Hugging Face's logo

JsST
/
TinyMed

TensorBoard
Safetensors
Model card Files Metrics Community
1
JsST commited on
Commit
c7a25c3
·
1 Parent(s): 071df92

commit from songtaojiang

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -36
  2. MoE-Tinymed-phi2-llava/added_tokens.json +0 -41
  3. MoE-Tinymed-phi2-llava/config.json +0 -105
  4. MoE-Tinymed-phi2-llava/generation_config.json +0 -6
  5. MoE-Tinymed-phi2-llava/merges.txt +0 -0
  6. MoE-Tinymed-phi2-llava/model.safetensors.index.json +0 -0
  7. MoE-Tinymed-phi2-llava/special_tokens_map.json +0 -24
  8. MoE-Tinymed-phi2-llava/tokenizer_config.json +0 -335
  9. MoE-Tinymed-phi2-llava/trainer_state.json +0 -0
  10. MoE-Tinymed-phi2-llava/vocab.json +0 -0
  11. MoE-Tinymed-stablelm-llava/config.json +0 -92
  12. MoE-Tinymed-stablelm-llava/generation_config.json +0 -6
  13. MoE-Tinymed-stablelm-llava/merges.txt +0 -0
  14. MoE-Tinymed-stablelm-llava/model.safetensors.index.json +0 -862
  15. MoE-Tinymed-stablelm-llava/special_tokens_map.json +0 -53
  16. MoE-Tinymed-stablelm-llava/tokenizer_config.json +0 -314
  17. MoE-Tinymed-stablelm-llava/trainer_state.json +0 -0
  18. MoE-Tinymed-stablelm-llava/vocab.json +0 -0
  19. Stage2/llavaphi-2.7b-stage2/added_tokens.json +3 -0
  20. Stage2/llavaphi-2.7b-stage2/config.json +3 -0
  21. Stage2/llavaphi-2.7b-stage2/generation_config.json +3 -0
  22. Stage2/llavaphi-2.7b-stage2/merges.txt +3 -0
  23. {llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/model-00001-of-00002.safetensors +0 -0
  24. {llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/model-00002-of-00002.safetensors +0 -0
  25. Stage2/llavaphi-2.7b-stage2/model.safetensors.index.json +3 -0
  26. {llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/runs/Mar24_13-31-30_r750xa/events.out.tfevents.1711287125.r750xa +0 -0
  27. {llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/runs/Mar25_00-52-54_r750xa/events.out.tfevents.1711327986.r750xa +0 -0
  28. {llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/runs/Mar25_00-57-31_r750xa/events.out.tfevents.1711328286.r750xa +0 -0
  29. Stage2/llavaphi-2.7b-stage2/special_tokens_map.json +3 -0
  30. Stage2/llavaphi-2.7b-stage2/tokenizer_config.json +3 -0
  31. Stage2/llavaphi-2.7b-stage2/trainer_state.json +3 -0
  32. {llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/training_args.bin +0 -0
  33. Stage2/llavaphi-2.7b-stage2/vocab.json +3 -0
  34. Stage2/llavastablelm-1.6b-stage2/config.json +3 -0
  35. Stage2/llavastablelm-1.6b-stage2/generation_config.json +3 -0
  36. Stage2/llavastablelm-1.6b-stage2/merges.txt +3 -0
  37. {llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/model.safetensors +0 -0
  38. {llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/runs/Apr06_03-59-00_r750xa/events.out.tfevents.1712375971.r750xa +0 -0
  39. {llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/runs/Apr06_04-27-32_r750xa/events.out.tfevents.1712377675.r750xa +0 -0
  40. Stage2/llavastablelm-1.6b-stage2/special_tokens_map.json +3 -0
  41. Stage2/llavastablelm-1.6b-stage2/tokenizer_config.json +3 -0
  42. Stage2/llavastablelm-1.6b-stage2/trainer_state.json +3 -0
  43. {llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/training_args.bin +0 -0
  44. Stage2/llavastablelm-1.6b-stage2/vocab.json +3 -0
  45. Stage3/MoE-Tinymed-phi2-llava/added_tokens.json +3 -0
  46. Stage3/MoE-Tinymed-phi2-llava/config.json +3 -0
  47. Stage3/MoE-Tinymed-phi2-llava/generation_config.json +3 -0
  48. Stage3/MoE-Tinymed-phi2-llava/merges.txt +3 -0
  49. Stage3/MoE-Tinymed-phi2-llava/model-00001-of-00003.safetensors +3 -0
  50. Stage3/MoE-Tinymed-phi2-llava/model-00002-of-00003.safetensors +3 -0
.gitattributes CHANGED
@@ -1,36 +1,3 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
36
- train_all.json filter=lfs diff=lfs merge=lfs -text
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1f58fd32af1d9afe3c8d06ebe19deef3656ab96408bbdfb46cf45e8eeb0bc3
3
+ size 38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-phi2-llava/added_tokens.json DELETED
@@ -1,41 +0,0 @@
1
- {
2
- "\t\t": 50294,
3
- "\t\t\t": 50293,
4
- "\t\t\t\t": 50292,
5
- "\t\t\t\t\t": 50291,
6
- "\t\t\t\t\t\t": 50290,
7
- "\t\t\t\t\t\t\t": 50289,
8
- "\t\t\t\t\t\t\t\t": 50288,
9
- "\t\t\t\t\t\t\t\t\t": 50287,
10
- " ": 50286,
11
- " ": 50285,
12
- " ": 50284,
13
- " ": 50283,
14
- " ": 50282,
15
- " ": 50281,
16
- " ": 50280,
17
- " ": 50279,
18
- " ": 50278,
19
- " ": 50277,
20
- " ": 50276,
21
- " ": 50275,
22
- " ": 50274,
23
- " ": 50273,
24
- " ": 50272,
25
- " ": 50271,
26
- " ": 50270,
27
- " ": 50269,
28
- " ": 50268,
29
- " ": 50267,
30
- " ": 50266,
31
- " ": 50265,
32
- " ": 50264,
33
- " ": 50263,
34
- " ": 50262,
35
- " ": 50261,
36
- " ": 50260,
37
- " ": 50259,
38
- " ": 50258,
39
- " ": 50257,
40
- "<|extra_0|>": 50295
41
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-phi2-llava/config.json DELETED
@@ -1,105 +0,0 @@
1
- {
2
- "_name_or_path": "/home/songtaojiang/TinyLLaVABench/MoE-LLaVA/checkpoints/llavaphi-2.7b-finetune-3epoch",
3
- "architectures": [
4
- "MoELLaVAPhiForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "auto_map": {
8
- "AutoConfig": "configuration_phi.PhiConfig",
9
- "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
10
- },
11
- "bos_token_id": 50256,
12
- "embd_pdrop": 0.0,
13
- "eos_token_id": 50256,
14
- "freeze_mm_mlp_adapter": false,
15
- "hidden_act": "gelu_new",
16
- "hidden_size": 2560,
17
- "image_aspect_ratio": "pad",
18
- "image_projector_type": "mlp2x_gelu",
19
- "initializer_range": 0.02,
20
- "intermediate_size": 10240,
21
- "layer_norm_eps": 1e-05,
22
- "max_position_embeddings": 2048,
23
- "mm_hidden_size": 1024,
24
- "mm_image_tower": "/home/songtaojiang/MobileVLM/clip-vit-large-patch14-336",
25
- "mm_projector_lr": null,
26
- "mm_use_im_patch_token": false,
27
- "mm_use_im_start_end": false,
28
- "mm_video_tower": null,
29
- "mm_vision_select_feature": "patch",
30
- "mm_vision_select_layer": -2,
31
- "model_type": "moe_llava_phi",
32
- "moe": {
33
- "capacity_factor": 1.5,
34
- "ep_size": 1,
35
- "eval_capacity_factor": 2.0,
36
- "min_capacity": 0,
37
- "moe_enable": true,
38
- "moe_layers_idx": [
39
- 0,
40
- 2,
41
- 4,
42
- 6,
43
- 8,
44
- 10,
45
- 12,
46
- 14,
47
- 16,
48
- 18,
49
- 20,
50
- 22,
51
- 24,
52
- 26,
53
- 28,
54
- 30
55
- ],
56
- "moe_mode": "sparse",
57
- "num_experts": [
58
- 4,
59
- 4,
60
- 4,
61
- 4,
62
- 4,
63
- 4,
64
- 4,
65
- 4,
66
- 4,
67
- 4,
68
- 4,
69
- 4,
70
- 4,
71
- 4,
72
- 4,
73
- 4
74
- ],
75
- "router_aux_loss_coef": 0.01,
76
- "top_k_experts": 2,
77
- "train_modules": [
78
- "fc1",
79
- "fc2",
80
- "wg"
81
- ],
82
- "use_residual": false
83
- },
84
- "num_attention_heads": 32,
85
- "num_hidden_layers": 32,
86
- "num_key_value_heads": 32,
87
- "pad_token_id": 50295,
88
- "partial_rotary_factor": 0.4,
89
- "qk_layernorm": false,
90
- "resid_pdrop": 0.1,
91
- "rope_scaling": null,
92
- "rope_theta": 10000.0,
93
- "tie_word_embeddings": false,
94
- "tokenizer_padding_side": "right",
95
- "torch_dtype": "bfloat16",
96
- "transformers_version": "4.39.2",
97
- "tune_mm_mlp_adapter": false,
98
- "use_cache": true,
99
- "use_mm_proj": true,
100
- "video_global_proj": false,
101
- "video_projector_type": "linear",
102
- "video_spatial_proj": false,
103
- "video_temproal_proj": false,
104
- "vocab_size": 51200
105
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-phi2-llava/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.39.2"
6
- }
 
 
 
 
 
 
 
MoE-Tinymed-phi2-llava/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
MoE-Tinymed-phi2-llava/model.safetensors.index.json DELETED
The diff for this file is too large to render. See raw diff
 
MoE-Tinymed-phi2-llava/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|endoftext|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<|extra_0|>",
17
- "unk_token": {
18
- "content": "<|extra_0|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-phi2-llava/tokenizer_config.json DELETED
@@ -1,335 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "50256": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "50257": {
14
- "content": " ",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "50258": {
22
- "content": " ",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "50259": {
30
- "content": " ",
31
- "lstrip": false,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- },
37
- "50260": {
38
- "content": " ",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "50261": {
46
- "content": " ",
47
- "lstrip": false,
48
- "normalized": true,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "50262": {
54
- "content": " ",
55
- "lstrip": false,
56
- "normalized": true,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
- },
61
- "50263": {
62
- "content": " ",
63
- "lstrip": false,
64
- "normalized": true,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": false
68
- },
69
- "50264": {
70
- "content": " ",
71
- "lstrip": false,
72
- "normalized": true,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": false
76
- },
77
- "50265": {
78
- "content": " ",
79
- "lstrip": false,
80
- "normalized": true,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": false
84
- },
85
- "50266": {
86
- "content": " ",
87
- "lstrip": false,
88
- "normalized": true,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": false
92
- },
93
- "50267": {
94
- "content": " ",
95
- "lstrip": false,
96
- "normalized": true,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": false
100
- },
101
- "50268": {
102
- "content": " ",
103
- "lstrip": false,
104
- "normalized": true,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": false
108
- },
109
- "50269": {
110
- "content": " ",
111
- "lstrip": false,
112
- "normalized": true,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": false
116
- },
