Hugging Face's logo

memmelma
/
vila_3b_oxe_sim_jack_o

Safetensors
llava_llama
Model card Files
xet
Community
memmelma commited on
Commit
d0f7c05
·
verified ·
1 Parent(s): e0b84a1

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-8700/config.json +253 -0
  2. checkpoint-8700/global_step8700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  3. checkpoint-8700/global_step8700/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
  4. checkpoint-8700/global_step8700/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
  5. checkpoint-8700/global_step8700/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
  6. checkpoint-8700/global_step8700/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
  7. checkpoint-8700/global_step8700/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
  8. checkpoint-8700/global_step8700/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
  9. checkpoint-8700/global_step8700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  10. checkpoint-8700/global_step8700/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  11. checkpoint-8700/global_step8700/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  12. checkpoint-8700/global_step8700/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  13. checkpoint-8700/global_step8700/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  14. checkpoint-8700/global_step8700/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  15. checkpoint-8700/global_step8700/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  16. checkpoint-8700/global_step8700/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
  17. checkpoint-8700/global_step8700/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
  18. checkpoint-8700/global_step8700/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  19. checkpoint-8700/global_step8700/zero_pp_rank_10_mp_rank_00_model_states.pt +3 -0
  20. checkpoint-8700/global_step8700/zero_pp_rank_11_mp_rank_00_model_states.pt +3 -0
  21. checkpoint-8700/global_step8700/zero_pp_rank_12_mp_rank_00_model_states.pt +3 -0
  22. checkpoint-8700/global_step8700/zero_pp_rank_13_mp_rank_00_model_states.pt +3 -0
  23. checkpoint-8700/global_step8700/zero_pp_rank_14_mp_rank_00_model_states.pt +3 -0
  24. checkpoint-8700/global_step8700/zero_pp_rank_15_mp_rank_00_model_states.pt +3 -0
  25. checkpoint-8700/global_step8700/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  26. checkpoint-8700/global_step8700/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  27. checkpoint-8700/global_step8700/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  28. checkpoint-8700/global_step8700/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  29. checkpoint-8700/global_step8700/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  30. checkpoint-8700/global_step8700/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  31. checkpoint-8700/global_step8700/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  32. checkpoint-8700/global_step8700/zero_pp_rank_8_mp_rank_00_model_states.pt +3 -0
  33. checkpoint-8700/global_step8700/zero_pp_rank_9_mp_rank_00_model_states.pt +3 -0
  34. checkpoint-8700/latest +1 -0
  35. checkpoint-8700/llm/config.json +32 -0
  36. checkpoint-8700/llm/generation_config.json +7 -0
  37. checkpoint-8700/llm/model-00001-of-00002.safetensors +3 -0
  38. checkpoint-8700/llm/model-00002-of-00002.safetensors +3 -0
  39. checkpoint-8700/llm/model.safetensors.index.json +298 -0
  40. checkpoint-8700/llm/special_tokens_map.json +24 -0
  41. checkpoint-8700/llm/tokenizer.model +3 -0
  42. checkpoint-8700/llm/tokenizer_config.json +43 -0
  43. checkpoint-8700/mm_projector/config.json +10 -0
  44. checkpoint-8700/mm_projector/model.safetensors +3 -0
  45. checkpoint-8700/rng_state_0.pth +3 -0
  46. checkpoint-8700/rng_state_1.pth +3 -0
  47. checkpoint-8700/rng_state_10.pth +3 -0
  48. checkpoint-8700/rng_state_11.pth +3 -0
  49. checkpoint-8700/rng_state_12.pth +3 -0
  50. checkpoint-8700/rng_state_13.pth +3 -0
checkpoint-8700/config.json ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila/vila_3b_oxe_sim_jack_o/tmp-checkpoint-8700",
3
+ "architectures": [
4
+ "LlavaLlamaModel"
5
+ ],
6
+ "drop_path_rate": 0.0,
7
+ "hidden_size": 2560,
8
+ "image_aspect_ratio": "resize",
9
+ "interpolate_mode": "linear",
10
+ "llm_cfg": {
11
+ "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila/vila_3b_oxe_sim_jack_o/tmp-checkpoint-8700/llm",
12
+ "add_cross_attention": false,
13
