mgoin commited on
Commit
5883b46
·
verified ·
1 Parent(s): efc1798

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/a272c74b2481d8aff3aa6fc2c4bf891fe57334fb",
3
+ "architectures": [
4
+ "SparseLlavaForConditionalGeneration"
5
+ ],
6
+ "compression_config": {
7
+ "config_groups": {
8
+ "group_0": {
9
+ "input_activations": {
10
+ "actorder": null,
11
+ "block_structure": null,
12
+ "dynamic": true,
13
+ "group_size": null,
14
+ "num_bits": 8,
15
+ "observer": "memoryless",
16
+ "observer_kwargs": {},
17
+ "strategy": "token",
18
+ "symmetric": true,
19
+ "type": "float"
20
+ },
21
+ "output_activations": null,
22
+ "targets": [
23
+ "Linear"
24
+ ],
25
+ "weights": {
26
+ "actorder": null,
27
+ "block_structure": null,
28
+ "dynamic": false,
29
+ "group_size": null,
30
+ "num_bits": 8,
31
+ "observer": "minmax",
32
+ "observer_kwargs": {},
33
+ "strategy": "channel",
34
+ "symmetric": true,
35
+ "type": "float"
36
+ }
37
+ }
38
+ },
39
+ "format": "float-quantized",
40
+ "global_compression_ratio": 1.2426076581224452,
41
+ "ignore": [],
42
+ "kv_cache_scheme": null,
43
+ "quant_method": "compressed-tensors",
44
+ "quantization_status": "compressed"
45
+ },
46
+ "ignore_index": -100,
47
+ "image_seq_length": 576,
48
+ "image_token_index": 32000,
49
+ "model_type": "llava",
50
+ "pad_token_id": 32001,
51
+ "projector_hidden_act": "gelu",
52
+ "text_config": {
53
+ "_name_or_path": "lmsys/vicuna-7b-v1.5",
54
+ "add_cross_attention": false,
55
+ "architectures": [
56
+ "LlamaForCausalLM"
57
+ ],
58
+ "attention_bias": false,
59
+ "attention_dropout": 0.0,
60
+ "bad_words_ids": null,
61
+ "begin_suppress_tokens": null,
62
+ "bos_token_id": 1,
63
+ "chunk_size_feed_forward": 0,
64
+ "cross_attention_hidden_size": null,
65
+ "decoder_start_token_id": null,
66
+ "diversity_penalty": 0.0,
67
+ "do_sample": false,
68
+ "early_stopping": false,
69
+ "encoder_no_repeat_ngram_size": 0,
70
+ "eos_token_id": 2,
71
+ "exponential_decay_length_penalty": null,
72
+ "finetuning_task": null,
73
+ "forced_bos_token_id": null,
74
+ "forced_eos_token_id": null,
75
+ "head_dim": 128,
76
+ "hidden_act": "silu",
77
+ "hidden_size": 4096,
78
+ "id2label": {
79
+ "0": "LABEL_0",
80
+ "1": "LABEL_1"
81
+ },
82
+ "initializer_range": 0.02,
83
+ "intermediate_size": 11008,
84
+ "is_decoder": false,
85
+ "is_encoder_decoder": false,
86
+ "label2id": {
87
+ "LABEL_0": 0,
88
+ "LABEL_1": 1
89
+ },
90
+ "length_penalty": 1.0,
91
+ "max_length": 20,
92
+ "max_position_embeddings": 4096,
93
+ "min_length": 0,
94
+ "mlp_bias": false,
95
+ "model_type": "llama",
96
+ "no_repeat_ngram_size": 0,
97
+ "num_attention_heads": 32,
98
+ "num_beam_groups": 1,
99
+ "num_beams": 1,
100
+ "num_hidden_layers": 32,
101
+ "num_key_value_heads": 32,
102
+ "num_return_sequences": 1,
103
+ "output_attentions": false,
104
+ "output_hidden_states": false,
105
+ "output_scores": false,
106
+ "pad_token_id": null,
107
+ "prefix": null,
108
+ "pretraining_tp": 1,
109
+ "problem_type": null,
110
+ "pruned_heads": {},
111
+ "remove_invalid_values": false,
112
+ "repetition_penalty": 1.0,
113
+ "return_dict": true,
114
+ "return_dict_in_generate": false,
115
+ "rms_norm_eps": 1e-05,
116
+ "rope_scaling": null,
117
+ "rope_theta": 10000.0,
118
+ "sep_token_id": null,
119
+ "suppress_tokens": null,
120
+ "task_specific_params": null,
121
+ "temperature": 1.0,
122
+ "tf_legacy_loss": false,
123
+ "tie_encoder_decoder": false,
124
+ "tie_word_embeddings": false,
125
+ "tokenizer_class": null,
126
+ "top_k": 50,
127
+ "top_p": 1.0,
128
+ "torch_dtype": "float16",
129