117
- "50270": {
118
- "content": " ",
119
- "lstrip": false,
120
- "normalized": true,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "50271": {
126
- "content": " ",
127
- "lstrip": false,
128
- "normalized": true,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "50272": {
134
- "content": " ",
135
- "lstrip": false,
136
- "normalized": true,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "50273": {
142
- "content": " ",
143
- "lstrip": false,
144
- "normalized": true,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "50274": {
150
- "content": " ",
151
- "lstrip": false,
152
- "normalized": true,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "50275": {
158
- "content": " ",
159
- "lstrip": false,
160
- "normalized": true,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "50276": {
166
- "content": " ",
167
- "lstrip": false,
168
- "normalized": true,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "50277": {
174
- "content": " ",
175
- "lstrip": false,
176
- "normalized": true,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "50278": {
182
- "content": " ",
183
- "lstrip": false,
184
- "normalized": true,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "50279": {
190
- "content": " ",
191
- "lstrip": false,
192
- "normalized": true,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "50280": {
198
- "content": " ",
199
- "lstrip": false,
200
- "normalized": true,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "50281": {
206
- "content": " ",
207
- "lstrip": false,
208
- "normalized": true,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- },
213
- "50282": {
214
- "content": " ",
215
- "lstrip": false,
216
- "normalized": true,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": false
220
- },
221
- "50283": {
222
- "content": " ",
223
- "lstrip": false,
224
- "normalized": true,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": false
228
- },
229
- "50284": {
230
- "content": " ",
231
- "lstrip": false,
232
- "normalized": true,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": false
236
- },
237
- "50285": {
238
- "content": " ",
239
- "lstrip": false,
240
- "normalized": true,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": false
244
- },
245
- "50286": {
246
- "content": " ",
247
- "lstrip": false,
248
- "normalized": true,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": false
252
- },
253
- "50287": {
254
- "content": "\t\t\t\t\t\t\t\t\t",
255
- "lstrip": false,
256
- "normalized": true,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": false
260
- },
261
- "50288": {
262
- "content": "\t\t\t\t\t\t\t\t",
263
- "lstrip": false,
264
- "normalized": true,
265
- "rstrip": false,
266
- "single_word": false,
267
- "special": false
268
- },
269
- "50289": {
270
- "content": "\t\t\t\t\t\t\t",
271
- "lstrip": false,
272
- "normalized": true,
273
- "rstrip": false,
274
- "single_word": false,
275
- "special": false
276
- },
277
- "50290": {
278
- "content": "\t\t\t\t\t\t",
279
- "lstrip": false,
280
- "normalized": true,
281
- "rstrip": false,
282
- "single_word": false,
283
- "special": false
284
- },
285
- "50291": {
286
- "content": "\t\t\t\t\t",
287
- "lstrip": false,
288
- "normalized": true,
289
- "rstrip": false,
290
- "single_word": false,
291
- "special": false
292
- },
293
- "50292": {
294
- "content": "\t\t\t\t",
295
- "lstrip": false,
296
- "normalized": true,
297
- "rstrip": false,
298
- "single_word": false,
299
- "special": false
300
- },
301
- "50293": {
302
- "content": "\t\t\t",
303
- "lstrip": false,
304
- "normalized": true,
305
- "rstrip": false,
306
- "single_word": false,
307
- "special": false
308
- },
309
- "50294": {
310
- "content": "\t\t",
311
- "lstrip": false,
312
- "normalized": true,
313
- "rstrip": false,
314
- "single_word": false,
315
- "special": false
316
- },
317
- "50295": {
318
- "content": "<|extra_0|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": false,
322
- "single_word": false,
323
- "special": true
324
- }
325
- },
326
- "bos_token": "<|endoftext|>",
327
- "clean_up_tokenization_spaces": true,
328
- "eos_token": "<|endoftext|>",
329
- "errors": "replace",
330
- "model_max_length": 2048,
331
- "pad_token": "<|extra_0|>",
332
- "padding_side": "right",
333
- "tokenizer_class": "CodeGenTokenizer",
334
- "unk_token": "<|extra_0|>"
335
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-phi2-llava/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
MoE-Tinymed-phi2-llava/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
MoE-Tinymed-stablelm-llava/config.json DELETED
@@ -1,92 +0,0 @@
1
- {
2
- "_name_or_path": "./checkpoints-clip336/llavastablelm-1.6b-finetune",
3
- "architectures": [
4
- "MoELLaVAStablelmForCausalLM"
5
- ],
6
- "bos_token_id": 100257,
7
- "eos_token_id": 100257,
8
- "freeze_mm_mlp_adapter": false,
9
- "hidden_act": "silu",
10
- "hidden_size": 2048,
11
- "image_aspect_ratio": "pad",
12
- "image_projector_type": "mlp2x_gelu",
13
- "initializer_range": 0.02,
14
- "intermediate_size": 5632,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 4096,
17
- "mm_hidden_size": 1024,
18
- "mm_image_tower": "/home/songtaojiang/MobileVLM/clip-vit-large-patch14-336",
19
- "mm_projector_lr": null,
20
- "mm_use_im_patch_token": false,
21
- "mm_use_im_start_end": false,
22
- "mm_video_tower": null,
23
- "mm_vision_select_feature": "patch",
24
- "mm_vision_select_layer": -2,
25
- "model_type": "moe_llava_stablelm",
26
- "moe": {
27
- "capacity_factor": 1.5,
28
- "ep_size": 1,
29
- "eval_capacity_factor": 2.0,
30
- "min_capacity": 0,
31
- "moe_enable": true,
32
- "moe_layers_idx": [
33
- 0,
34
- 2,
35
- 4,
36
- 6,
37
- 8,
38
- 10,
39
- 12,
40
- 14,
41
- 16,
42
- 18,
43
- 20,
44
- 22
45
- ],
46
- "moe_mode": "sparse",
47
- "num_experts": [
48
- 4,
49
- 4,
50
- 4,
51
- 4,
52
- 4,
53
- 4,
54
- 4,
55
- 4,
56
- 4,
57
- 4,
58
- 4,
59
- 4
60
- ],
61
- "router_aux_loss_coef": 0.01,
62
- "top_k_experts": 2,
63
- "train_modules": [
64
- "gate_proj",
65
- "up_proj",
66
- "down_proj",
67
- "wg"
68
- ],
69
- "use_residual": false
70
- },
71
- "norm_eps": 1e-05,
72
- "num_attention_heads": 32,
73
- "num_hidden_layers": 24,
74
- "num_key_value_heads": 32,
75
- "pad_token_id": 100280,
76
- "partial_rotary_factor": 0.25,
77
- "rope_pct": 0.25,
78
- "rope_theta": 10000,
79
- "tie_word_embeddings": false,
80
- "tokenizer_padding_side": "right",
81
- "torch_dtype": "bfloat16",
82
- "transformers_version": "4.39.2",
83
- "tune_mm_mlp_adapter": false,
84
- "use_cache": true,
85
- "use_mm_proj": true,
86
- "use_qkv_bias": true,
87
- "video_global_proj": false,
88
- "video_projector_type": "linear",
89
- "video_spatial_proj": false,
90
- "video_temproal_proj": false,
91
- "vocab_size": 100352
92
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-stablelm-llava/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 100257,
4
- "eos_token_id": 100257,
5
- "transformers_version": "4.39.2"
6
- }
 
 
 
 
 
 
 
MoE-Tinymed-stablelm-llava/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
MoE-Tinymed-stablelm-llava/model.safetensors.index.json DELETED
@@ -1,862 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 6400249856
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00002-of-00002.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.image_tower.image_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
9
- "model.image_tower.image_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
10
- "model.image_tower.image_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
11
- "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
12
- "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
13
- "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
14
- "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
15
- "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
16
- "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
17
- "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
18
- "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
19
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
20
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
21
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
22
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
23
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
24
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
25
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
26
- "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
27
- "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
28
- "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
29
- "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
30
- "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
31
- "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
32
- "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
33
- "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
34
- "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
35
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
36
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
37
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
38
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
39
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
40
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
41
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
42
- "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
43
- "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
44
- "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
45
- "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
46
- "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
47
- "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
48
- "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
49
- "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