+ "architectures": [
14
+ "LlamaForCausalLM"
15
+ ],
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": 1,
21
+ "chunk_size_feed_forward": 0,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 2,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 2560,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 6912,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 4096,
50
+ "min_length": 0,
51
+ "model_max_length": 4096,
52
+ "model_type": "llama",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 20,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 32,
58
+ "num_key_value_heads": 20,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": 0,
64
+ "prefix": null,
65
+ "pretraining_tp": 1,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "rms_norm_eps": 1e-05,
73
+ "rope_scaling": null,
74
+ "rope_theta": 10000.0,
75
+ "sep_token_id": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": false,
82
+ "tokenizer_class": null,
83
+ "tokenizer_model_max_length": 4096,
84
+ "tokenizer_padding_side": "right",
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": "bfloat16",
88
+ "torchscript": false,
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false,
91
+ "use_cache": false,
92
+ "vocab_size": 32000
93
+ },
94
+ "mm_hidden_size": 1152,
95
+ "mm_projector_cfg": {
96
+ "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila/vila_3b_oxe_sim_jack_o/tmp-checkpoint-8700/mm_projector",
97
+ "add_cross_attention": false,
98
+ "architectures": [
99
+ "MultimodalProjector"
100
+ ],
101
+ "bad_words_ids": null,
102
+ "begin_suppress_tokens": null,
103
+ "bos_token_id": null,
104
+ "chunk_size_feed_forward": 0,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "length_penalty": 1.0,
127
+ "max_length": 20,
128
+ "min_length": 0,
129
+ "mm_projector_type": "mlp_downsample",
130
+ "model_type": "v2l_projector",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_beam_groups": 1,
133
+ "num_beams": 1,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": null,
139
+ "prefix": null,
140
+ "problem_type": null,
141
+ "pruned_heads": {},
142
+ "remove_invalid_values": false,
143
+ "repetition_penalty": 1.0,
144
+ "return_dict": true,
145
+ "return_dict_in_generate": false,
146
+ "sep_token_id": null,
147
+ "suppress_tokens": null,
148
+ "task_specific_params": null,
149
+ "temperature": 1.0,
150
+ "tf_legacy_loss": false,
151
+ "tie_encoder_decoder": false,
152
+ "tie_word_embeddings": true,
153
+ "tokenizer_class": null,
154
+ "top_k": 50,
155
+ "top_p": 1.0,
156
+ "torch_dtype": "bfloat16",
157
+ "torchscript": false,
158
+ "typical_p": 1.0,
159
+ "use_bfloat16": false
160
+ },
161
+ "mm_projector_lr": null,
162
+ "mm_use_im_patch_token": false,
163
+ "mm_use_im_start_end": false,
164
+ "mm_vision_select_feature": "cls_patch",
165
+ "mm_vision_select_layer": -2,
166
+ "model_dtype": "torch.bfloat16",
167
+ "model_type": "llava_llama",
168
+ "num_video_frames": 8,
169
+ "resume_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila/vila_3b_oxe_sim_jack_o/checkpoint-7000",
170
+ "s2": false,
171
+ "s2_max_split_size": 336,
172
+ "s2_scales": "336,672,1008",
173
+ "transformers_version": "4.36.2",
174
+ "tune_language_model": true,
175
+ "tune_mm_projector": true,
176
+ "tune_vision_tower": true,
177
+ "vision_resolution": -1,
178
+ "vision_tower_cfg": {
179
+ "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila/vila_3b_oxe_sim_jack_o/tmp-checkpoint-8700/vision_tower",
180
+ "add_cross_attention": false,
181
+ "architectures": [
182
+ "SiglipVisionModel"
183
+ ],
184
+ "attention_dropout": 0.0,
185
+ "bad_words_ids": null,
186
+ "begin_suppress_tokens": null,
187
+ "bos_token_id": null,
188
+ "chunk_size_feed_forward": 0,
189
+ "cross_attention_hidden_size": null,
190
+ "decoder_start_token_id": null,
191
+ "diversity_penalty": 0.0,
192
+ "do_sample": false,
193
+ "early_stopping": false,
194
+ "encoder_no_repeat_ngram_size": 0,
195
+ "eos_token_id": null,
196
+ "exponential_decay_length_penalty": null,
197
+ "finetuning_task": null,
198
+ "forced_bos_token_id": null,
199
+ "forced_eos_token_id": null,
200
+ "hidden_act": "gelu_pytorch_tanh",
201
+ "hidden_size": 1152,
202
+ "id2label": {
203
+ "0": "LABEL_0",
204
+ "1": "LABEL_1"
205
+ },
206
+ "image_size": 384,
207
+ "intermediate_size": 4304,
208
+ "is_decoder": false,
209
+ "is_encoder_decoder": false,
210
+ "label2id": {
211
+ "LABEL_0": 0,
212
+ "LABEL_1": 1
213
+ },
214
+ "layer_norm_eps": 1e-06,
215
+ "length_penalty": 1.0,
216
