Hugging Face's logo

tetttssts
/
test

Image-to-Text
Transformers
Safetensors
English
mllama
text-generation-inference
unsloth
Model card Files
xet
Community
tetttssts commited on
Commit
137059c
·
verified ·
1 Parent(s): 67e2f60

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +218 -104
config.json CHANGED
@@ -1,109 +1,223 @@
1
  {
2
- "architectures": [
3
- "MllamaForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
- "image_token_index": 128256,
6
- "model_type": "mllama",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "pad_token_id": 128004,
8
- "text_config": {
9
- "cross_attention_layers": [
10
- 3,
11
- 8,
12
- 13,
13
- 18,
14
- 23,
15
- 28,
16
- 33,
17
- 38
18
- ],
19
- "dropout": 0,
20
- "eos_token_id": [
21
- 128001,
22
- 128008,
23
- 128009
24
- ],
25
- "hidden_act": "silu",
26
- "hidden_size": 4096,
27
- "initializer_range": 0.02,
28
- "intermediate_size": 14336,
29
- "max_position_embeddings": 131072,
30
- "model_type": "mllama_text_model",
31
- "num_attention_heads": 32,
32
- "num_hidden_layers": 40,
33
- "num_key_value_heads": 8,
34
- "rms_norm_eps": 1e-05,
35
- "rope_scaling": {
36
- "factor": 8.0,
37
- "high_freq_factor": 4.0,
38
- "low_freq_factor": 1.0,
39
- "original_max_position_embeddings": 8192,
40
- "rope_type": "llama3"
41
- },
42
- "rope_theta": 500000.0,
43
- "torch_dtype": "float16",
44
- "use_cache": true,
45
- "vocab_size": 128256
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  },
47
- "torch_dtype": "float16",
48
- "transformers_version": "4.51.3",
49
- "unsloth_fixed": true,
50
- "unsloth_version": "2025.3.16",
51
- "vision_config": {
52
- "attention_heads": 16,
53
- "hidden_act": "gelu",
54
- "hidden_size": 1280,
55
- "image_size": 560,
56
- "initializer_range": 0.02,
57
- "intermediate_layers_indices": [
58
- 3,
59
- 7,
60
- 15,
61
- 23,
62
- 30
63
- ],
64
- "intermediate_size": 5120,
65
- "max_num_tiles": 4,
66
- "model_type": "mllama_vision_model",
67
- "norm_eps": 1e-05,
68
- "num_channels": 3,
69
- "num_global_layers": 8,
70
- "num_hidden_layers": 32,
71
- "patch_size": 14,
72
- "supported_aspect_ratios": [
73
- [
74
- 1,
75
- 1
76
- ],
77
- [
78
- 1,
79
- 2
80
- ],
81
- [
82
- 1,
83
- 3
84
- ],
85
- [
86
- 1,
87
- 4
88
- ],
89
- [
90
- 2,
91
- 1
92
- ],
93
- [
94
- 2,
95
- 2
96
- ],
97
- [
98
- 3,
99
- 1
100
- ],
101
- [
102
- 4,
103
- 1
104
- ]
105
- ],
106
- "torch_dtype": "float16",
107
- "vision_output_dim": 7680
108
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Llama-3.2-11B-Vision",
3
+ "architectures": [
4
+ "MllamaForConditionalGeneration"
5
+ ],
6
+ "image_token_index": 128256,
7
+ "model_type": "mllama",
8
+ "text_config": {
9
+ "_attn_implementation_autoset": false,
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "architectures": null,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 128000,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "cross_attention_layers": [
19
+ 3,
20
+ 8,
21
+ 13,
22
+ 18,
23
+ 23,
24
+ 28,
25
+ 33,
26
+ 38
27
  ],
28
+ "decoder_start_token_id": null,
29
+ "diversity_penalty": 0.0,
30
+ "do_sample": false,
31
+ "dropout": 0,
32
+ "early_stopping": false,
33
+ "encoder_no_repeat_ngram_size": 0,
34
+ "eos_token_id": 128001,
35
+ "exponential_decay_length_penalty": null,
36
+ "finetuning_task": null,
37
+ "forced_bos_token_id": null,
38
+ "forced_eos_token_id": null,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 4096,
41
+ "id2label": {
42
+ "0": "LABEL_0",
43
+ "1": "LABEL_1"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 14336,
47
+ "is_decoder": false,
48
+ "is_encoder_decoder": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "length_penalty": 1.0,
54
+ "max_length": 20,
55
+ "max_position_embeddings": 131072,
56
+ "min_length": 0,
57
+ "model_type": "mllama_text_model",
58
+ "no_repeat_ngram_size": 0,
59
+ "num_attention_heads": 32,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_hidden_layers": 40,