50
- "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
51
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
52
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
53
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
54
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
55
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
56
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
57
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
58
- "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
59
- "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
60
- "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
61
- "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
62
- "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
63
- "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
64
- "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
65
- "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
66
- "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
67
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
68
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
69
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
70
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
71
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
72
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
73
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
74
- "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
75
- "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
76
- "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
77
- "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
78
- "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
79
- "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
80
- "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
81
- "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
82
- "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
83
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
84
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
85
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
86
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
87
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
88
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
89
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
90
- "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
91
- "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
92
- "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
93
- "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
94
- "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
95
- "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
96
- "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
97
- "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
98
- "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
99
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
100
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
101
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
102
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
103
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
104
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
105
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
106
- "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
107
- "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
108
- "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
109
- "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
110
- "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
111
- "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
112
- "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
113
- "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
114
- "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
115
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
116
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
117
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
118
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
119
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
120
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
121
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
122
- "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
123
- "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
124
- "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
125
- "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
126
- "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
127
- "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
128
- "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
129
- "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
130
- "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
131
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
132
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
133
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
134
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
135
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
136
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
138
- "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
139
- "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
140
- "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
141
- "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
142
- "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
143
- "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
144
- "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
145
- "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
146
- "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
147
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
148
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
150
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
151
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
152
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
153
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
154
- "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
155
- "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
156
- "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
157
- "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
158
- "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
159
- "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
160
- "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
161
- "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
162
- "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
163
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
164
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
165
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
166
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
167
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
168
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
170
- "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
171
- "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
172
- "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
173
- "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
174
- "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
175
- "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
176
- "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
177
- "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
178
- "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
179
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
180
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
181
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
182
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
183
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
184
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
185
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
186
- "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
188
- "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
189
- "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
190
- "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
191
- "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
192
- "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
193
- "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
194
- "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
195
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
196
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
197
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
198
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
199
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
200
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
201
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
202
- "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
203
- "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
204
- "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
205
- "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
206
- "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
207
- "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
208
- "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
209
- "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
210
- "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
211
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
212
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
214
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
215
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
216
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
217
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
218
- "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
219
- "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