+ "max_length": 20,
217
+ "min_length": 0,
218
+ "model_type": "siglip_vision_model",
219
+ "no_repeat_ngram_size": 0,
220
+ "num_attention_heads": 16,
221
+ "num_beam_groups": 1,
222
+ "num_beams": 1,
223
+ "num_channels": 3,
224
+ "num_hidden_layers": 27,
225
+ "num_return_sequences": 1,
226
+ "output_attentions": false,
227
+ "output_hidden_states": false,
228
+ "output_scores": false,
229
+ "pad_token_id": null,
230
+ "patch_size": 14,
231
+ "prefix": null,
232
+ "problem_type": null,
233
+ "pruned_heads": {},
234
+ "remove_invalid_values": false,
235
+ "repetition_penalty": 1.0,
236
+ "return_dict": true,
237
+ "return_dict_in_generate": false,
238
+ "sep_token_id": null,
239
+ "suppress_tokens": null,
240
+ "task_specific_params": null,
241
+ "temperature": 1.0,
242
+ "tf_legacy_loss": false,
243
+ "tie_encoder_decoder": false,
244
+ "tie_word_embeddings": true,
245
+ "tokenizer_class": null,
246
+ "top_k": 50,
247
+ "top_p": 1.0,
248
+ "torch_dtype": "bfloat16",
249
+ "torchscript": false,
250
+ "typical_p": 1.0,
251
+ "use_bfloat16": false
252
+ }
253
+ }
checkpoint-8700/global_step8700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cf2093bbaab2171e7bc9a904c72eacfdb8e57165dc45588c954f194f4720bd
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1eb14bd71544adf8fbd7d58ceba441e6f41e027a483e5f94d31526fd09c436
3
+ size 2361117185
checkpoint-8700/global_step8700/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadce2d9804841cb74193dab63e4875231e65f53c9901467abf3ef79d5f2e0e4
3
+ size 2361117185
checkpoint-8700/global_step8700/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd60dd63746253a89578b12be8e1478d70915e8af4897c35f7353b9af227ba2
3
+ size 2361117185
checkpoint-8700/global_step8700/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec2cf28aa6764be766a04d525a06c084f8909e7f39030586c04fe4d1be978be
3
+ size 2361117185
checkpoint-8700/global_step8700/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837d8cb41a3a8152201887325998253becfca186acd5f3f4296bf10bd64fa760
3
+ size 2361117185
checkpoint-8700/global_step8700/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16de79772c9f510c95ed0708862fa47361428370981bc25db36c541f3f5831da
3
+ size 2361117185
checkpoint-8700/global_step8700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9146bcde0640dbe48dab01efa1b9438eaadd38eaa090e283d3c75c647f8b88e
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876509abf46748c0725423f4a190e783d12e1afd5645e596feabcfa94a09eb58
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb61beecb7c7ca378965bf2e9fa626fc617b7aa7e269dd6d1000b037698d0dc4
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc41738696670e89427b97a2783f961fdf8c501ce04d0f7ce3238d7ba177daf
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832e2564f0f49db4b7efc5fa5149bdc2192baab4b018041bb8876d6fb4d5b3db
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf30c5ca64b82e24298ef493690a62e24cdd2d689cc56115e05bda0d1483cde
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe95762c71f57f4cf40f3264760422f95277bfb655fe9d1314736514fae495e
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c5a14ac01bc36389117a7a0c97cf5095c728f41fb3608ea0b02291385cd37b
3
+ size 2361117175
checkpoint-8700/global_step8700/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ac71527e85f9778c00f4c0b5bd48b5486fc0a15f26ae12cb6e58452ebc3444
3
+ size 2361117175
checkpoint-8700/global_step8700/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c392ae1cf60ca191375c128709d5ac489ae36ad649ad72f0dfa144acc5c8f2a6
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_10_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3da7aeb2a742b4a7c82786e7e9204e6b5a3dcb34a89c217c5ffcee2f464701b
3
+ size 414735
checkpoint-8700/global_step8700/zero_pp_rank_11_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c392bb724876fd6881905f78053d0825183854893c764028012db92f3b7326a5
3
+ size 414735
checkpoint-8700/global_step8700/zero_pp_rank_12_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a27093f96aff3b0576e01ccfca437a718b929ebd7f80bab16ae4994a87076c
3
+ size 414735
checkpoint-8700/global_step8700/zero_pp_rank_13_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33b54a7200f44c695e7f9d5ee56a7267fa4983099007794032d7b17caf8fab2
3
+ size 414735
checkpoint-8700/global_step8700/zero_pp_rank_14_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9681082546c6199d1f86e5e20462f019dd28937c1305b1c3c90a3356a756769c
3
+ size 414735
