057e-05,
148
+ "loss": 0.0539,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 1.4383561643835616,
153
+ "grad_norm": 0.34468358755111694,
154
+ "learning_rate": 9.968428675226714e-05,
155
+ "loss": 0.0577,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 1.5068493150684932,
160
+ "grad_norm": 0.483900785446167,
161
+ "learning_rate": 9.96057350657239e-05,
162
+ "loss": 0.052,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 1.5753424657534247,
167
+ "grad_norm": 0.4898487627506256,
168
+ "learning_rate": 9.95185038118915e-05,
169
+ "loss": 0.0477,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 1.643835616438356,
174
+ "grad_norm": 0.5045291781425476,
175
+ "learning_rate": 9.942260825371358e-05,
176
+ "loss": 0.0528,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 1.7123287671232876,
181
+ "grad_norm": 0.5695160031318665,
182
+ "learning_rate": 9.931806517013612e-05,
183
+ "loss": 0.0439,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.7808219178082192,
188
+ "grad_norm": 0.33678483963012695,
189
+ "learning_rate": 9.92048928531717e-05,
190
+ "loss": 0.0488,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 1.8493150684931505,
195
+ "grad_norm": 0.3467772305011749,
196
+ "learning_rate": 9.90831111046988e-05,
197
+ "loss": 0.0448,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.9178082191780823,
202
+ "grad_norm": 0.4071213901042938,
203
+ "learning_rate": 9.895274123299723e-05,
204
+ "loss": 0.0431,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 1.9863013698630136,
209
+ "grad_norm": 0.30543234944343567,
210
+ "learning_rate": 9.881380604901964e-05,
211
+ "loss": 0.0429,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 2.0547945205479454,
216
+ "grad_norm": 0.6378459334373474,
217
+ "learning_rate": 9.86663298624003e-05,
218
+ "loss": 0.0464,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 2.1232876712328768,
223
+ "grad_norm": 0.4035351276397705,
224
+ "learning_rate": 9.851033847720166e-05,
225
+ "loss": 0.0488,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 2.191780821917808,
230
+ "grad_norm": 0.3094054162502289,
231
+ "learning_rate": 9.834585918739936e-05,
232
+ "loss": 0.0364,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 2.26027397260274,
237
+ "grad_norm": 0.45768025517463684,
238
+ "learning_rate": 9.817292077210659e-05,
239
+ "loss": 0.0373,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 2.328767123287671,
244
+ "grad_norm": 0.504475474357605,
245
+ "learning_rate": 9.799155349053851e-05,
246
+ "loss": 0.047,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 2.3972602739726026,
251
+ "grad_norm": 0.36838439106941223,
252
+ "learning_rate": 9.780178907671789e-05,
253
+ "loss": 0.0396,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 2.4657534246575343,
258
+ "grad_norm": 0.3892686665058136,
259
+ "learning_rate": 9.760366073392246e-05,
260
+ "loss": 0.04,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 2.5342465753424657,
265
+ "grad_norm": 0.376288503408432,
266
+ "learning_rate": 9.739720312887535e-05,
267
+ "loss": 0.0352,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 2.602739726027397,
272
+ "grad_norm": 0.33039844036102295,
273
+ "learning_rate": 9.718245238567939e-05,
274
+ "loss": 0.0364,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 2.671232876712329,
279
+ "grad_norm": 0.38675811886787415,
280
+ "learning_rate": 9.695944607949649e-05,
281
+ "loss": 0.0367,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 2.73972602739726,
286
+ "grad_norm": 0.3453963100910187,
287
+ "learning_rate": 9.672822322997305e-05,
288
+ "loss": 0.0337,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 2.808219178082192,
293
+ "grad_norm": 0.5285444259643555,
294
+ "learning_rate": 9.648882429441257e-05,
295
+ "loss": 0.0414,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 2.8767123287671232,
300
+ "grad_norm": 0.38015297055244446,
301
+ "learning_rate": 9.624129116069694e-05,
302
+ "loss": 0.0348,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 2.9452054794520546,
307
+ "grad_norm": 0.44161203503608704,
308
+ "learning_rate": 9.598566713995718e-05,
309
+ "loss": 0.0377,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 3.0136986301369864,
314
+ "grad_norm": 0.4227602779865265,
315
+ "learning_rate": 9.572199695899522e-05,
316
+ "loss": 0.0323,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 3.0821917808219177,
321
+ "grad_norm": 0.2722010314464569,
322
+ "learning_rate": 9.545032675245813e-05,
323
+ "loss": 0.0345,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 3.1506849315068495,
328
+ "grad_norm": 0.4375353753566742,
329
+ "learning_rate": 9.517070405476575e-05,
330
+ "loss": 0.0315,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 3.219178082191781,
335
+ "grad_norm": 0.4301266372203827,
336
+ "learning_rate": 9.488317779179361e-05,
337
+ "loss": 0.0348,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 3.287671232876712,
342
+ "grad_norm": 0.458469957113266,
343
+ "learning_rate": 9.458779827231237e-05,
344
+ "loss": 0.0348,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 3.356164383561644,
349
+ "grad_norm": 0.3810347616672516,
350
+ "learning_rate": 9.428461717918511e-05,
351
+ "loss": 0.0304,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 3.4246575342465753,
356
+ "grad_norm": 0.3728407919406891,
357
+ "learning_rate": 9.397368756032445e-05,
358
+ "loss": 0.0332,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 3.493150684931507,
363
+ "grad_norm": 0.3293081223964691,
364
+ "learning_rate": 9.365506381941066e-05,
365
+ "loss": 0.0305,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 3.5616438356164384,
370
+ "grad_norm": 0.35907241702079773,
371
+ "learning_rate": 9.332880170637252e-05,
372
+ "loss": 0.0319,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 3.6301369863013697,
377
+ "grad_norm": 0.3396986126899719,
378
+ "learning_rate": 9.299495830763286e-05,
379
+ "loss": 0.0319,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 3.6986301369863015,
384
+ "grad_norm": 0.22632896900177002,
385
+ "learning_rate": 9.265359203611987e-05,
386
+ "loss": 0.0318,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 3.767123287671233,
391
+ "grad_norm": 0.2579493522644043,
392
+ "learning_rate": 9.230476262104677e-05,
393
+ "loss": 0.0295,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 3.8356164383561646,
398
+ "grad_norm": 0.2979259788990021,
399
+ "learning_rate": 9.194853109746074e-05,
400
+ "loss": 0.0317,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 3.904109589041096,
405
+ "grad_norm": 0.28193944692611694,
406
+ "learning_rate": 9.158495979556358e-05,
407
+ "loss": 0.0324,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 3.9726027397260273,
412
+ "grad_norm": 0.30196675658226013,
413
+ "learning_rate": 9.121411232980588e-05,
414
+ "loss": 0.0282,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 4.041095890410959,
419
+ "grad_norm": 0.2790427505970001,
420
+ "learning_rate": 9.083605358775612e-05,
421
+ "loss": 0.0322,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 4.109589041095891,
426
+ "grad_norm": 0.3180605173110962,
427
+ "learning_rate": 9.045084971874738e-05,
428
+ "loss": 0.0311,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 4.178082191780822,
433
+ "grad_norm": 0.23422259092330933,
434
+ "learning_rate": 9.005856812230304e-05,
435
+ "loss": 0.0313,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 4.2465753424657535,
440
+ "grad_norm": 0.1887388378381729,
441
+ "learning_rate": 8.965927743634391e-05,
442
+ "loss": 0.0297,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 4.315068493150685,
447
+ "grad_norm": 0.21844805777072906,
448
+ "learning_rate": 8.92530475251784e-05,
449
+ "loss": 0.0306,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 4.383561643835616,
454
+ "grad_norm": 0.45273661613464355,
455
+ "learning_rate": 8.883994946727849e-05,
456
+ "loss": 0.0292,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 4.4520547945205475,
461
+ "grad_norm": 0.39670127630233765,
462
+ "learning_rate": 8.842005554284296e-05,
463
+ "loss": 0.0331,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 4.52054794520548,
468
+ "grad_norm": 0.25612273812294006,
469
+ "learning_rate": 8.799343922115044e-05,
470
+ "loss": 0.0305,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 4.589041095890411,
475
+ "grad_norm": 0.22720636427402496,
476
+ "learning_rate": 8.756017514770443e-05,
477
+ "loss": 0.0284,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 4.657534246575342,
482
+ "grad_norm": 0.39644864201545715,
483
+ "learning_rate": 8.71203391311725e-05,
484
+ "loss": 0.0286,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 4.726027397260274,
489
+ "grad_norm": 0.4030825197696686,
490
+ "learning_rate": 8.6674008130122e-05,
491
+ "loss": 0.0268,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 4.794520547945205,
496
+ "grad_norm": 0.33811622858047485,
497
+ "learning_rate": 8.622126023955446e-05,
498
+ "loss": 0.0274,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 4.863013698630137,
503
+ "grad_norm": 0.27626654505729675,
504
+ "learning_rate": 8.576217467724128e-05,
505
+ "loss": 0.0267,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 4.931506849315069,
510
+ "grad_norm": 0.3249574899673462,
511
+ "learning_rate": 8.529683176986295e-05,
512
+ "loss": 0.0297,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 5.0,
517
+ "grad_norm": 0.6223666071891785,
518
+ "learning_rate": 8.482531293895412e-05,
519
+ "loss": 0.0289,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 5.068493150684931,
524
+ "grad_norm": 0.4200395941734314,
525
+ "learning_rate": 8.434770068665723e-05,
526
+ "loss": 0.0293,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 5.136986301369863,
531
+ "grad_norm": 0.33773040771484375,
532
+ "learning_rate": 8.386407858128706e-05,
533
+ "loss": 0.0243,
534
+ "step": 750
535
+ }
536
+ ],
537
+ "logging_steps": 10,
538
+ "max_steps": 2500,
539
+ "num_input_tokens_seen": 0,
540
+ "num_train_epochs": 18,
541
+ "save_steps": 125,
542
+ "stateful_callbacks": {
543
+ "TrainerControl": {
544
+ "args": {
545
+ "should_epoch_stop": false,
546
+ "should_evaluate": false,
547
+ "should_log": false,
548
+ "should_save": true,
549
+ "should_training_stop": false
550
+ },
551
+ "attributes": {}
552
+ }
553
+ },
554
+ "total_flos": 1.0243918948403232e+17,
555
+ "train_batch_size": 64,
556
+ "trial_name": null,
557
+ "trial_params": null
558
+ }