220
- "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
221
- "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
222
- "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
223
- "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
224
- "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
225
- "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
226
- "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
227
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
228
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
229
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
230
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
231
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
232
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
234
- "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
235
- "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
236
- "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
237
- "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
238
- "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
239
- "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
240
- "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
241
- "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
242
- "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
243
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
244
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
245
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
246
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
247
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
248
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
250
- "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
251
- "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
252
- "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
253
- "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
254
- "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
255
- "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
256
- "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
257
- "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
258
- "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
259
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
260
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
261
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
262
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
263
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
264
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
265
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
266
- "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
267
- "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
268
- "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
269
- "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
270
- "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
271
- "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
272
- "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
273
- "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
274
- "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
275
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
276
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
277
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
278
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
279
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
280
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
281
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
282
- "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
- "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
284
- "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
285
- "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
286
- "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
287
- "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
288
- "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
289
- "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
290
- "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
291
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
292
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
293
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
294
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
295
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
296
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
297
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
298
- "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
299
- "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
300
- "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
301
- "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
302
- "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
303
- "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
304
- "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
305
- "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
306
- "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
307
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
308
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
309
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
310
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
311
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
312
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
313
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
314
- "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
315
- "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
316
- "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
317
- "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
318
- "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
319
- "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
320
- "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
321
- "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
322
- "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
323
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
324
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
325
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
326
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
327
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
328
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
329
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
330
- "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
331
- "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
332
- "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
333
- "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
334
- "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
335
- "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
336
- "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
337
- "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
338
- "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
339
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
340
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
341
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
342
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
343
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
344
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
345
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
346
- "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
347
- "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
348
- "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
349
- "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
350
- "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
351
- "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
352
- "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
353
- "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
354
- "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
355
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
356
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
357
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
358
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
359
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
360
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
361
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
362
- "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
363
- "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
364
- "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
365
- "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
366
- "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
367
- "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
368
- "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
369
- "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
370
- "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
371
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
372
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
373
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
374
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
375
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
376
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
377
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
378
- "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
379
- "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
380
- "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
381
- "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
382
- "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
383
- "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
384
- "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
385
- "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
