LlamaFinetuneBase commited on
Commit
bbdcda3
1 Parent(s): 97000a4

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +218 -0
config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MllamaForConditionalGeneration"
4
+ ],
5
+ "image_token_index": 128256,
6
+ "model_type": "mllama",
7
+ "text_config": {
8
+ "_name_or_path": "",
9
+ "add_cross_attention": false,
10
+ "architectures": null,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": 128000,
14
+ "chunk_size_feed_forward": 0,
15
+ "cross_attention_hidden_size": null,
16
+ "cross_attention_layers": [
17
+ 3,
18
+ 8,
19
+ 13,
20
+ 18,
21
+ 23,
22
+ 28,
23
+ 33,
24
+ 38
25
+ ],
26
+ "decoder_start_token_id": null,
27
+ "diversity_penalty": 0.0,
28
+ "do_sample": false,
29
+ "dropout": 0,
30
+ "early_stopping": false,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "eos_token_id": 128001,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "hidden_act": "silu",
38
+ "hidden_size": 4096,
39
+ "id2label": {
40
+ "0": "LABEL_0",
41
+ "1": "LABEL_1"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 14336,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 131072,
54
+ "min_length": 0,
55
+ "model_type": "mllama_text_model",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 32,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 40,
61
+ "num_key_value_heads": 8,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 128004,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "rms_norm_eps": 1e-05,
75
+ "rope_scaling": {
76
+ "factor": 8.0,
77
+ "high_freq_factor": 4.0,
78
+ "low_freq_factor": 1.0,
79
+ "original_max_position_embeddings": 8192,
80
+ "rope_type": "llama3"
81
+ },
82
+ "rope_theta": 500000.0,
83
+ "sep_token_id": null,
84
+ "suppress_tokens": null,
85
+ "task_specific_params": null,
86
+ "temperature": 1.0,
87
+ "tf_legacy_loss": false,
88
+ "tie_encoder_decoder": false,
89
+ "tie_word_embeddings": false,
90
+ "tokenizer_class": null,
91
+ "top_k": 50,
92
+ "top_p": 1.0,
93
+ "torch_dtype": "bfloat16",
94
+ "torchscript": false,
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": false,
97
+ "use_cache": true,
98
+ "vocab_size": 128256
99
+ },
100
+ "torch_dtype": "bfloat16",
101
+ "transformers_version": "4.45.0.dev0",
102
+ "vision_config": {
103
+ "_name_or_path": "",
104
+ "add_cross_attention": false,
105
+ "architectures": null,
106
+ "attention_heads": 16,
107
+ "bad_words_ids": null,
108
+ "begin_suppress_tokens": null,
109
+ "bos_token_id": null,
110
+ "chunk_size_feed_forward": 0,
111
+ "cross_attention_hidden_size": null,
112
+ "decoder_start_token_id": null,
113
+ "diversity_penalty": 0.0,
114
+ "do_sample": false,
115
+ "early_stopping": false,
116
+ "encoder_no_repeat_ngram_size": 0,
117
+ "eos_token_id": null,
118
+ "exponential_decay_length_penalty": null,
119
+ "finetuning_task": null,
120
+ "forced_bos_token_id": null,
121
+ "forced_eos_token_id": null,
122
+ "hidden_act": "gelu",
123
+ "hidden_size": 1280,
124
+ "id2label": {
125
+ "0": "LABEL_0",
126
+ "1": "LABEL_1"
127
+ },
128
+ "image_size": 448,
129
+ "intermediate_layers_indices": [
130
+ 3,
131
+ 7,
132
+ 15,
133
+ 23,
134
+ 30
135
+ ],
136
+ "intermediate_size": 5120,
137
+ "is_decoder": false,
138
+ "is_encoder_decoder": false,
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "length_penalty": 1.0,
144
+ "max_length": 20,
145
+ "max_num_tiles": 4,
146
+ "min_length": 0,
147
+ "model_type": "mllama_vision_model",
148
+ "no_repeat_ngram_size": 0,
149
+ "norm_eps": 1e-05,
150
+ "num_beam_groups": 1,
151
+ "num_beams": 1,
152
+ "num_channels": 3,
153
+ "num_global_layers": 8,
154
+ "num_hidden_layers": 32,
155
+ "num_return_sequences": 1,
156
+ "output_attentions": false,
157
+ "output_hidden_states": false,
158
+ "output_scores": false,
159
+ "pad_token_id": null,
160
+ "patch_size": 14,
161
+ "prefix": null,
162
+ "problem_type": null,
163
+ "pruned_heads": {},
164
+ "remove_invalid_values": false,
165
+ "repetition_penalty": 1.0,
166
+ "return_dict": true,
167
+ "return_dict_in_generate": false,
168
+ "sep_token_id": null,
169
+ "supported_aspect_ratios": [
170
+ [
171
+ 1,
172
+ 1
173
+ ],
174
+ [
175
+ 1,
176
+ 2
177
+ ],
178
+ [
179
+ 1,
180
+ 3
181
+ ],
182
+ [
183
+ 1,
184
+ 4
185
+ ],
186
+ [
187
+ 2,
188
+ 1
189
+ ],
190
+ [
191
+ 2,
192
+ 2
193
+ ],
194
+ [
195
+ 3,
196
+ 1
197
+ ],
198
+ [
199
+ 4,
200
+ 1
201
+ ]
202
+ ],
203
+ "suppress_tokens": null,
204
+ "task_specific_params": null,
205
+ "temperature": 1.0,
206
+ "tf_legacy_loss": false,
207
+ "tie_encoder_decoder": false,
208
+ "tie_word_embeddings": true,
209
+ "tokenizer_class": null,
210
+ "top_k": 50,
211
+ "top_p": 1.0,
212
+ "torch_dtype": "bfloat16",
213
+ "torchscript": false,
214
+ "typical_p": 1.0,
215
+ "use_bfloat16": false,
216
+ "vision_output_dim": 7680
217
+ }
218
+ }