+ "torchscript": false,
130
+ "typical_p": 1.0,
131
+ "use_bfloat16": false,
132
+ "use_cache": true,
133
+ "vocab_size": 32064
134
+ },
135
+ "tie_word_embeddings": false,
136
+ "torch_dtype": "float16",
137
+ "transformers_version": "4.45.0.dev0",
138
+ "vision_config": {
139
+ "_name_or_path": "",
140
+ "add_cross_attention": false,
141
+ "architectures": null,
142
+ "attention_dropout": 0.0,
143
+ "bad_words_ids": null,
144
+ "begin_suppress_tokens": null,
145
+ "bos_token_id": null,
146
+ "chunk_size_feed_forward": 0,
147
+ "cross_attention_hidden_size": null,
148
+ "decoder_start_token_id": null,
149
+ "diversity_penalty": 0.0,
150
+ "do_sample": false,
151
+ "early_stopping": false,
152
+ "encoder_no_repeat_ngram_size": 0,
153
+ "eos_token_id": null,
154
+ "exponential_decay_length_penalty": null,
155
+ "finetuning_task": null,
156
+ "forced_bos_token_id": null,
157
+ "forced_eos_token_id": null,
158
+ "hidden_act": "quick_gelu",
159
+ "hidden_size": 1024,
160
+ "id2label": {
161
+ "0": "LABEL_0",
162
+ "1": "LABEL_1"
163
+ },
164
+ "image_size": 336,
165
+ "initializer_factor": 1.0,
166
+ "initializer_range": 0.02,
167
+ "intermediate_size": 4096,
168
+ "is_decoder": false,
169
+ "is_encoder_decoder": false,
170
+ "label2id": {
171
+ "LABEL_0": 0,
172
+ "LABEL_1": 1
173
+ },
174
+ "layer_norm_eps": 1e-05,
175
+ "length_penalty": 1.0,
176
+ "max_length": 20,
177
+ "min_length": 0,
178
+ "model_type": "clip_vision_model",
179
+ "no_repeat_ngram_size": 0,
180
+ "num_attention_heads": 16,
181
+ "num_beam_groups": 1,
182
+ "num_beams": 1,
183
+ "num_channels": 3,
184
+ "num_hidden_layers": 24,
185
+ "num_return_sequences": 1,
186
+ "output_attentions": false,
187
+ "output_hidden_states": false,
188
+ "output_scores": false,
189
+ "pad_token_id": null,
190
+ "patch_size": 14,
191
+ "prefix": null,
192
+ "problem_type": null,
193
+ "projection_dim": 768,
194
+ "pruned_heads": {},
195
+ "remove_invalid_values": false,
196
+ "repetition_penalty": 1.0,
197
+ "return_dict": true,
198
+ "return_dict_in_generate": false,
199
+ "sep_token_id": null,
200
+ "suppress_tokens": null,
201
+ "task_specific_params": null,
202
+ "temperature": 1.0,
203
+ "tf_legacy_loss": false,
204
+ "tie_encoder_decoder": false,
205
+ "tie_word_embeddings": true,
206
+ "tokenizer_class": null,
207
+ "top_k": 50,
208
+ "top_p": 1.0,
209
+ "torch_dtype": null,
210
+ "torchscript": false,
211
+ "typical_p": 1.0,
212
+ "use_bfloat16": false,
213
+ "vocab_size": 32000
214
+ },
215
+ "vision_feature_layer": -2,
216
+ "vision_feature_select_strategy": "default",
217
+ "vocab_size": 32064
218
+ }
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": 32001,
6
+ "transformers_version": "4.45.0.dev0"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1ed5371f9ba7895c74694635f27d3f7a30d6de98f441a3548aa2c9e951a963
3
+ size 4998631632
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a124671ac452964b9b614f4aa4b36f0e1f3b2f9245eaaeec2dda7863741a91bf
3
+ size 2201306736
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
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
+ "32000": {
31
+ "content": "<image>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "bos_token": "<s>",
48
+ "clean_up_tokenization_spaces": false,
49
+ "eos_token": "</s>",
50
+ "legacy": false,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "padding_side": "left",
54
+ "processor_class": "LlavaProcessor",
55
+ "sp_model_kwargs": {},
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "trust_remote_code": false,
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": false
60
+ }