386
- "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
387
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
388
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
389
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
390
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
391
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
392
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
393
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
394
- "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
395
- "model.image_tower.image_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
396
- "model.image_tower.image_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
397
- "model.image_tower.image_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
398
- "model.image_tower.image_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors",
399
- "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
400
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
401
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
402
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
403
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
404
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
405
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
406
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
407
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
408
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
409
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
410
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
411
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
412
- "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
413
- "model.layers.0.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
414
- "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
415
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
416
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
417
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
418
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
419
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
420
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
421
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
422
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
423
- "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
424
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
426
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
427
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
428
- "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
429
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
430
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
431
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
432
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
433
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
434
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
435
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
436
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
437
- "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
438
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
439
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
440
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
441
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
442
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
443
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
444
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
445
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
446
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
447
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
448
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
449
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
450
- "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
451
- "model.layers.10.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
452
- "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
453
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
454
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
455
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
456
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
457
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
458
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
459
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
460
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
- "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
462
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
463
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
464
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
465
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
466
- "model.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
467
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
468
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
469
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
470
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
471
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
472
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
473
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
474
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
475
- "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
476
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
477
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
478
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
479
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
480
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
481
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
482
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
483
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
484
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
485
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
486
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
487
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
488
- "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
489
- "model.layers.12.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
490
- "model.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
491
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
492
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
493
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
494
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
495
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
496
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
497
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
498
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
499
- "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
500
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
501
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
502
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
503
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
504
- "model.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
505
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
506
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
507
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
508
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
509
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
510
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
511
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
512
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
513
- "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
514
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
515
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
516
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
517
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
518
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
519
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
520
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
521
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
522
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
523
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
524
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
525
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
526
- "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
527
- "model.layers.14.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
528
- "model.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
529
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
530
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
531
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
532
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
533
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
534
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
535
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
536
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
537
- "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
538
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
539
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
540
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
541
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
542
- "model.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
543
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
544
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
545
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
546
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
547
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
548
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
549
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
550
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
551
- "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
552
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
553
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
554
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
555
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
556
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
557
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
558
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
559
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
560
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
561
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
562
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
563
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
564
- "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
565
- "model.layers.16.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
566
- "model.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
567
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
568
- "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
569
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
570
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
571
- "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
572
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
573
- "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
574
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
575
- "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
576
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
577
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
578
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
579
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
580
- "model.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
581
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
582
- "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
583
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
584
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
585
- "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
586
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
587
- "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
588
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
589
- "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
590
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
591
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
592
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
593
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
594
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
595
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
596
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
597
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
598
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
599
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
600
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
601
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
602
- "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
603
- "model.layers.18.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
604
- "model.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
605
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
606
- "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
607
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
608
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
609
- "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
610
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
611
- "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
612
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
613
- "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
614
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
615
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
616
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
617
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
618
- "model.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
619
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
620
- "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
621
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
622
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
623
- "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
624
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
625
- "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
626
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
627
- "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
628
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
629
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
630
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
631
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
632
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
633
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
634
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
635
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
636
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
637
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
638
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
639
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
640
- "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
641
- "model.layers.2.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
642
- "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
643
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
644
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
645
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
646
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
647
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
648
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
649
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
650
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
651
- "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
652
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
653
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
654
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
655
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
656
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
657
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
658
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
659
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
660
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
661
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
662
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
663
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
664
- "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
665
- "model.layers.20.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
666
- "model.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
667
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
668
- "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
669
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
670
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
671
- "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
672
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
673
- "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
674
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
675
- "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
676
- "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
677
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
678
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
679
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
680
- "model.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
681
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
682
- "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
683
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
684
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
685
- "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
686
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
687
- "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
688
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
689
- "model.layers.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
690
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
691
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00002-of-00002.safetensors",
692
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00002-of-00002.safetensors",
693
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00002-of-00002.safetensors",
694
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00002-of-00002.safetensors",
695
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00002-of-00002.safetensors",
696
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00002-of-00002.safetensors",
697
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00002-of-00002.safetensors",
698
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00002-of-00002.safetensors",
699
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00002-of-00002.safetensors",
700
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00002-of-00002.safetensors",
701
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00002-of-00002.safetensors",
702
- "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00002-of-00002.safetensors",
703
- "model.layers.22.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
704
- "model.layers.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
705
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
706
- "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
707
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
708
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
709
