abdurafeyf commited on
Commit
e2dc34d
·
verified ·
1 Parent(s): d950bba

Delete config.json

Browse files
Files changed (1) hide show
  1. config.json +0 -259
config.json DELETED
@@ -1,259 +0,0 @@
1
- {
2
- "_name_or_path": "unsloth/Llama-3.2-11B-Vision-Instruct",
3
- "architectures": [
4
- "MllamaForConditionalGeneration"
5
- ],
6
- "image_token_index": 128256,
7
- "model_type": "mllama",
8
- "quantization_config": {
9
- "_load_in_4bit": true,
10
- "_load_in_8bit": false,
11
- "bnb_4bit_compute_dtype": "bfloat16",
12
- "bnb_4bit_quant_storage": "uint8",
13
- "bnb_4bit_quant_type": "nf4",
14
- "bnb_4bit_use_double_quant": true,
15
- "llm_int8_enable_fp32_cpu_offload": false,
16
- "llm_int8_has_fp16_weight": false,
17
- "llm_int8_skip_modules": [
18
- "lm_head",
19
- "multi_modal_projector",
20
- "merger",
21
- "modality_projection",
22
- "language_model.model.layers.1.self_attn",
23
- "language_model.model.layers.1.mlp",
24
- "vision_model.transformer.layers.13.mlp.fc2",
25
- "language_model.model.layers.8.cross_attn.o_proj",
26
- "language_model.model.layers.13.cross_attn.o_proj",
27
- "language_model.model.layers.13.mlp.down_proj",
28
- "language_model.model.layers.18.cross_attn.o_proj",
29
- "language_model.model.layers.18.mlp.down_proj",
30
- "language_model.model.layers.23.cross_attn.o_proj",
31
- "language_model.model.layers.28.cross_attn.o_proj",
32
- "language_model.model.layers.33.cross_attn.o_proj",
33
- "language_model.model.layers.38.cross_attn.o_proj"
34
- ],
35
- "llm_int8_threshold": 6.0,
36
- "load_in_4bit": true,
37
- "load_in_8bit": false,
38
- "quant_method": "bitsandbytes"
39
- },
40
- "text_config": {
41
- "_attn_implementation_autoset": false,
42
- "_name_or_path": "",
43
- "add_cross_attention": false,
44
- "architectures": null,
45
- "bad_words_ids": null,
46
- "begin_suppress_tokens": null,
47
- "bos_token_id": 128000,
48
- "chunk_size_feed_forward": 0,
49
- "cross_attention_hidden_size": null,
50
- "cross_attention_layers": [
51
- 3,
52
- 8,
53
- 13,
54
- 18,
55
- 23,
56
- 28,
57
- 33,
58
- 38
59
- ],
60
- "decoder_start_token_id": null,
61
- "diversity_penalty": 0.0,
62
- "do_sample": false,
63
- "dropout": 0,
64
- "early_stopping": false,
65
- "encoder_no_repeat_ngram_size": 0,
66
- "eos_token_id": [
67
- 128001,
68
- 128008,
69
- 128009
70
- ],
71
- "exponential_decay_length_penalty": null,
72
- "finetuning_task": null,
73
- "forced_bos_token_id": null,
74
- "forced_eos_token_id": null,
75
- "hidden_act": "silu",
76
- "hidden_size": 4096,
77
- "id2label": {
78
- "0": "LABEL_0",
79
- "1": "LABEL_1"
80
- },
81
- "initializer_range": 0.02,
82
- "intermediate_size": 14336,
83
- "is_decoder": false,
84
- "is_encoder_decoder": false,
85
- "label2id": {
86
- "LABEL_0": 0,
87
- "LABEL_1": 1
88
- },
89
- "length_penalty": 1.0,
90
- "max_length": 20,
91
- "max_position_embeddings": 131072,
92
- "min_length": 0,
93
- "model_type": "mllama_text_model",
94
- "no_repeat_ngram_size": 0,
95
- "num_attention_heads": 32,
96
- "num_beam_groups": 1,
97
- "num_beams": 1,
98
- "num_hidden_layers": 40,
99
- "num_key_value_heads": 8,
100
- "num_return_sequences": 1,
101
- "output_attentions": false,
102
- "output_hidden_states": false,
103
- "output_scores": false,
104
- "pad_token_id": 128004,
105
- "prefix": null,
106
- "problem_type": null,
107
- "pruned_heads": {},
108
- "remove_invalid_values": false,
109
- "repetition_penalty": 1.0,
110
- "return_dict": true,
111
- "return_dict_in_generate": false,
112
- "rms_norm_eps": 1e-05,
113
- "rope_scaling": {
114
- "factor": 8.0,
115
- "high_freq_factor": 4.0,
116
- "low_freq_factor": 1.0,
117
- "original_max_position_embeddings": 8192,
118
- "rope_type": "llama3"
119
- },
120
- "rope_theta": 500000.0,
121
- "sep_token_id": null,
122
- "suppress_tokens": null,
123
- "task_specific_params": null,
124
- "temperature": 1.0,
125
- "tf_legacy_loss": false,
126
- "tie_encoder_decoder": false,
127
- "tie_word_embeddings": false,
128
- "tokenizer_class": null,
129
- "top_k": 50,
130
- "top_p": 1.0,
131
- "torch_dtype": "bfloat16",
132
- "torchscript": false,
133
- "typical_p": 1.0,
134
- "use_bfloat16": false,
135
- "use_cache": true,
136
- "vocab_size": 128256
137
- },
138
- "torch_dtype": "bfloat16",
139
- "transformers_version": "4.46.3",
140
- "unsloth_fixed": true,
141
- "vision_config": {
142
- "_attn_implementation_autoset": false,
143
- "_name_or_path": "",
144
- "add_cross_attention": false,
145
- "architectures": null,
146
- "attention_heads": 16,
147
- "bad_words_ids": null,
148
- "begin_suppress_tokens": null,
149
- "bos_token_id": null,
150
- "chunk_size_feed_forward": 0,
151
- "cross_attention_hidden_size": null,
152
- "decoder_start_token_id": null,
153
- "diversity_penalty": 0.0,
154
- "do_sample": false,
155
- "early_stopping": false,
156
- "encoder_no_repeat_ngram_size": 0,
157
- "eos_token_id": null,
158
- "exponential_decay_length_penalty": null,
159
- "finetuning_task": null,
160
- "forced_bos_token_id": null,
161
- "forced_eos_token_id": null,
162
- "hidden_act": "gelu",
163
- "hidden_size": 1280,
164
- "id2label": {
165
- "0": "LABEL_0",
166
- "1": "LABEL_1"
167
- },
168
- "image_size": 560,
169
- "initializer_range": 0.02,
170
- "intermediate_layers_indices": [
171
- 3,
172
- 7,
173
- 15,
174
- 23,
175
- 30
176
- ],
177
- "intermediate_size": 5120,
178
- "is_decoder": false,
179
- "is_encoder_decoder": false,
180
- "label2id": {
181
- "LABEL_0": 0,
182
- "LABEL_1": 1
183
- },
184
- "length_penalty": 1.0,
185
- "max_length": 20,
186
- "max_num_tiles": 4,
187
- "min_length": 0,
188
- "model_type": "mllama_vision_model",
189
- "no_repeat_ngram_size": 0,
190
- "norm_eps": 1e-05,
191
- "num_beam_groups": 1,
192
- "num_beams": 1,
193
- "num_channels": 3,
194
- "num_global_layers": 8,
195
- "num_hidden_layers": 32,
196
- "num_return_sequences": 1,
197
- "output_attentions": false,
198
- "output_hidden_states": false,
199
- "output_scores": false,
200
- "pad_token_id": null,
201
- "patch_size": 14,
202
- "prefix": null,
203
- "problem_type": null,
204
- "pruned_heads": {},
205
- "remove_invalid_values": false,
206
- "repetition_penalty": 1.0,
207
- "return_dict": true,
208
- "return_dict_in_generate": false,
209
- "sep_token_id": null,
210
- "supported_aspect_ratios": [
211
- [
212
- 1,
213
- 1
214
- ],
215
- [
216
- 1,
217
- 2
218
- ],
219
- [
220
- 1,
221
- 3
222
- ],
223
- [
224
- 1,
225
- 4
226
- ],
227
- [
228
- 2,
229
- 1
230
- ],
231
- [
232
- 2,
233
- 2
234
- ],
235
- [
236
- 3,
237
- 1
238
- ],
239
- [
240
- 4,
241
- 1
242
- ]
243
- ],
244
- "suppress_tokens": null,
245
- "task_specific_params": null,
246
- "temperature": 1.0,
247
- "tf_legacy_loss": false,
248
- "tie_encoder_decoder": false,
249
- "tie_word_embeddings": true,
250
- "tokenizer_class": null,
251
- "top_k": 50,
252
- "top_p": 1.0,
253
- "torch_dtype": "bfloat16",
254
- "torchscript": false,
255
- "typical_p": 1.0,
256
- "use_bfloat16": false,
257
- "vision_output_dim": 7680
258
- }
259
- }