Hugging Face's logo

unsloth
/
Llama-3.2-11B-Vision-Instruct

Image-Text-to-Text
Transformers
Safetensors
PyTorch
English
mllama
llama-3
llama
meta
facebook
unsloth
multimodal
vision
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
4
danielhanchen commited on
Commit
b174a69
•
1 Parent(s): b4b019d

Upload MllamaForConditionalGeneration

Browse files
Files changed (8) hide show
  1. config.json +218 -40
  2. generation_config.json +1 -1
  3. model-00001-of-00005.safetensors +3 -0
  4. model-00002-of-00005.safetensors +3 -0
  5. model-00003-of-00005.safetensors +3 -0
  6. model-00004-of-00005.safetensors +3 -0
  7. model-00005-of-00005.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,46 +1,224 @@
1
  {
 
2
  "architectures": [
3
- "MllamaForCausalLM"
4
  ],
5
- "bos_token_id": 128000,
6
- "cross_attention_layers": [
7
- 3,
8
- 8,
9
- 13,
10
- 18,
11
- 23,
12
- 28,
13
- 33,
14
- 38
15
- ],
16
- "dropout": 0,
17
- "eos_token_id": [
18
- 128001,
19
- 128008,
20
- 128009
21
- ],
22
- "hidden_act": "silu",
23
- "hidden_size": 4096,
24
- "initializer_range": 0.02,
25
- "intermediate_size": 14336,
26
- "max_position_embeddings": 131072,
27
- "model_type": "mllama_text_model",
28
- "num_attention_heads": 32,
29
- "num_hidden_layers": 40,
30
- "num_key_value_heads": 8,
31
- "pad_token_id": 128004,
32
- "rms_norm_eps": 1e-05,
33
- "rope_scaling": {
34
- "factor": 8.0,
35
- "high_freq_factor": 4.0,
36
- "low_freq_factor": 1.0,
37
- "original_max_position_embeddings": 8192,
38
- "rope_type": "llama3"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
- "rope_theta": 500000.0,
41
- "tie_word_embeddings": false,
42
  "torch_dtype": "bfloat16",
43
- "transformers_version": "4.46.0.dev0",
44
- "use_cache": true,
45
- "vocab_size": 128256
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
3
  "architectures": [
4
+ "MllamaForConditionalGeneration"
5
  ],
6
+ "image_token_index": 128256,
7
+ "model_type": "mllama",
8
+ "text_config": {
9
+ "_name_or_path": "",
10
+ "add_cross_attention": false,
11
+ "architectures": null,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": 128000,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "cross_attention_layers": [
18
+ 3,
19
+ 8,
20
+ 13,
21
+ 18,
22
+ 23,
23
+ 28,
24
+ 33,
25
+ 38
26
+ ],
27
+ "decoder_start_token_id": null,
28
+ "diversity_penalty": 0.0,
29
+ "do_sample": false,
30
+ "dropout": 0,
31
+ "early_stopping": false,
32
+ "encoder_no_repeat_ngram_size": 0,
33
+ "eos_token_id": [
34
+ 128001,
35
+ 128008,
36
+ 128009
37
+ ],
38
+ "exponential_decay_length_penalty": null,
39
+ "finetuning_task": null,
40
+ "forced_bos_token_id": null,
41
+ "forced_eos_token_id": null,
42
+ "hidden_act": "silu",
43
+ "hidden_size": 4096,
44
+ "id2label": {
45
+ "0": "LABEL_0",
46
+ "1": "LABEL_1"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 14336,
50
+ "is_decoder": false,
51
+ "is_encoder_decoder": false,
52
+ "label2id": {
53
+ "LABEL_0": 0,
54
+ "LABEL_1": 1
55
+ },
56
+ "length_penalty": 1.0,
57
+ "max_length": 20,
58
+ "max_position_embeddings": 131072,
59
+ "min_length": 0,
60
+ "model_type": "mllama_text_model",
61
+ "no_repeat_ngram_size": 0,
62
+ "num_attention_heads": 32,
63
+ "num_beam_groups": 1,
64
+ "num_beams": 1,
65
+ "num_hidden_layers": 40,
66
+ "num_key_value_heads": 8,
67
+ "num_return_sequences": 1,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "output_scores": false,
71
+ "pad_token_id": 128004,
72
+ "prefix": null,
73
+ "problem_type": null,
74
+ "pruned_heads": {},
75
+ "remove_invalid_values": false,
76
+ "repetition_penalty": 1.0,
77
+ "return_dict": true,
78
+ "return_dict_in_generate": false,
79
+ "rms_norm_eps": 1e-05,
80
+ "rope_scaling": {
81
+ "factor": 8.0,
82
+ "high_freq_factor": 4.0,
83
+ "low_freq_factor": 1.0,
84
+ "original_max_position_embeddings": 8192,
85
+ "rope_type": "llama3"
86
+ },
87
+ "rope_theta": 500000.0,
88
+ "sep_token_id": null,
89
+ "suppress_tokens": null,
90
+ "task_specific_params": null,
91
+ "temperature": 1.0,
92
+ "tf_legacy_loss": false,
93
+ "tie_encoder_decoder": false,
94
+ "tie_word_embeddings": false,
95
+ "tokenizer_class": null,
96
+ "top_k": 50,
97
+ "top_p": 1.0,
98
+ "torch_dtype": "bfloat16",
99
+ "torchscript": false,
100
+ "typical_p": 1.0,
101
+ "use_bfloat16": false,
102
+ "use_cache": true,
103
+ "vocab_size": 128256
104
  },
 