- "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
710
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
711
- "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
712
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
713
- "model.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
714
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
715
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
716
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
717
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
718
- "model.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
719
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
720
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
721
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
722
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
723
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
724
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
725
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
726
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
727
- "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
728
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
729
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
730
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
731
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
732
- "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
733
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
734
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
735
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
736
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
737
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
738
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
739
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
740
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
741
- "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
742
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
743
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
744
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
745
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
746
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
747
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
748
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
749
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
750
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
751
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
752
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
753
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
754
- "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
755
- "model.layers.4.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
756
- "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
757
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
758
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
759
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
760
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
761
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
762
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
763
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
764
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
765
- "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
766
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
767
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
768
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
769
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
770
- "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
771
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
772
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
773
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
774
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
775
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
776
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
777
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
778
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
779
- "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
780
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
781
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
782
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
783
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
784
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
785
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
786
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
787
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
788
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
789
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
790
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
791
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
792
- "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
793
- "model.layers.6.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
794
- "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
795
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
796
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
797
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
798
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
799
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
800
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
801
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
802
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
803
- "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
804
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
805
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
806
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
807
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
808
- "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
809
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
810
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
811
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
812
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
813
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
814
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
815
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
816
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
817
- "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
818
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
819
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
820
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
821
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
822
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
823
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
824
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
825
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
826
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
827
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
828
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
829
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
830
- "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
831
- "model.layers.8.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
832
- "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
833
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
834
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
835
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
836
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
837
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
838
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
839
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
840
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
841
- "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
842
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
843
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
844
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
845
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
846
- "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
847
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
848
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
849
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
850
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
851
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
852
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
853
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
854
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
855
- "model.mm_projector.image_spatial_proj.0.bias": "model-00002-of-00002.safetensors",
856
- "model.mm_projector.image_spatial_proj.0.weight": "model-00002-of-00002.safetensors",
857
- "model.mm_projector.image_spatial_proj.2.bias": "model-00002-of-00002.safetensors",
858
- "model.mm_projector.image_spatial_proj.2.weight": "model-00002-of-00002.safetensors",
859
- "model.norm.bias": "model-00002-of-00002.safetensors",
860
- "model.norm.weight": "model-00002-of-00002.safetensors"
861
- }
862
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-stablelm-llava/special_tokens_map.json DELETED
@@ -1,53 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|reg_extra|>",
4
- "<|endoftext|>",
5
- "<|fim_prefix|>",
6
- "<|fim_middle|>",
7
- "<|fim_suffix|>",
8
- "<|fim_pad|>",
9
- "<gh_stars>",
10
- "<filename>",
11
- "<issue_start>",
12
- "<issue_comment>",
13
- "<issue_closed>",
14
- "<jupyter_start>",
15
- "<jupyter_text>",
16
- "<jupyter_code>",
17
- "<jupyter_output>",
18
- "<empty_output>",
19
- "<commit_before>",
20
- "<commit_msg>",
21
- "<commit_after>",
22
- "<reponame>",
23
- "<|endofprompt|>",
24
- "<|im_start|>",
25
- "<|im_end|>",
26
- "<|pause|>",
27
- "<|reg0|>",
28
- "<|reg1|>",
29