63
+ "num_key_value_heads": 8,
64
+ "num_return_sequences": 1,
65
+ "output_attentions": false,
66
+ "output_hidden_states": false,
67
+ "output_scores": false,
68
  "pad_token_id": 128004,
69
+ "prefix": null,
70
+ "problem_type": null,
71
+ "pruned_heads": {},
72
+ "remove_invalid_values": false,
73
+ "repetition_penalty": 1.0,
74
+ "return_dict": true,
75
+ "return_dict_in_generate": false,
76
+ "rms_norm_eps": 1e-05,
77
+ "rope_scaling": {
78
+ "factor": 8.0,
79
+ "high_freq_factor": 4.0,
80
+ "low_freq_factor": 1.0,
81
+ "original_max_position_embeddings": 8192,
82
+ "rope_type": "llama3"
83
+ },
84
+ "rope_theta": 500000.0,
85
+ "sep_token_id": null,
86
+ "suppress_tokens": null,
87
+ "task_specific_params": null,
88
+ "temperature": 1.0,
89
+ "tf_legacy_loss": false,
90
+ "tie_encoder_decoder": false,
91
+ "tie_word_embeddings": false,
92
+ "tokenizer_class": null,
93
+ "top_k": 50,
94
+ "top_p": 1.0,
95
+ "torch_dtype": "bfloat16",
96
+ "torchscript": false,
97
+ "typical_p": 1.0,
98
+ "use_bfloat16": false,
99
+ "use_cache": true,
100
+ "vocab_size": 128256
101
+ },
102
+ "torch_dtype": "bfloat16",
103
+ "transformers_version": "4.46.3",
104
+ "unsloth_fixed": true,
105
+ "vision_config": {
106
+ "_attn_implementation_autoset": false,
107
+ "_name_or_path": "",
108
+ "add_cross_attention": false,
109
+ "architectures": null,
110
+ "attention_heads": 16,
111
+ "bad_words_ids": null,
112
+ "begin_suppress_tokens": null,
113
+ "bos_token_id": null,
114
+ "chunk_size_feed_forward": 0,
115
+ "cross_attention_hidden_size": null,
116
+ "decoder_start_token_id": null,
117
+ "diversity_penalty": 0.0,
118
+ "do_sample": false,
119
+ "early_stopping": false,
120
+ "encoder_no_repeat_ngram_size": 0,
121
+ "eos_token_id": null,
122
+ "exponential_decay_length_penalty": null,
123
+ "finetuning_task": null,
124
+ "forced_bos_token_id": null,
125
+ "forced_eos_token_id": null,
126
+ "hidden_act": "gelu",
127
+ "hidden_size": 1280,
128
+ "id2label": {
129
+ "0": "LABEL_0",
130
+ "1": "LABEL_1"
131
  },
132
+ "image_size": 448,
133
+ "initializer_range": 0.02,
134
+ "intermediate_layers_indices": [
135
+ 3,
136
+ 7,
137
+ 15,
138
+ 23,
139
+ 30
140
+ ],
141
+ "intermediate_size": 5120,
142
+ "is_decoder": false,
143
+ "is_encoder_decoder": false,
144
+ "label2id": {
145
+ "LABEL_0": 0,
146
+ "LABEL_1": 1
147
+ },
148
+ "length_penalty": 1.0,
149
+ "max_length": 20,
150
+ "max_num_tiles": 4,
151
+ "min_length": 0,
152
+ "model_type": "mllama_vision_model",
153
+ "no_repeat_ngram_size": 0,
154
+ "norm_eps": 1e-05,
155
+ "num_beam_groups": 1,
156
+ "num_beams": 1,
157
+ "num_channels": 3,
158
+ "num_global_layers": 8,
159
+ "num_hidden_layers": 32,
160
+ "num_return_sequences": 1,
161
+ "output_attentions": false,
162
+ "output_hidden_states": false,
163
+ "output_scores": false,
164
+ "pad_token_id": null,
165
+ "patch_size": 14,
166
+ "prefix": null,
167
+ "problem_type": null,
168
+ "pruned_heads": {},
169
+ "remove_invalid_values": false,
170
+ "repetition_penalty": 1.0,
171
+ "return_dict": true,
172
+ "return_dict_in_generate": false,
173
+ "sep_token_id": null,
174
+ "supported_aspect_ratios": [
175
+ [
176
+ 1,
177
+ 1
178
+ ],
179
+ [
180
+ 1,
181
+ 2
182
+ ],
183
+ [
184
+ 1,
185
+ 3
186
+ ],
187
+ [
188
+ 1,
189
+ 4
190
+ ],
191
+ [
192
+ 2,
193
+ 1
194
+ ],
195
+ [
196
+ 2,
197
+ 2
198
+ ],
199
+ [
200
+ 3,
201
+ 1
202
+ ],
203
+ [
204
+ 4,
205
+ 1
206
+ ]
207
+ ],
208
+ "suppress_tokens": null,
209
+ "task_specific_params": null,
210
+ "temperature": 1.0,
211
+ "tf_legacy_loss": false,
212
+ "tie_encoder_decoder": false,
213
+ "tie_word_embeddings": true,
214
+ "tokenizer_class": null,
215
+ "top_k": 50,
216
+ "top_p": 1.0,
217
+ "torch_dtype": "bfloat16",
218
+ "torchscript": false,
219
+ "typical_p": 1.0,
220
+ "use_bfloat16": false,
221
+ "vision_output_dim": 7680
222
+ }
223
  }