 
105
  "torch_dtype": "bfloat16",
106
+ "transformers_version": "4.45.0",
107
+ "vision_config": {
108
+ "_name_or_path": "",
109
+ "add_cross_attention": false,
110
+ "architectures": null,
111
+ "attention_heads": 16,
112
+ "bad_words_ids": null,
113
+ "begin_suppress_tokens": null,
114
+ "bos_token_id": null,
115
+ "chunk_size_feed_forward": 0,
116
+ "cross_attention_hidden_size": null,
117
+ "decoder_start_token_id": null,
118
+ "diversity_penalty": 0.0,
119
+ "do_sample": false,
120
+ "early_stopping": false,
121
+ "encoder_no_repeat_ngram_size": 0,
122
+ "eos_token_id": null,
123
+ "exponential_decay_length_penalty": null,
124
+ "finetuning_task": null,
125
+ "forced_bos_token_id": null,
126
+ "forced_eos_token_id": null,
127
+ "hidden_act": "gelu",
128
+ "hidden_size": 1280,
129
+ "id2label": {
130
+ "0": "LABEL_0",
131
+ "1": "LABEL_1"
132
+ },
133
+ "image_size": 560,
134
+ "initializer_range": 0.02,
135
+ "intermediate_layers_indices": [
136
+ 3,
137
+ 7,
138
+ 15,
139
+ 23,
140
+ 30
141
+ ],
142
+ "intermediate_size": 5120,
143
+ "is_decoder": false,
144
+ "is_encoder_decoder": false,
145
+ "label2id": {
146
+ "LABEL_0": 0,
147
+ "LABEL_1": 1
148
+ },
149
+ "length_penalty": 1.0,
150
+ "max_length": 20,
151
+ "max_num_tiles": 4,
152
+ "min_length": 0,
153
+ "model_type": "mllama_vision_model",
154
+ "no_repeat_ngram_size": 0,
155
+ "norm_eps": 1e-05,
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_channels": 3,
159
+ "num_global_layers": 8,
160
+ "num_hidden_layers": 32,
161
+ "num_return_sequences": 1,
162
+ "output_attentions": false,
163
+ "output_hidden_states": false,
164
+ "output_scores": false,
165
+ "pad_token_id": null,
166
+ "patch_size": 14,
167
+ "prefix": null,
168
+ "problem_type": null,
169
+ "pruned_heads": {},
170
+ "remove_invalid_values": false,
171
+ "repetition_penalty": 1.0,
172
+ "return_dict": true,
173
+ "return_dict_in_generate": false,
174
+ "sep_token_id": null,
175
+ "supported_aspect_ratios": [
176
+ [
177
+ 1,
178
+ 1
179
+ ],
180
+ [
181
+ 1,
182
+ 2
183
+ ],
184
+ [
185
+ 1,
186
+ 3
187
+ ],
188
+ [
189
+ 1,
190
+ 4
191
+ ],
192
+ [
193
+ 2,
194
+ 1
195
+ ],
196
+ [
197
+ 2,
198
+ 2
199
+ ],
200
+ [
201
+ 3,
202
+ 1
203
+ ],
204
+ [
205
+ 4,
206
+ 1
207
+ ]
208
+ ],
209
+ "suppress_tokens": null,
210
+ "task_specific_params": null,
211
+ "temperature": 1.0,
212
+ "tf_legacy_loss": false,
213
+ "tie_encoder_decoder": false,
214
+ "tie_word_embeddings": true,
215
+ "tokenizer_class": null,
216
+ "top_k": 50,
217
+ "top_p": 1.0,
218
+ "torch_dtype": "bfloat16",
219
+ "torchscript": false,
220
+ "typical_p": 1.0,
221
+ "use_bfloat16": false,
222
+ "vision_output_dim": 7680
223
+ }
224
  }
generation_config.json CHANGED
@@ -9,5 +9,5 @@
9
  "pad_token_id": 128004,
10
  "temperature": 0.6,
11
  "top_p": 0.9,
12
- "transformers_version": "4.46.0.dev0"
13
  }
 
9
  "pad_token_id": 128004,
10
  "temperature": 0.6,
11
  "top_p": 0.9,
12
+ "transformers_version": "4.45.0"
13
  }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d183d799f0476061adc580ccc0a24abba5ab274d610f02e73aff7576e581118c
3
+ size 4992622346
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a7afac7fbc248a8b038709ec3fb5bae4e5588ea84130056c8ed4e5a5144b40
3
+ size 4966251712
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24149e6a1922551067d64d78d8a41ac8393e502d6b64f551a4f73bbacbb5bf90
3
+ size 4915919704
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf17798db8a5de475bc7580706956032533cd7a9dfb588ad8488229c745bbad
3
+ size 4999823980
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656566a9aeee1115ca174c16ea3c51a2839b3a7f14cc349805aa0ef5c7433e7b
3
+ size 1465943128
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff