Fudan-FUXI commited on
Commit
d0009e6
1 Parent(s): cd4d187

Upload 3 files

Browse files
Files changed (3) hide show
  1. adapter_config.json +34 -0
  2. config.json +261 -0
  3. non_lora_trainables.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "v_proj",
25
+ "k_proj",
26
+ "o_proj",
27
+ "q_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
config.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/LiFT-Critic-40b",
3
+ "architectures": [
4
+ "LlavaLlamaModel"
5
+ ],
6
+ "drop_path_rate": 0.0,
7
+ "fps": 0.0,
8
+ "hidden_size": 7168,
9
+ "image_aspect_ratio": "resize",
10
+ "interpolate_mode": "linear",
11
+ "llm_cfg": {
12
+ "_name_or_path": "./llm",
13
+ "add_cross_attention": false,
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": 1,
22
+ "chunk_size_feed_forward": 0,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 7,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "hidden_act": "silu",
35
+ "hidden_size": 7168,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 20480,
42
+ "is_decoder": false,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1
47
+ },
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 4096,
51
+ "min_length": 0,
52
+ "model_max_length": 4096,
53
+ "model_type": "llama",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_attention_heads": 56,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_hidden_layers": 60,
59
+ "num_key_value_heads": 8,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": 0,
65
+ "prefix": null,
66
+ "pretraining_tp": 1,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "rms_norm_eps": 1e-05,
74
+ "rope_scaling": null,
75
+ "rope_theta": 5000000.0,
76
+ "sep_token_id": null,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": null,
79
+ "temperature": 1.0,
80
+ "tf_legacy_loss": false,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": false,
83
+ "tokenizer_class": null,
84
+ "tokenizer_model_max_length": 4096,
85
+ "tokenizer_padding_side": "right",
86
+ "top_k": 50,
87
+ "top_p": 1.0,
88
+ "torch_dtype": "bfloat16",
89
+ "torchscript": false,
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": false,
93
+ "vocab_size": 64000
94
+ },
95
+ "mm_hidden_size": 3200,
96
+ "mm_projector_cfg": {
97
+ "_name_or_path": "./mm_projector",
98
+ "add_cross_attention": false,
99
+ "architectures": [
100
+ "MultimodalProjector"
101
+ ],
102
+ "bad_words_ids": null,
103
+ "begin_suppress_tokens": null,
104
+ "bos_token_id": null,
105
+ "chunk_size_feed_forward": 0,
106
+ "cross_attention_hidden_size": null,
107
+ "decoder_start_token_id": null,
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "mm_projector_type": "mlp_downsample",
131
+ "model_type": "v2l_projector",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_return_sequences": 1,
136
+ "output_attentions": false,
137
+ "output_hidden_states": false,
138
+ "output_scores": false,
139
+ "pad_token_id": null,
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "pruned_heads": {},
143
+ "remove_invalid_values": false,
144
+ "repetition_penalty": 1.0,
145
+ "return_dict": true,
146
+ "return_dict_in_generate": false,
147
+ "sep_token_id": null,
148
+ "suppress_tokens": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tf_legacy_loss": false,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": "bfloat16",
158
+ "torchscript": false,
159
+ "typical_p": 1.0,
160
+ "use_bfloat16": false
161
+ },
162
+ "mm_projector_lr": null,
163
+ "mm_use_im_patch_token": false,
164
+ "mm_use_im_start_end": false,
165
+ "mm_vision_select_feature": "patch",
166
+ "mm_vision_select_layer": -1,
167
+ "model_dtype": "torch.bfloat16",
168
+ "model_type": "llava_llama",
169
+ "num_video_frames": 8,
170
+ "resume_path": "./checkpoints/LiFT-Critic-40b",
171
+ "s2": false,
172
+ "s2_max_split_size": 336,
173
+ "s2_scales": "336,672,1008",
174
+ "transformers_version": "4.37.2",
175
+ "tune_language_model": false,
176
+ "tune_mm_projector": false,
177
+ "tune_vision_tower": false,
178
+ "vision_resolution": -1,
179
+ "vision_tower_cfg": {
180
+ "_name_or_path": "./vision_tower",
181
+ "add_cross_attention": false,
182
+ "architectures": [
183
+ "InternVisionModel"
184
+ ],
185
+ "attention_dropout": 0.0,
186
+ "bad_words_ids": null,
187
+ "begin_suppress_tokens": null,
188
+ "bos_token_id": null,
189
+ "chunk_size_feed_forward": 0,
190
+ "cross_attention_hidden_size": null,
191
+ "decoder_start_token_id": null,
192
+ "diversity_penalty": 0.0,
193
+ "do_sample": false,
194
+ "drop_path_rate": 0.0,
195
+ "dropout": 0.0,
196
+ "early_stopping": false,
197
+ "encoder_no_repeat_ngram_size": 0,
198
+ "eos_token_id": null,
199
+ "exponential_decay_length_penalty": null,
200
+ "finetuning_task": null,
201
+ "forced_bos_token_id": null,
202
+ "forced_eos_token_id": null,
203
+ "hidden_act": "gelu",
204
+ "hidden_size": 3200,
205
+ "id2label": {
206
+ "0": "LABEL_0",
207
+ "1": "LABEL_1"
208
+ },
209
+ "image_size": 448,
210
+ "initializer_factor": 0.1,
211
+ "initializer_range": 1e-10,
212
+ "intermediate_size": 12800,
213
+ "is_decoder": false,
214
+ "is_encoder_decoder": false,
215
+ "label2id": {
216
+ "LABEL_0": 0,
217
+ "LABEL_1": 1
218
+ },
219
+ "layer_norm_eps": 1e-06,
220
+ "length_penalty": 1.0,
221
+ "max_length": 20,
222
+ "min_length": 0,
223
+ "model_type": "intern_vit_6b",
224
+ "no_repeat_ngram_size": 0,
225
+ "num_attention_heads": 25,
226
+ "num_beam_groups": 1,
227
+ "num_beams": 1,
228
+ "num_channels": 3,
229
+ "num_hidden_layers": 45,
230
+ "num_return_sequences": 1,
231
+ "output_attentions": false,
232
+ "output_hidden_states": false,
233
+ "output_scores": false,
234
+ "pad_token_id": null,
235
+ "patch_size": 14,
236
+ "prefix": null,
237
+ "problem_type": null,
238
+ "pruned_heads": {},
239
+ "qk_normalization": true,
240
+ "qkv_bias": false,
241
+ "remove_invalid_values": false,
242
+ "repetition_penalty": 1.0,
243
+ "return_dict": true,
244
+ "return_dict_in_generate": false,
245
+ "sep_token_id": null,
246
+ "suppress_tokens": null,
247
+ "task_specific_params": null,
248
+ "temperature": 1.0,
249
+ "tf_legacy_loss": false,
250
+ "tie_encoder_decoder": false,
251
+ "tie_word_embeddings": true,
252
+ "tokenizer_class": null,
253
+ "top_k": 50,
254
+ "top_p": 1.0,
255
+ "torch_dtype": "bfloat16",
256
+ "torchscript": false,
257
+ "typical_p": 1.0,
258
+ "use_bfloat16": true,
259
+ "use_flash_attn": true
260
+ }
261
+ }
non_lora_trainables.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fb82c3660319e6d0b239950b20c28181e97f1ade117dc0660b40e2ad94a89b
3
+ size 912