Hugging Face's logo

nextbig
/
starforce-3b-v0

Safetensors
starforce_s1
Model card Files
xet
Community
nextbig commited on
Commit
af36966
·
verified ·
1 Parent(s): 353097f

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +58 -0
  2. experiment_cfg/metadata.json +387 -0
  3. model-00001-of-00003.safetensors +3 -0
  4. model-00002-of-00003.safetensors +3 -0
  5. model-00003-of-00003.safetensors +3 -0
  6. model.safetensors.index.json +859 -0
  7. trainer_state.json +0 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "action_dim": 32,
3
+ "action_head_cfg": {
4
+ "action_dim": 32,
5
+ "action_horizon": 16,
6
+ "add_pos_embed": true,
7
+ "backbone_embedding_dim": 2048,
8
+ "diffusion_model_cfg": {
9
+ "attention_head_dim": 48,
10
+ "cross_attention_dim": 2048,
11
+ "dropout": 0.2,
12
+ "final_dropout": true,
13
+ "interleave_self_attention": true,
14
+ "norm_type": "ada_norm",
15
+ "num_attention_heads": 32,
16
+ "num_layers": 16,
17
+ "output_dim": 1024,
18
+ "positional_embeddings": null
19
+ },
20
+ "hidden_size": 1024,
21
+ "input_embedding_dim": 1536,
22
+ "max_action_dim": 32,
23
+ "max_state_dim": 64,
24
+ "model_dtype": "float32",
25
+ "noise_beta_alpha": 1.5,
26
+ "noise_beta_beta": 1.0,
27
+ "noise_s": 0.999,
28
+ "num_inference_timesteps": 4,
29
+ "num_target_vision_tokens": 32,
30
+ "num_timestep_buckets": 1000,
31
+ "tune_diffusion_model": true,
32
+ "tune_projector": true,
33
+ "use_vlln": true,
34
+ "vl_self_attention_cfg": {
35
+ "attention_head_dim": 64,
36
+ "dropout": 0.2,
37
+ "final_dropout": true,
38
+ "num_attention_heads": 32,
39
+ "num_layers": 4,
40
+ "positional_embeddings": null
41
+ }
42
+ },
43
+ "action_horizon": 16,
44
+ "architectures": [
45
+ "Starforce_S1"
46
+ ],
47
+ "attn_implementation": null,
48
+ "backbone_cfg": {
49
+ "project_to_dim": 2048,
50
+ "select_layer": 12,
51
+ "tune_llm": false,
52
+ "vllm_base_model_path": "checkpoints/Qwen2.5-VL-3B-Instruct"
53
+ },
54
+ "compute_dtype": "bfloat16",
55
+ "model_type": "starforce_s1",
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.51.3"
58
+ }
experiment_cfg/metadata.json ADDED
@@ -0,0 +1,387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "new_embodiment": {
3
+ "statistics": {
4
+ "state": {
5
+ "left_arm": {
6
+ "max": [
7
+ 0.028386248275637627,
8
+ 3.8291454315185547,
9
+ 4.531617164611816,
10
+ 1.5979410409927368,
11
+ 1.2893240451812744,
12
+ 1.9682021141052246
13
+ ],
14
+ "min": [
15
+ -1.0874532461166382,
16
+ -1.1016938515240327e-05,
17
+ -0.0016509370179846883,
18
+ -1.9563316106796265,
19
+ -1.3035399913787842,
20
+ -5.517308235168457
21
+ ],
22
+ "mean": [
23
+ -0.24873395179316682,
24
+ 1.20304758782828,
25
+ 0.8961652763150714,
26
+ -0.47400657036084537,
27
+ 0.07538467442301071,
28
+ 0.1852616305015898
29
+ ],
30
+ "std": [
31
+ 0.2657169175038166,
32
+ 0.9994392727506382,
33
+ 0.8266723802763669,
34
+ 0.6527157251083382,
35
+ 0.2917792295710166,
36
+ 0.5195768478640669
37
+ ],
38
+ "q01": [
39
+ -0.76131535333529,
40
+ 0.0,
41
+ -1.3604623604662279e-05,
42
+ -1.5672673129201617,
43
+ -0.15860364420114587,
44
+ -0.6651115738454233
45
+ ],
46
+ "q99": [
47
+ 0.008882988533419811,
48
+ 2.570175074548637,
49
+ 2.4436710772465036,
50
+ 0.6765962560162986,
51
+ 0.6707903538716176,
52
+ 1.3596203121924704
53
+ ]
54
+ },
55
+ "left_gripper": {
56
+ "max": [
57
+ 1.0
58
+ ],
59
+ "min": [
60
+ 0.0
61
+ ],
62
+ "mean": [
63
+ 0.6461290622532674
64
+ ],
65
+ "std": [
66
+ 0.46351442328258813
67
+ ],
68
+ "q01": [
69
+ 0.0
70
+ ],
71
+ "q99": [
72
+ 1.0
73
+ ]
74
+ },
75
+ "right_arm": {
76
+ "max": [
77
+ 1.0705821514129639,
78
+ 3.7924766540527344,
79
+ 4.627494812011719,
80
+ 1.9165027141571045,
81
+ 1.4920110702514648,
82
+ 5.2781548500061035
83
+ ],
84
+ "min": [
85
+ -8.5399169921875,
86
+ -0.626270592212677,
87
+ -0.0023644985631108284,
88
+ -2.0034823417663574,
89
+ -1.1340138912200928,
90
+ -4.045521259307861
91
+ ],
92
+ "mean": [
93
+ 0.18279155418071263,
94
+ 1.1704241595052947,
95
+ 0.9308129959746257,
96
+ -0.46743315360802434,
97
+ -0.006775139919187014,
98
+ -0.1412867797629498
99
+ ],
100
+ "std": [
101
+ 0.6272266698907886,
102
+ 1.0203715447391875,
103
+ 0.862183653303289,
104
+ 0.6772284907366957,
105
+ 0.27451755571859393,
106
+ 0.6675314761949047
107
+ ],
108
+ "q01": [
109
+ -2.5161718449581443,
110
+ -0.23770474638803446,
111
+ -1.062960664345454e-05,
112
+ -1.6431772501976352,
113
+ -0.5999989872998127,
114
+ -1.6846236907914132
115
+ ],
116
+ "q99": [
117
+ 0.8224301011570899,
118
+ 2.5934956215872633,
119
+ 2.733773587743206,
120
+ 0.8198583532970538,
121
+ 0.7163819747543168,
122
+ 1.7400009686694697
123
+ ]
124
+ },
125
+ "right_gripper": {
126
+ "max": [
127
+ 1.0
128
+ ],
129
+ "min": [
130
+ 0.0
131
+ ],
132
+ "mean": [
133
+ 0.6453511363271474
134
+ ],
135
+ "std": [
136
+ 0.4635804001550843
137
+ ],
138
+ "q01": [
139
+ 0.0
140
+ ],
141
+ "q99": [
142
+ 1.0
143
+ ]
144
+ }
145
+ },
146
+ "action": {
147
+ "left_arm": {
148
+ "max": [
149
+ 0.028386248275637627,
150
+ 3.8291454315185547,
151
+ 4.531617164611816,
152
+ 1.5979410409927368,
153
+ 1.2893240451812744,
154
+ 1.9682021141052246
155
+ ],
156
+ "min": [
157
+ -1.0874532461166382,
158
+ -1.1016938515240327e-05,
159
+ -0.0016509370179846883,
160
+ -1.9563316106796265,
161
+ -1.3035399913787842,
162
+ -5.517308235168457
163
+ ],
164
+ "mean": [
165
+ -0.250489821057887,
166
+ 1.2096493687417171,
167
+ 0.9012527534024196,
168
+ -0.4766287635770255,
169
+ 0.07514412924037535,
170
+ 0.18693278526527476
171
+ ],
172
+ "std": [
173
+ 0.2657986202082524,
174
+ 0.9979742789410523,
175
+ 0.8268724898530565,
176
+ 0.6545924099509021,
177
+ 0.29206973702584077,
178
+ 0.5211376260767341
179
+ ],
180
+ "q01": [
181
+ -0.7617348821620069,
182
+ 0.0,
183
+ -1.3604623604662279e-05,
184
+ -1.568813525549133,
185
+ -0.15980671979415398,
186
+ -0.6654537841855944
187
+ ],
188
+ "q99": [
189
+ 0.008882988533419811,
190
+ 2.5702339072888973,
191
+ 2.4465517105355428,
192
+ 0.6768845884148182,
193
+ 0.6717806602989578,
194
+ 1.3596203121924704
195
+ ]
196
+ },
197
+ "left_gripper": {
198
+ "max": [
199
+ 1.0
200
+ ],
201
+ "min": [
202
+ 0.0
203
+ ],
204
+ "mean": [
205
+ 0.6434114207121902
206
+ ],
207
+ "std": [
208
+ 0.46437440665350477
209
+ ],
210
+ "q01": [
211
+ 0.0
212
+ ],
213
+ "q99": [
214
+ 1.0
215
+ ]
216
+ },
217
+ "right_arm": {
218
+ "max": [
219
+ 1.0705821514129639,
220
+ 3.7924766540527344,
221
+ 4.627494812011719,
222
+ 1.9165027141571045,
223
+ 1.4926984310150146,
224
+ 5.2781548500061035
225
+ ],
226
+ "min": [
227
+ -8.5399169921875,
228
+ -0.626270592212677,
229
+ -0.0023644985631108284,
230
+ -2.0034823417663574,
231
+ -1.1340138912200928,
232
+ -4.045521259307861
233
+ ],
234
+ "mean": [
235
+ 0.1847503366704651,
236
+ 1.177295750418034,
237
+ 0.9364356012409922,
238
+ -0.470384427452085,
239
+ -0.006297215123100594,
240
+ -0.14300655022662584
241
+ ],
242
+ "std": [
243
+ 0.6274643902308454,
244
+ 1.019601594757656,
245
+ 0.8627576118367177,
246
+ 0.6793038272348151,
247
+ 0.2751963082492061,
248
+ 0.6687146861314195
249
+ ],
250
+ "q01": [
251
+ -2.51615847853924,
252
+ -0.23765859175781345,
253
+ 3.002811730454637e-05,
254
+ -1.6435741124066157,
255
+ -0.6008508307438889,
256
+ -1.6846236907914132
257
+ ],
258
+ "q99": [
259
+ 0.8224301011570899,
260
+ 2.593506571879349,
261
+ 2.7352777339935295,
262
+ 0.8202188173182625,
263
+ 0.7186558284630454,
264
+ 1.7438166198961447
265
+ ]
266
+ },
267
+ "right_gripper": {
268
+ "max": [
269
+ 1.0
270
+ ],
271
+ "min": [
272
+ 0.0
273
+ ],
274
+ "mean": [
275
+ 0.64264604477628
276
+ ],
277
+ "std": [
278
+ 0.4643728379785374
279
+ ],
280
+ "q01": [
281
+ 0.0
282
+ ],
283
+ "q99": [
284
+ 1.0
285
+ ]
286
+ }
287
+ }
288
+ },
289
+ "modalities": {
290
+ "video": {
291
+ "cam_high": {
292
+ "resolution": [
293
+ 640,
294
+ 480
295
+ ],
296
+ "channels": 3,
297
+ "fps": 30.0
298
+ },
299
+ "cam_left_wrist": {
300
+ "resolution": [
301
+ 640,
302
+ 480
303
+ ],
304
+ "channels": 3,
305
+ "fps": 30.0
306
+ },
307
+ "cam_right_wrist": {
308
+ "resolution": [
309
+ 640,
310
+ 480
311
+ ],
312
+ "channels": 3,
313
+ "fps": 30.0
314
+ }
315
+ },
316
+ "state": {
317
+ "left_arm": {
318
+ "absolute": true,
319
+ "rotation_type": null,
320
+ "shape": [
321
+ 6
322
+ ],
323
+ "continuous": true
324
+ },
325
+ "left_gripper": {
326
+ "absolute": true,
327
+ "rotation_type": null,
328
+ "shape": [
329
+ 1
330
+ ],
331
+ "continuous": true
332
+ },
333
+ "right_arm": {
334
+ "absolute": true,
335
+ "rotation_type": null,
336
+ "shape": [
337
+ 6
338
+ ],
339
+ "continuous": true
340
+ },
341
+ "right_gripper": {
342
+ "absolute": true,
343
+ "rotation_type": null,
344
+ "shape": [
345
+ 1
346
+ ],
347
+ "continuous": true
348
+ }
349
+ },
350
+ "action": {
351
+ "left_arm": {
352
+ "absolute": true,
353
+ "rotation_type": null,
354
+ "shape": [
355
+ 6
356
+ ],
357
+ "continuous": true
358
+ },
359
+ "left_gripper": {
360
+ "absolute": true,
361
+ "rotation_type": null,
362
+ "shape": [
363
+ 1
364
+ ],
365
+ "continuous": true
366
+ },
367
+ "right_arm": {
368
+ "absolute": true,
369
+ "rotation_type": null,
370
+ "shape": [
371
+ 6
372
+ ],
373
+ "continuous": true
374
+ },
375
+ "right_gripper": {
376
+ "absolute": true,
377
+ "rotation_type": null,
378
+ "shape": [
379
+ 1
380
+ ],
381
+ "continuous": true
382
+ }
383
+ }
384
+ },
385
+ "embodiment_tag": "new_embodiment"
386
+ }
387
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c063ebcb2e25e3257f485699f2ebecb4280da96ad5258a611ea86e1f33194028
3
+ size 4972313088
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700712710f753bfd4f4b5582ffc5877c92aa089335395a77f2b7c3200ed1aa1b
3
+ size 4964255640
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac245db64050deb4090fc9158d7821f589b07d40d227d16a7064ce42d45c017d
3
+ size 3219115832
model.safetensors.index.json ADDED
@@ -0,0 +1,859 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13155573760
4
+ },
5
+ "weight_map": {
6
+ "action_head.action_decoder.layer1.W": "model-00003-of-00003.safetensors",
7
+ "action_head.action_decoder.layer1.b": "model-00003-of-00003.safetensors",
8
+ "action_head.action_decoder.layer2.W": "model-00003-of-00003.safetensors",
9
+ "action_head.action_decoder.layer2.b": "model-00003-of-00003.safetensors",
10
+ "action_head.action_encoder.W1.W": "model-00003-of-00003.safetensors",
11
+ "action_head.action_encoder.W1.b": "model-00003-of-00003.safetensors",
12
+ "action_head.action_encoder.W2.W": "model-00003-of-00003.safetensors",
13
+ "action_head.action_encoder.W2.b": "model-00003-of-00003.safetensors",
14
+ "action_head.action_encoder.W3.W": "model-00003-of-00003.safetensors",
15
+ "action_head.action_encoder.W3.b": "model-00003-of-00003.safetensors",
16
+ "action_head.model.proj_out_1.bias": "model-00003-of-00003.safetensors",
17
+ "action_head.model.proj_out_1.weight": "model-00003-of-00003.safetensors",
18
+ "action_head.model.proj_out_2.bias": "model-00003-of-00003.safetensors",
19
+ "action_head.model.proj_out_2.weight": "model-00003-of-00003.safetensors",
20
+ "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00003.safetensors",
21
+ "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00003.safetensors",
22
+ "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00003.safetensors",
23
+ "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00003.safetensors",
24
+ "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00003.safetensors",
25
+ "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00003.safetensors",
26
+ "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
27
+ "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
28
+ "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00003.safetensors",
29
+ "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00003.safetensors",
30
+ "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00003.safetensors",
31
+ "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00003.safetensors",
32
+ "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
33
+ "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
34
+ "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00003.safetensors",
35
+ "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00003.safetensors",
36
+ "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00003.safetensors",
37
+ "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00003.safetensors",
38
+ "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00003.safetensors",
39
+ "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00003.safetensors",
40
+ "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
41
+ "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
42
+ "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00003.safetensors",
43
+ "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00003.safetensors",
44
+ "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00003.safetensors",
45
+ "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00003.safetensors",
46
+ "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
47
+ "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
48
+ "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00003.safetensors",
49
+ "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00003.safetensors",
50
+ "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00003.safetensors",
51
+ "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00003.safetensors",
52
+ "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00003-of-00003.safetensors",
53
+ "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00003-of-00003.safetensors",
54
+ "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
55
+ "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
56
+ "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00003-of-00003.safetensors",
57
+ "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00003-of-00003.safetensors",
58
+ "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00003-of-00003.safetensors",
59
+ "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00003-of-00003.safetensors",
60
+ "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
61
+ "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
62
+ "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00003-of-00003.safetensors",
63
+ "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00003-of-00003.safetensors",
64
+ "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00003-of-00003.safetensors",
65
+ "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00003-of-00003.safetensors",
66
+ "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00003-of-00003.safetensors",
67
+ "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00003-of-00003.safetensors",
68
+ "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
69
+ "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
70
+ "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00003-of-00003.safetensors",
71
+ "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00003-of-00003.safetensors",
72
+ "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00003-of-00003.safetensors",
73
+ "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00003-of-00003.safetensors",
74
+ "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
75
+ "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
76
+ "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00003-of-00003.safetensors",
77
+ "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00003-of-00003.safetensors",
78
+ "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00003-of-00003.safetensors",
79
+ "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00003-of-00003.safetensors",
80
+ "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00003-of-00003.safetensors",
81
+ "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00003-of-00003.safetensors",
82
+ "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
83
+ "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
84
+ "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00003-of-00003.safetensors",
85
+ "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00003-of-00003.safetensors",
86
+ "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00003-of-00003.safetensors",
87
+ "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00003-of-00003.safetensors",
88
+ "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
89
+ "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
90
+ "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00003-of-00003.safetensors",
91
+ "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00003-of-00003.safetensors",
92
+ "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00003-of-00003.safetensors",
93
+ "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00003-of-00003.safetensors",
94
+ "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00003-of-00003.safetensors",
95
+ "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00003-of-00003.safetensors",
96
+ "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
97
+ "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
98
+ "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00003-of-00003.safetensors",
99
+ "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00003-of-00003.safetensors",
100
+ "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00003-of-00003.safetensors",
101
+ "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00003-of-00003.safetensors",
102
+ "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
103
+ "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
104
+ "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00003-of-00003.safetensors",
105
+ "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00003-of-00003.safetensors",
106
+ "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00003-of-00003.safetensors",
107
+ "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00003-of-00003.safetensors",
108
+ "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00003-of-00003.safetensors",
109
+ "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00003-of-00003.safetensors",
110
+ "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
111
+ "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
112
+ "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00003-of-00003.safetensors",
113
+ "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00003-of-00003.safetensors",
114
+ "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00003-of-00003.safetensors",
115
+ "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00003-of-00003.safetensors",
116
+ "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
117
+ "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
118
+ "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00003-of-00003.safetensors",
119
+ "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00003-of-00003.safetensors",
120
+ "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00003-of-00003.safetensors",
121
+ "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00003-of-00003.safetensors",
122
+ "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00003-of-00003.safetensors",
123
+ "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00003-of-00003.safetensors",
124
+ "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
125
+ "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
126
+ "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00003-of-00003.safetensors",
127
+ "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00003-of-00003.safetensors",
128
+ "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00003-of-00003.safetensors",
129
+ "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00003-of-00003.safetensors",
130
+ "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
131
+ "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
132
+ "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00003-of-00003.safetensors",
133
+ "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00003-of-00003.safetensors",
134
+ "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00003-of-00003.safetensors",
135
+ "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00003-of-00003.safetensors",
136
+ "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00003.safetensors",
137
+ "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00003.safetensors",
138
+ "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
139
+ "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
140
+ "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00003.safetensors",
141
+ "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00003.safetensors",
142
+ "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00003.safetensors",
143
+ "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00003.safetensors",
144
+ "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
145
+ "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
146
+ "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00003.safetensors",
147
+ "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00003.safetensors",
148
+ "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00003.safetensors",
149
+ "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00003.safetensors",
150
+ "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00003.safetensors",
151
+ "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00003.safetensors",
152
+ "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
153
+ "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
154
+ "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00003.safetensors",
155
+ "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00003.safetensors",
156
+ "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00003.safetensors",
157
+ "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00003.safetensors",
158
+ "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
159
+ "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
160
+ "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00003.safetensors",
161
+ "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00003.safetensors",
162
+ "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00003.safetensors",
163
+ "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00003.safetensors",
164
+ "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00003.safetensors",
165
+ "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00003.safetensors",
166
+ "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
167
+ "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
168
+ "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00003.safetensors",
169
+ "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00003.safetensors",
170
+ "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00003.safetensors",
171
+ "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00003.safetensors",
172
+ "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
173
+ "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
174
+ "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00003.safetensors",
175
+ "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00003.safetensors",
176
+ "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00003.safetensors",
177
+ "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00003.safetensors",
178
+ "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00003.safetensors",
179
+ "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00003.safetensors",
180
+ "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
181
+ "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
182
+ "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00003.safetensors",
183
+ "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00003.safetensors",
184
+ "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00003.safetensors",
185
+ "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00003.safetensors",
186
+ "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
187
+ "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
188
+ "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00003.safetensors",
189
+ "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00003.safetensors",
190
+ "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00003.safetensors",
191
+ "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00003.safetensors",
192
+ "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00003.safetensors",
193
+ "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00003.safetensors",
194
+ "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
195
+ "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
196
+ "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00003.safetensors",
197
+ "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00003.safetensors",
198
+ "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00003.safetensors",
199
+ "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00003.safetensors",
200
+ "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
201
+ "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
202
+ "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00003.safetensors",
203
+ "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00003.safetensors",
204
+ "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00003.safetensors",
205
+ "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00003.safetensors",
206
+ "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00003.safetensors",
207
+ "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00003.safetensors",
208
+ "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00003.safetensors",
209
+ "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00003.safetensors",
210
+ "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00003.safetensors",
211
+ "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00003.safetensors",
212
+ "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00003.safetensors",
213
+ "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00003.safetensors",
214
+ "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00003.safetensors",
215
+ "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00003.safetensors",
216
+ "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00003-of-00003.safetensors",
217
+ "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00003-of-00003.safetensors",
218
+ "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00003.safetensors",
219
+ "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00003.safetensors",
220
+ "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00003-of-00003.safetensors",
221
+ "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00003-of-00003.safetensors",
222
+ "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
223
+ "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
224
+ "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00003-of-00003.safetensors",
225
+ "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00003-of-00003.safetensors",
226
+ "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00003-of-00003.safetensors",
227
+ "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00003-of-00003.safetensors",
228
+ "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
229
+ "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
230
+ "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00003-of-00003.safetensors",
231
+ "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00003-of-00003.safetensors",
232
+ "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00003-of-00003.safetensors",
233
+ "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00003-of-00003.safetensors",
234
+ "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00003-of-00003.safetensors",
235
+ "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00003-of-00003.safetensors",
236
+ "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
237
+ "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
238
+ "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00003-of-00003.safetensors",
239
+ "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00003-of-00003.safetensors",
240
+ "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00003-of-00003.safetensors",
241
+ "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00003-of-00003.safetensors",
242
+ "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
243
+ "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
244
+ "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00003-of-00003.safetensors",
245
+ "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00003-of-00003.safetensors",
246
+ "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00003-of-00003.safetensors",
247
+ "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00003-of-00003.safetensors",
248
+ "action_head.position_embedding.weight": "model-00003-of-00003.safetensors",
249
+ "action_head.state_encoder.layer1.W": "model-00003-of-00003.safetensors",
250
+ "action_head.state_encoder.layer1.b": "model-00003-of-00003.safetensors",
251
+ "action_head.state_encoder.layer2.W": "model-00003-of-00003.safetensors",
252
+ "action_head.state_encoder.layer2.b": "model-00003-of-00003.safetensors",
253
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00003-of-00003.safetensors",
254
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00003-of-00003.safetensors",
255
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
256
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
257
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00003-of-00003.safetensors",
258
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00003-of-00003.safetensors",
259
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00003-of-00003.safetensors",
260
+ "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00003-of-00003.safetensors",
261
+ "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
262
+ "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
263
+ "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00003-of-00003.safetensors",
264
+ "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00003-of-00003.safetensors",
265
+ "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00003-of-00003.safetensors",
266
+ "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00003-of-00003.safetensors",
267
+ "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00003-of-00003.safetensors",
268
+ "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00003-of-00003.safetensors",
269
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00003-of-00003.safetensors",
270
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00003-of-00003.safetensors",
271
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
272
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
273
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00003-of-00003.safetensors",
274
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00003-of-00003.safetensors",
275
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00003-of-00003.safetensors",
276
+ "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00003-of-00003.safetensors",
277
+ "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
278
+ "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
279
+ "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00003-of-00003.safetensors",
280
+ "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00003-of-00003.safetensors",
281
+ "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00003-of-00003.safetensors",
282
+ "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00003-of-00003.safetensors",
283
+ "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00003-of-00003.safetensors",
284
+ "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00003-of-00003.safetensors",
285
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00003-of-00003.safetensors",
286
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00003-of-00003.safetensors",
287
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
288
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
289
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00003-of-00003.safetensors",
290
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00003-of-00003.safetensors",
291
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00003-of-00003.safetensors",
292
+ "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00003-of-00003.safetensors",
293
+ "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
294
+ "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
295
+ "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00003-of-00003.safetensors",
296
+ "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00003-of-00003.safetensors",
297
+ "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00003-of-00003.safetensors",
298
+ "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00003-of-00003.safetensors",
299
+ "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00003-of-00003.safetensors",
300
+ "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00003-of-00003.safetensors",
301
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00003-of-00003.safetensors",
302
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00003-of-00003.safetensors",
303
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00003-of-00003.safetensors",
304
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00003-of-00003.safetensors",
305
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00003-of-00003.safetensors",
306
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00003-of-00003.safetensors",
307
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00003-of-00003.safetensors",
308
+ "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00003-of-00003.safetensors",
309
+ "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00003-of-00003.safetensors",
310
+ "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00003-of-00003.safetensors",
311
+ "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00003-of-00003.safetensors",
312
+ "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00003-of-00003.safetensors",
313
+ "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00003-of-00003.safetensors",
314
+ "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00003-of-00003.safetensors",
315
+ "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00003-of-00003.safetensors",
316
+ "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00003-of-00003.safetensors",
317
+ "action_head.vlln.bias": "model-00003-of-00003.safetensors",
318
+ "action_head.vlln.weight": "model-00003-of-00003.safetensors",
319
+ "backbone.eagle_linear.bias": "model-00002-of-00003.safetensors",
320
+ "backbone.eagle_linear.weight": "model-00002-of-00003.safetensors",
321
+ "backbone.vllm_model.lm_head.weight": "model-00002-of-00003.safetensors",
322
+ "backbone.vllm_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
323
+ "backbone.vllm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
324
+ "backbone.vllm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
325
+ "backbone.vllm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
326
+ "backbone.vllm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
327
+ "backbone.vllm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "backbone.vllm_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
329
+ "backbone.vllm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
330
+ "backbone.vllm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
331
+ "backbone.vllm_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
332
+ "backbone.vllm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
333
+ "backbone.vllm_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
334
+ "backbone.vllm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
335
+ "backbone.vllm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
336
+ "backbone.vllm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
337
+ "backbone.vllm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
338
+ "backbone.vllm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
339
+ "backbone.vllm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
340
+ "backbone.vllm_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
341
+ "backbone.vllm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
342
+ "backbone.vllm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
343
+ "backbone.vllm_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
344
+ "backbone.vllm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
345
+ "backbone.vllm_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
346
+ "backbone.vllm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
347
+ "backbone.vllm_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
348
+ "backbone.vllm_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
349
+ "backbone.vllm_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
350
+ "backbone.vllm_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
351
+ "backbone.vllm_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
352
+ "backbone.vllm_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
353
+ "backbone.vllm_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
354
+ "backbone.vllm_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
355
+ "backbone.vllm_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
356
+ "backbone.vllm_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
357
+ "backbone.vllm_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
358
+ "backbone.vllm_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
359
+ "backbone.vllm_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
360
+ "backbone.vllm_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
361
+ "backbone.vllm_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
362
+ "backbone.vllm_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
363
+ "backbone.vllm_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
364
+ "backbone.vllm_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
365
+ "backbone.vllm_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
366
+ "backbone.vllm_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
367
+ "backbone.vllm_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
368
+ "backbone.vllm_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
369
+ "backbone.vllm_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
370
+ "backbone.vllm_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
371
+ "backbone.vllm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
372
+ "backbone.vllm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
373
+ "backbone.vllm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
374
+ "backbone.vllm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
375
+ "backbone.vllm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
376
+ "backbone.vllm_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
377
+ "backbone.vllm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
378
+ "backbone.vllm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
379
+ "backbone.vllm_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
380
+ "backbone.vllm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
381
+ "backbone.vllm_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
382
+ "backbone.vllm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
383
+ "backbone.vllm_model.model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
384
+ "backbone.vllm_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
385
+ "backbone.vllm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
386
+ "backbone.vllm_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
387
+ "backbone.vllm_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
388
+ "backbone.vllm_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
389
+ "backbone.vllm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
390
+ "backbone.vllm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
391
+ "backbone.vllm_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
392
+ "backbone.vllm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
393
+ "backbone.vllm_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
394
+ "backbone.vllm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
395
+ "backbone.vllm_model.model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
396
+ "backbone.vllm_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
397
+ "backbone.vllm_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
398
+ "backbone.vllm_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
399
+ "backbone.vllm_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
400
+ "backbone.vllm_model.model.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
401
+ "backbone.vllm_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
402
+ "backbone.vllm_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
403
+ "backbone.vllm_model.model.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
404
+ "backbone.vllm_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
405
+ "backbone.vllm_model.model.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
406
+ "backbone.vllm_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
407
+ "backbone.vllm_model.model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
408
+ "backbone.vllm_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
409
+ "backbone.vllm_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
410
+ "backbone.vllm_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
411
+ "backbone.vllm_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
412
+ "backbone.vllm_model.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
413
+ "backbone.vllm_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
414
+ "backbone.vllm_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
415
+ "backbone.vllm_model.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
416
+ "backbone.vllm_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
417
+ "backbone.vllm_model.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
418
+ "backbone.vllm_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
419
+ "backbone.vllm_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
420
+ "backbone.vllm_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
421
+ "backbone.vllm_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
422
+ "backbone.vllm_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
423
+ "backbone.vllm_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
424
+ "backbone.vllm_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
425
+ "backbone.vllm_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
426
+ "backbone.vllm_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
427
+ "backbone.vllm_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
428
+ "backbone.vllm_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
429
+ "backbone.vllm_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
430
+ "backbone.vllm_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
431
+ "backbone.vllm_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
432
+ "backbone.vllm_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
433
+ "backbone.vllm_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
434
+ "backbone.vllm_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
435
+ "backbone.vllm_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
436
+ "backbone.vllm_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
437
+ "backbone.vllm_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
438
+ "backbone.vllm_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
439
+ "backbone.vllm_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
440
+ "backbone.vllm_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
441
+ "backbone.vllm_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
442
+ "backbone.vllm_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
443
+ "backbone.vllm_model.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
444
+ "backbone.vllm_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
445
+ "backbone.vllm_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
446
+ "backbone.vllm_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
447
+ "backbone.vllm_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
448
+ "backbone.vllm_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
449
+ "backbone.vllm_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
450
+ "backbone.vllm_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
451
+ "backbone.vllm_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
452
+ "backbone.vllm_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
453
+ "backbone.vllm_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
454
+ "backbone.vllm_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
455
+ "backbone.vllm_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
456
+ "backbone.vllm_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
457
+ "backbone.vllm_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
458
+ "backbone.vllm_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
459
+ "backbone.vllm_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
460
+ "backbone.vllm_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
461
+ "backbone.vllm_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
462
+ "backbone.vllm_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
463
+ "backbone.vllm_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
464
+ "backbone.vllm_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
465
+ "backbone.vllm_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
466
+ "backbone.vllm_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
467
+ "backbone.vllm_model.model.norm.weight": "model-00002-of-00003.safetensors",
468
+ "backbone.vllm_model.visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
469
+ "backbone.vllm_model.visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
470
+ "backbone.vllm_model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
471
+ "backbone.vllm_model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
472
+ "backbone.vllm_model.visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
473
+ "backbone.vllm_model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
474
+ "backbone.vllm_model.visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
475
+ "backbone.vllm_model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
476
+ "backbone.vllm_model.visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
477
+ "backbone.vllm_model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
478
+ "backbone.vllm_model.visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
479
+ "backbone.vllm_model.visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
480
+ "backbone.vllm_model.visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
481
+ "backbone.vllm_model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
482
+ "backbone.vllm_model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
483
+ "backbone.vllm_model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
484
+ "backbone.vllm_model.visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
485
+ "backbone.vllm_model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
486
+ "backbone.vllm_model.visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
487
+ "backbone.vllm_model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
488
+ "backbone.vllm_model.visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
489
+ "backbone.vllm_model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
490
+ "backbone.vllm_model.visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
491
+ "backbone.vllm_model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
492
+ "backbone.vllm_model.visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
493
+ "backbone.vllm_model.visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
494
+ "backbone.vllm_model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
495
+ "backbone.vllm_model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
496
+ "backbone.vllm_model.visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
497
+ "backbone.vllm_model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
498
+ "backbone.vllm_model.visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
499
+ "backbone.vllm_model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
500
+ "backbone.vllm_model.visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
501
+ "backbone.vllm_model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
502
+ "backbone.vllm_model.visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
503
+ "backbone.vllm_model.visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
504
+ "backbone.vllm_model.visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
505
+ "backbone.vllm_model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
506
+ "backbone.vllm_model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
507
+ "backbone.vllm_model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
508
+ "backbone.vllm_model.visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
509
+ "backbone.vllm_model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
510
+ "backbone.vllm_model.visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
511
+ "backbone.vllm_model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
512
+ "backbone.vllm_model.visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
513
+ "backbone.vllm_model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
514
+ "backbone.vllm_model.visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
515
+ "backbone.vllm_model.visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
516
+ "backbone.vllm_model.visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
517
+ "backbone.vllm_model.visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
518
+ "backbone.vllm_model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
519
+ "backbone.vllm_model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
520
+ "backbone.vllm_model.visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
521
+ "backbone.vllm_model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
522
+ "backbone.vllm_model.visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
523
+ "backbone.vllm_model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
524
+ "backbone.vllm_model.visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
525
+ "backbone.vllm_model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
526
+ "backbone.vllm_model.visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
527
+ "backbone.vllm_model.visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
528
+ "backbone.vllm_model.visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
529
+ "backbone.vllm_model.visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
530
+ "backbone.vllm_model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
531
+ "backbone.vllm_model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
532
+ "backbone.vllm_model.visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
533
+ "backbone.vllm_model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
534
+ "backbone.vllm_model.visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
535
+ "backbone.vllm_model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
536
+ "backbone.vllm_model.visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
537
+ "backbone.vllm_model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
538
+ "backbone.vllm_model.visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
539
+ "backbone.vllm_model.visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
540
+ "backbone.vllm_model.visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
541
+ "backbone.vllm_model.visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
542
+ "backbone.vllm_model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
543
+ "backbone.vllm_model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
544
+ "backbone.vllm_model.visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
545
+ "backbone.vllm_model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
546
+ "backbone.vllm_model.visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
547
+ "backbone.vllm_model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
548
+ "backbone.vllm_model.visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
549
+ "backbone.vllm_model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
550
+ "backbone.vllm_model.visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
551
+ "backbone.vllm_model.visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
552
+ "backbone.vllm_model.visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
553
+ "backbone.vllm_model.visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
554
+ "backbone.vllm_model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
555
+ "backbone.vllm_model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
556
+ "backbone.vllm_model.visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
557
+ "backbone.vllm_model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
558
+ "backbone.vllm_model.visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
559
+ "backbone.vllm_model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
560
+ "backbone.vllm_model.visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
561
+ "backbone.vllm_model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
562
+ "backbone.vllm_model.visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
563
+ "backbone.vllm_model.visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
564
+ "backbone.vllm_model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
565
+ "backbone.vllm_model.visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
566
+ "backbone.vllm_model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
567
+ "backbone.vllm_model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
568
+ "backbone.vllm_model.visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
569
+ "backbone.vllm_model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
570
+ "backbone.vllm_model.visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
571
+ "backbone.vllm_model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
572
+ "backbone.vllm_model.visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
573
+ "backbone.vllm_model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
574
+ "backbone.vllm_model.visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
575
+ "backbone.vllm_model.visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
576
+ "backbone.vllm_model.visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
577
+ "backbone.vllm_model.visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
578
+ "backbone.vllm_model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
579
+ "backbone.vllm_model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
580
+ "backbone.vllm_model.visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
581
+ "backbone.vllm_model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
582
+ "backbone.vllm_model.visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
583
+ "backbone.vllm_model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
584
+ "backbone.vllm_model.visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
585
+ "backbone.vllm_model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
586
+ "backbone.vllm_model.visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
587
+ "backbone.vllm_model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
588
+ "backbone.vllm_model.visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
589
+ "backbone.vllm_model.visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
590
+ "backbone.vllm_model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
591
+ "backbone.vllm_model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
592
+ "backbone.vllm_model.visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
593
+ "backbone.vllm_model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
594
+ "backbone.vllm_model.visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
595
+ "backbone.vllm_model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
596
+ "backbone.vllm_model.visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
597
+ "backbone.vllm_model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
598
+ "backbone.vllm_model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
599
+ "backbone.vllm_model.visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
600
+ "backbone.vllm_model.visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
601
+ "backbone.vllm_model.visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
602
+ "backbone.vllm_model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
603
+ "backbone.vllm_model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
604
+ "backbone.vllm_model.visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
605
+ "backbone.vllm_model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
606
+ "backbone.vllm_model.visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
607
+ "backbone.vllm_model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
608
+ "backbone.vllm_model.visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
609
+ "backbone.vllm_model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
610
+ "backbone.vllm_model.visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
611
+ "backbone.vllm_model.visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
612
+ "backbone.vllm_model.visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
613
+ "backbone.vllm_model.visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
614
+ "backbone.vllm_model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
615
+ "backbone.vllm_model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
616
+ "backbone.vllm_model.visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
617
+ "backbone.vllm_model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
618
+ "backbone.vllm_model.visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
619
+ "backbone.vllm_model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
620
+ "backbone.vllm_model.visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
621
+ "backbone.vllm_model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
622
+ "backbone.vllm_model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
623
+ "backbone.vllm_model.visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
624
+ "backbone.vllm_model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
625
+ "backbone.vllm_model.visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
626
+ "backbone.vllm_model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
627
+ "backbone.vllm_model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
628
+ "backbone.vllm_model.visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
629
+ "backbone.vllm_model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
630
+ "backbone.vllm_model.visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
631
+ "backbone.vllm_model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
632
+ "backbone.vllm_model.visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
633
+ "backbone.vllm_model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
634
+ "backbone.vllm_model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
635
+ "backbone.vllm_model.visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
636
+ "backbone.vllm_model.visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
637
+ "backbone.vllm_model.visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
638
+ "backbone.vllm_model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
639
+ "backbone.vllm_model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
640
+ "backbone.vllm_model.visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
641
+ "backbone.vllm_model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
642
+ "backbone.vllm_model.visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
643
+ "backbone.vllm_model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
644
+ "backbone.vllm_model.visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
645
+ "backbone.vllm_model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
646
+ "backbone.vllm_model.visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
647
+ "backbone.vllm_model.visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
648
+ "backbone.vllm_model.visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
649
+ "backbone.vllm_model.visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
650
+ "backbone.vllm_model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
651
+ "backbone.vllm_model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
652
+ "backbone.vllm_model.visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
653
+ "backbone.vllm_model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
654
+ "backbone.vllm_model.visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
655
+ "backbone.vllm_model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
656
+ "backbone.vllm_model.visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
657
+ "backbone.vllm_model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
658
+ "backbone.vllm_model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
659
+ "backbone.vllm_model.visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
660
+ "backbone.vllm_model.visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
661
+ "backbone.vllm_model.visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
662
+ "backbone.vllm_model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
663
+ "backbone.vllm_model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
664
+ "backbone.vllm_model.visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
665
+ "backbone.vllm_model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
666
+ "backbone.vllm_model.visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
667
+ "backbone.vllm_model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
668
+ "backbone.vllm_model.visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
669
+ "backbone.vllm_model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
670
+ "backbone.vllm_model.visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
671
+ "backbone.vllm_model.visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
672
+ "backbone.vllm_model.visual.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
673
+ "backbone.vllm_model.visual.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
674
+ "backbone.vllm_model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
675
+ "backbone.vllm_model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
676
+ "backbone.vllm_model.visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
677
+ "backbone.vllm_model.visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
678
+ "backbone.vllm_model.visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
679
+ "backbone.vllm_model.visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
680
+ "backbone.vllm_model.visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
681
+ "backbone.vllm_model.visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
682
+ "backbone.vllm_model.visual.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
683
+ "backbone.vllm_model.visual.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
684
+ "backbone.vllm_model.visual.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
685
+ "backbone.vllm_model.visual.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
686
+ "backbone.vllm_model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
687
+ "backbone.vllm_model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
688
+ "backbone.vllm_model.visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
689
+ "backbone.vllm_model.visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
690
+ "backbone.vllm_model.visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
691
+ "backbone.vllm_model.visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
692
+ "backbone.vllm_model.visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
693
+ "backbone.vllm_model.visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
694
+ "backbone.vllm_model.visual.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
695
+ "backbone.vllm_model.visual.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
696
+ "backbone.vllm_model.visual.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
697
+ "backbone.vllm_model.visual.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
698
+ "backbone.vllm_model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
699
+ "backbone.vllm_model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
700
+ "backbone.vllm_model.visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
701
+ "backbone.vllm_model.visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
702
+ "backbone.vllm_model.visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
703
+ "backbone.vllm_model.visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
704
+ "backbone.vllm_model.visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
705
+ "backbone.vllm_model.visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
706
+ "backbone.vllm_model.visual.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
707
+ "backbone.vllm_model.visual.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
708
+ "backbone.vllm_model.visual.blocks.27.attn.proj.bias": "model-00001-of-00003.safetensors",
709
+ "backbone.vllm_model.visual.blocks.27.attn.proj.weight": "model-00001-of-00003.safetensors",
710
+ "backbone.vllm_model.visual.blocks.27.attn.qkv.bias": "model-00001-of-00003.safetensors",
711
+ "backbone.vllm_model.visual.blocks.27.attn.qkv.weight": "model-00001-of-00003.safetensors",
712
+ "backbone.vllm_model.visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
713
+ "backbone.vllm_model.visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
714
+ "backbone.vllm_model.visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
715
+ "backbone.vllm_model.visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
716
+ "backbone.vllm_model.visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
717
+ "backbone.vllm_model.visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
718
+ "backbone.vllm_model.visual.blocks.27.norm1.weight": "model-00001-of-00003.safetensors",
719
+ "backbone.vllm_model.visual.blocks.27.norm2.weight": "model-00001-of-00003.safetensors",
720
+ "backbone.vllm_model.visual.blocks.28.attn.proj.bias": "model-00001-of-00003.safetensors",
721
+ "backbone.vllm_model.visual.blocks.28.attn.proj.weight": "model-00001-of-00003.safetensors",
722
+ "backbone.vllm_model.visual.blocks.28.attn.qkv.bias": "model-00001-of-00003.safetensors",
723
+ "backbone.vllm_model.visual.blocks.28.attn.qkv.weight": "model-00001-of-00003.safetensors",
724
+ "backbone.vllm_model.visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
725
+ "backbone.vllm_model.visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
726
+ "backbone.vllm_model.visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
727
+ "backbone.vllm_model.visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
728
+ "backbone.vllm_model.visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
729
+ "backbone.vllm_model.visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
730
+ "backbone.vllm_model.visual.blocks.28.norm1.weight": "model-00001-of-00003.safetensors",
731
+ "backbone.vllm_model.visual.blocks.28.norm2.weight": "model-00001-of-00003.safetensors",
732
+ "backbone.vllm_model.visual.blocks.29.attn.proj.bias": "model-00001-of-00003.safetensors",
733
+ "backbone.vllm_model.visual.blocks.29.attn.proj.weight": "model-00001-of-00003.safetensors",
734
+ "backbone.vllm_model.visual.blocks.29.attn.qkv.bias": "model-00001-of-00003.safetensors",
735
+ "backbone.vllm_model.visual.blocks.29.attn.qkv.weight": "model-00001-of-00003.safetensors",
736
+ "backbone.vllm_model.visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
737
+ "backbone.vllm_model.visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
738
+ "backbone.vllm_model.visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
739
+ "backbone.vllm_model.visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
740
+ "backbone.vllm_model.visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
741
+ "backbone.vllm_model.visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
742
+ "backbone.vllm_model.visual.blocks.29.norm1.weight": "model-00001-of-00003.safetensors",
743
+ "backbone.vllm_model.visual.blocks.29.norm2.weight": "model-00001-of-00003.safetensors",
744
+ "backbone.vllm_model.visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
745
+ "backbone.vllm_model.visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
746
+ "backbone.vllm_model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
747
+ "backbone.vllm_model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
748
+ "backbone.vllm_model.visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
749
+ "backbone.vllm_model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
750
+ "backbone.vllm_model.visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
751
+ "backbone.vllm_model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
752
+ "backbone.vllm_model.visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
753
+ "backbone.vllm_model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
754
+ "backbone.vllm_model.visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
755
+ "backbone.vllm_model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
756
+ "backbone.vllm_model.visual.blocks.30.attn.proj.bias": "model-00001-of-00003.safetensors",
757
+ "backbone.vllm_model.visual.blocks.30.attn.proj.weight": "model-00001-of-00003.safetensors",
758
+ "backbone.vllm_model.visual.blocks.30.attn.qkv.bias": "model-00001-of-00003.safetensors",
759
+ "backbone.vllm_model.visual.blocks.30.attn.qkv.weight": "model-00001-of-00003.safetensors",
760
+ "backbone.vllm_model.visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
761
+ "backbone.vllm_model.visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
762
+ "backbone.vllm_model.visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
763
+ "backbone.vllm_model.visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
764
+ "backbone.vllm_model.visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
765
+ "backbone.vllm_model.visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
766
+ "backbone.vllm_model.visual.blocks.30.norm1.weight": "model-00001-of-00003.safetensors",
767
+ "backbone.vllm_model.visual.blocks.30.norm2.weight": "model-00001-of-00003.safetensors",
768
+ "backbone.vllm_model.visual.blocks.31.attn.proj.bias": "model-00001-of-00003.safetensors",
769
+ "backbone.vllm_model.visual.blocks.31.attn.proj.weight": "model-00001-of-00003.safetensors",
770
+ "backbone.vllm_model.visual.blocks.31.attn.qkv.bias": "model-00001-of-00003.safetensors",
771
+ "backbone.vllm_model.visual.blocks.31.attn.qkv.weight": "model-00001-of-00003.safetensors",
772
+ "backbone.vllm_model.visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
773
+ "backbone.vllm_model.visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
774
+ "backbone.vllm_model.visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
775
+ "backbone.vllm_model.visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
776
+ "backbone.vllm_model.visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
777
+ "backbone.vllm_model.visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
778
+ "backbone.vllm_model.visual.blocks.31.norm1.weight": "model-00001-of-00003.safetensors",
779
+ "backbone.vllm_model.visual.blocks.31.norm2.weight": "model-00001-of-00003.safetensors",
780
+ "backbone.vllm_model.visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
781
+ "backbone.vllm_model.visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
782
+ "backbone.vllm_model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
783
+ "backbone.vllm_model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
784
+ "backbone.vllm_model.visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
785
+ "backbone.vllm_model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
786
+ "backbone.vllm_model.visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
787
+ "backbone.vllm_model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
788
+ "backbone.vllm_model.visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
789
+ "backbone.vllm_model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
790
+ "backbone.vllm_model.visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
791
+ "backbone.vllm_model.visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
792
+ "backbone.vllm_model.visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
793
+ "backbone.vllm_model.visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
794
+ "backbone.vllm_model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
795
+ "backbone.vllm_model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
796
+ "backbone.vllm_model.visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
797
+ "backbone.vllm_model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
798
+ "backbone.vllm_model.visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
799
+ "backbone.vllm_model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
800
+ "backbone.vllm_model.visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
801
+ "backbone.vllm_model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
802
+ "backbone.vllm_model.visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
803
+ "backbone.vllm_model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
804
+ "backbone.vllm_model.visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
805
+ "backbone.vllm_model.visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
806
+ "backbone.vllm_model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
807
+ "backbone.vllm_model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
808
+ "backbone.vllm_model.visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
809
+ "backbone.vllm_model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
810
+ "backbone.vllm_model.visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
811
+ "backbone.vllm_model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
812
+ "backbone.vllm_model.visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
813
+ "backbone.vllm_model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
814
+ "backbone.vllm_model.visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
815
+ "backbone.vllm_model.visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
816
+ "backbone.vllm_model.visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
817
+ "backbone.vllm_model.visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
818
+ "backbone.vllm_model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
819
+ "backbone.vllm_model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
820
+ "backbone.vllm_model.visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
821
+ "backbone.vllm_model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
822
+ "backbone.vllm_model.visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
823
+ "backbone.vllm_model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
824
+ "backbone.vllm_model.visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
825
+ "backbone.vllm_model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
826
+ "backbone.vllm_model.visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
827
+ "backbone.vllm_model.visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
828
+ "backbone.vllm_model.visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
829
+ "backbone.vllm_model.visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
830
+ "backbone.vllm_model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
831
+ "backbone.vllm_model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
832
+ "backbone.vllm_model.visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
833
+ "backbone.vllm_model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
834
+ "backbone.vllm_model.visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
835
+ "backbone.vllm_model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
836
+ "backbone.vllm_model.visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
837
+ "backbone.vllm_model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
838
+ "backbone.vllm_model.visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
839
+ "backbone.vllm_model.visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
840
+ "backbone.vllm_model.visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
841
+ "backbone.vllm_model.visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
842
+ "backbone.vllm_model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
843
+ "backbone.vllm_model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
844
+ "backbone.vllm_model.visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
845
+ "backbone.vllm_model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
846
+ "backbone.vllm_model.visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
847
+ "backbone.vllm_model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
848
+ "backbone.vllm_model.visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
849
+ "backbone.vllm_model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
850
+ "backbone.vllm_model.visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
851
+ "backbone.vllm_model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
852
+ "backbone.vllm_model.visual.merger.ln_q.weight": "model-00001-of-00003.safetensors",
853
+ "backbone.vllm_model.visual.merger.mlp.0.bias": "model-00001-of-00003.safetensors",
854
+ "backbone.vllm_model.visual.merger.mlp.0.weight": "model-00001-of-00003.safetensors",
855
+ "backbone.vllm_model.visual.merger.mlp.2.bias": "model-00001-of-00003.safetensors",
856
+ "backbone.vllm_model.visual.merger.mlp.2.weight": "model-00001-of-00003.safetensors",
857
+ "backbone.vllm_model.visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors"
858
+ }
859
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb324c9918e5140380eb58a9feb2e90a0a13576cbeeaea10583c0f37d0e3f480
3
+ size 5304