checkpoint-8700/global_step8700/zero_pp_rank_15_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589e5894a60b42bf0c4d2dbe731ee2c56550dc20c4812cb2e97c8ab79b3e847c
3
+ size 414735
checkpoint-8700/global_step8700/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00efd683197584fead835a124592caa3d77c9ec371a9640691eaa713f4d3e852
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8110cf34f702ac6c2d547f943555ec81c687f49be9b2c698e0d61fd0e753e434
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9415ee6e8d00f8637ae90fb84fce6eb0b52199a197746cba20bc5afe1221b331
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93bdb24f247533420940f038fb38cce85e836556870eecde567b2f40185f704
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e04929e47dc577b42fbbf355fbf152a4f49c69d3d070719fb65d99422b9761
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d949b3c042c094cd5da5c19fb55222d9204dc5f49588bf0fb36b996f5d8d8bb8
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276822847b9858d17e272ec4b7749678280adb032a2a16a71098df5cc0987565
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_8_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed41c972fccc697c200ab811a95c7d178ca4e0894adcae8587c96e8b6ebeabaa
3
+ size 413988
checkpoint-8700/global_step8700/zero_pp_rank_9_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d9d4648064af665b895c90abdd26cf846b31098667f11289ffca01717250b8
3
+ size 413988
checkpoint-8700/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step8700
checkpoint-8700/llm/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila/vila_3b_oxe_sim_jack_o/tmp-checkpoint-8700/llm",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 6912,
14
+ "max_position_embeddings": 4096,
15
+ "model_max_length": 4096,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 20,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 20,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "tokenizer_model_max_length": 4096,
27
+ "tokenizer_padding_side": "right",
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.36.2",
30
+ "use_cache": false,
31
+ "vocab_size": 32000
32
+ }
checkpoint-8700/llm/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.36.2"
7
+ }
checkpoint-8700/llm/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3881c7d15f91b15b0dbd0e42f3f64082b9400bfe43781ae5f17a333417390b
3
+ size 4974521464
checkpoint-8700/llm/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ac1e6ed87765e83ca1e6e75e5b4044d4b8e9c7428cf9fe2eb6578e6491e3e6
3
+ size 428632856
checkpoint-8700/llm/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5403120640
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.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.norm.weight": "model-00002-of-00002.safetensors"
297
+ }
298
+ }
checkpoint-8700/llm/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-8700/llm/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aedb3582ecda9fa99ee9242c17a9658f6744db083ee6ebdc8fb14857f84d220
3
+ size 499723
checkpoint-8700/llm/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 4096,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
checkpoint-8700/mm_projector/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila/vila_3b_oxe_sim_jack_o/tmp-checkpoint-8700/mm_projector",
3
+ "architectures": [
4
+ "MultimodalProjector"
5
+ ],
6
+ "mm_projector_type": "mlp_downsample",
7
+ "model_type": "v2l_projector",
8
+ "torch_dtype": "bfloat16",
9
+ "transformers_version": "4.36.2"
10
+ }
checkpoint-8700/mm_projector/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c03fb1f3b76192c22eb31a30b72b613121bbe3bd334bee0aa1851b6c6117d4a
3
+ size 36729360
checkpoint-8700/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d427f50a4b918abd1b29c08d181c3049d53c751f7d62ab8b589e9737cdeb3c89
3
+ size 21687
checkpoint-8700/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f325e5dfaf9edb6ba115f90d6556217315523f097f447331e9dc48b74c1307
3
+ size 21687
checkpoint-8700/rng_state_10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ac5d961aa2a73a29239939231d8b8141771abfcb7500a5de06838964fd971b
3
+ size 21698
checkpoint-8700/rng_state_11.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a01ff5444331cc8871752d42550373325f51424611622467ed0e9ee1aa22f87d
3
+ size 21698
checkpoint-8700/rng_state_12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111bbdacabcb61556c1b120e649265d3ebcd5f731b84556a1721f16a895acaf7
3
+ size 21698
checkpoint-8700/rng_state_13.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20517a44d2277a5d5b1fe5ab6b227bcfd4e753cd4be36f0b0034f58550f6b2ed
3
+ size 21698