- "<|reg2|>",
30
- "<|reg3|>",
31
- "<|reg4|>",
32
- "<|reg5|>",
33
- "<|reg6|>",
34
- "<|reg7|>",
35
- "<|extra0|>"
36
- ],
37
- "bos_token": {
38
- "content": "<|endoftext|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "eos_token": {
45
- "content": "<|endoftext|>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false
50
- },
51
- "pad_token": "<|reg0|>",
52
- "unk_token": "<|reg0|>"
53
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-stablelm-llava/tokenizer_config.json DELETED
@@ -1,314 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "100256": {
6
- "content": "<|reg_extra|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "100257": {
14
- "content": "<|endoftext|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "100258": {
22
- "content": "<|fim_prefix|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "100259": {
30
- "content": "<|fim_middle|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "100260": {
38
- "content": "<|fim_suffix|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "100261": {
46
- "content": "<|fim_pad|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "100262": {
54
- "content": "<gh_stars>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "100263": {
62
- "content": "<filename>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "100264": {
70
- "content": "<issue_start>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "100265": {
78
- "content": "<issue_comment>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "100266": {
86
- "content": "<issue_closed>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "100267": {
94
- "content": "<jupyter_start>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "100268": {
102
- "content": "<jupyter_text>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "100269": {
110
- "content": "<jupyter_code>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "100270": {
118
- "content": "<jupyter_output>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "100271": {
126
- "content": "<empty_output>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "100272": {
134
- "content": "<commit_before>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "100273": {
142
- "content": "<commit_msg>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "100274": {
150
- "content": "<commit_after>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "100275": {
158
- "content": "<reponame>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "100276": {
166
- "content": "<|endofprompt|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "100277": {
174
- "content": "<|im_start|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "100278": {
182
- "content": "<|im_end|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "100279": {
190
- "content": "<|pause|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "100280": {
198
- "content": "<|reg0|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "100281": {
206
- "content": "<|reg1|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "100282": {
214
- "content": "<|reg2|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "100283": {
222
- "content": "<|reg3|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "100284": {
230
- "content": "<|reg4|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "100285": {
238
- "content": "<|reg5|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "100286": {
246
- "content": "<|reg6|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "100287": {
254
- "content": "<|reg7|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "100288": {
262
- "content": "<|extra0|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": false,
266
- "single_word": false,
267
- "special": true
268
- }
269
- },
270
- "additional_special_tokens": [
271
- "<|reg_extra|>",
272
- "<|endoftext|>",
273
- "<|fim_prefix|>",
274
- "<|fim_middle|>",
275
- "<|fim_suffix|>",
276
- "<|fim_pad|>",
277
- "<gh_stars>",
278
- "<filename>",
279
- "<issue_start>",
280
- "<issue_comment>",
281
- "<issue_closed>",
282
- "<jupyter_start>",
283
- "<jupyter_text>",
284
- "<jupyter_code>",
285
- "<jupyter_output>",
286
- "<empty_output>",
287
- "<commit_before>",
288
- "<commit_msg>",
289
- "<commit_after>",
290
- "<reponame>",
291
- "<|endofprompt|>",
292
- "<|im_start|>",
293
- "<|im_end|>",
294
- "<|pause|>",
295
- "<|reg0|>",
296
- "<|reg1|>",
297
- "<|reg2|>",
298
- "<|reg3|>",
299
- "<|reg4|>",
300
- "<|reg5|>",
301
- "<|reg6|>",
302
- "<|reg7|>",
303
- "<|extra0|>"
304
- ],
305
- "bos_token": "<|endoftext|>",
306
- "clean_up_tokenization_spaces": true,
307
- "eos_token": "<|endoftext|>",
308
- "errors": "replace",
309
- "model_max_length": 2048,
310
- "pad_token": "<|reg0|>",
311
- "padding_side": "right",
312
- "tokenizer_class": "GPT2Tokenizer",
313
- "unk_token": "<|reg0|>"
314
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
MoE-Tinymed-stablelm-llava/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
MoE-Tinymed-stablelm-llava/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
Stage2/llavaphi-2.7b-stage2/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23987c8c7c6c238f9c409d1c6b85a90bfd8c6c5ea9452fc0abef05901419980b
3
+ size 1104
Stage2/llavaphi-2.7b-stage2/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056bce3847ecaafba069aa558f004807f414f006b0766153cce644071176173c
3
+ size 1510
Stage2/llavaphi-2.7b-stage2/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87e5c0aa1c5bcf6375d529e11b7fa009caac13dbf9cd07e2747f77898e1d133
3
+ size 119
Stage2/llavaphi-2.7b-stage2/merges.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5
3
+ size 456318
{llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/model-00001-of-00002.safetensors RENAMED
File without changes
{llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/model-00002-of-00002.safetensors RENAMED
File without changes
Stage2/llavaphi-2.7b-stage2/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165de7814166d33e127f2c66655c42d7a0739df73d6e4ea738f04b94120b9533
3
+ size 84156
{llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/runs/Mar24_13-31-30_r750xa/events.out.tfevents.1711287125.r750xa RENAMED
File without changes
{llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/runs/Mar25_00-52-54_r750xa/events.out.tfevents.1711327986.r750xa RENAMED
File without changes
{llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/runs/Mar25_00-57-31_r750xa/events.out.tfevents.1711328286.r750xa RENAMED
File without changes
Stage2/llavaphi-2.7b-stage2/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c2862310a80b7156f180bd20b6467f4fbadc48a1ff65e0bcae550dfd07b6bb
3
+ size 469
Stage2/llavaphi-2.7b-stage2/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d5e07f74d009b29737abb304e98f5cf3303b3a7f1708e59d7f9545b81ce6c7
3
+ size 7620
Stage2/llavaphi-2.7b-stage2/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc89d66b888090654fbfe675027e4a34258d1e51b4ebfa8ca74b12e68cfe075
3
+ size 381536
{llavaphi-2.7b-finetune-3epoch → Stage2/llavaphi-2.7b-stage2}/training_args.bin RENAMED
File without changes
Stage2/llavaphi-2.7b-stage2/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6bd25a65e4e63ca31360e9fb11c7e4f9a391a78385d640acd814092dd6eee4f
3
+ size 999186
Stage2/llavastablelm-1.6b-stage2/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419fc9d7712ef0d1d1be14a1903e8eb961761fbfbcbddbf6acbed0deb0c5c209
3
+ size 1361
Stage2/llavastablelm-1.6b-stage2/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5348be82bce91d4f28cd96f1538335557aea35555c75deccac01e33cf7e26a
3
+ size 121
Stage2/llavastablelm-1.6b-stage2/merges.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7d2e9050603bd1565dd31b2d9e4cc5a7bc3b1fb6bd3304eca2225ec9ba6cd6
3
+ size 916634
{llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/model.safetensors RENAMED
File without changes
{llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/runs/Apr06_03-59-00_r750xa/events.out.tfevents.1712375971.r750xa RENAMED
File without changes
{llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/runs/Apr06_04-27-32_r750xa/events.out.tfevents.1712377675.r750xa RENAMED
File without changes
Stage2/llavastablelm-1.6b-stage2/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97831710d343d5eab78298e44ab90348994c537c63a7f2e4c1e67aa103e0a726
3
+ size 1035
Stage2/llavastablelm-1.6b-stage2/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6f32c956df20115f552a585893cb442f29be2e82ca776d285e00fb70ce5fa6
3
+ size 6946
Stage2/llavastablelm-1.6b-stage2/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc574d115cc1b91261183fc47fd0f2ffdcabcaef75380cfbb001b173dd0007ff
3
+ size 381482
{llavastablelm-1.6b-finetune → Stage2/llavastablelm-1.6b-stage2}/training_args.bin RENAMED
File without changes
Stage2/llavastablelm-1.6b-stage2/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f676e1596f8af5f6e33d35adacd6d5546b0135670c2cd87bcb569ba67074c23e
3
+ size 2012402
Stage3/MoE-Tinymed-phi2-llava/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23987c8c7c6c238f9c409d1c6b85a90bfd8c6c5ea9452fc0abef05901419980b
3
+ size 1104
Stage3/MoE-Tinymed-phi2-llava/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:358666ea964f3aa5547ca7cd14bb4b2b7fa9fa92722b10845db0f4aa54250366
3
+ size 2273
Stage3/MoE-Tinymed-phi2-llava/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fccd09f0ca8b9ad0fdeb32d89c933c2b7f8865d69550beedfa4c6dc79affac
3
+ size 119
Stage3/MoE-Tinymed-phi2-llava/merges.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5
3
+ size 456318
Stage3/MoE-Tinymed-phi2-llava/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b41e80e64d1fb022cad9a46dc03c1ff7afad854e81c57586f57ca8fc75373c
3
+ size 4982356792
Stage3/MoE-Tinymed-phi2-llava/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89003c821b2680a6cb7f09b77f7c122154077d01377729b79bfd22244269be17
3
+ size 4982435992