danielhanchen commited on
Commit
6f08469
1 Parent(s): 681fe35

Upload MllamaForConditionalGeneration

Browse files
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,285 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "vision_model.transformer.layers.0.mlp",
23
+ "vision_model.transformer.layers.1.mlp",
24
+ "vision_model.transformer.layers.2.mlp",
25
+ "vision_model.transformer.layers.3.mlp",
26
+ "vision_model.transformer.layers.4.mlp",
27
+ "vision_model.transformer.layers.5.mlp",
28
+ "vision_model.transformer.layers.6.mlp",
29
+ "vision_model.transformer.layers.7.mlp",
30
+ "vision_model.transformer.layers.8.mlp",
31
+ "vision_model.transformer.layers.9.mlp",
32
+ "vision_model.transformer.layers.10.mlp",
33
+ "vision_model.transformer.layers.11.mlp",
34
+ "vision_model.transformer.layers.12.mlp",
35
+ "vision_model.transformer.layers.13.mlp",
36
+ "vision_model.transformer.layers.14.mlp",
37
+ "vision_model.transformer.layers.15.mlp",
38
+ "vision_model.transformer.layers.16.mlp",
39
+ "vision_model.transformer.layers.17.mlp",
40
+ "vision_model.transformer.layers.18.mlp",
41
+ "vision_model.transformer.layers.19.mlp",
42
+ "vision_model.transformer.layers.20.mlp",
43
+ "vision_model.transformer.layers.21.mlp",
44
+ "vision_model.transformer.layers.22.mlp",
45
+ "vision_model.transformer.layers.23.mlp",
46
+ "vision_model.transformer.layers.24.mlp",
47
+ "vision_model.transformer.layers.25.mlp",
48
+ "vision_model.transformer.layers.26.mlp",
49
+ "vision_model.transformer.layers.27.mlp",
50
+ "vision_model.transformer.layers.28.mlp",
51
+ "vision_model.transformer.layers.29.mlp",
52
+ "vision_model.transformer.layers.30.mlp",
53
+ "vision_model.transformer.layers.31.mlp",
54
+ "vision_model.global_transformer.layers.0.mlp",
55
+ "vision_model.global_transformer.layers.1.mlp",
56
+ "vision_model.global_transformer.layers.2.mlp",
57
+ "vision_model.global_transformer.layers.3.mlp",
58
+ "vision_model.global_transformer.layers.4.mlp",
59
+ "vision_model.global_transformer.layers.5.mlp"
60
+ ],
61
+ "llm_int8_threshold": 6.0,
62
+ "load_in_4bit": true,
63
+ "load_in_8bit": false,
64
+ "quant_method": "bitsandbytes"
65
+ },
66
+ "text_config": {
67
+ "_attn_implementation_autoset": false,
68
+ "_name_or_path": "",
69
+ "add_cross_attention": false,
70
+ "architectures": null,
71
+ "bad_words_ids": null,
72
+ "begin_suppress_tokens": null,
73
+ "bos_token_id": 128000,
74
+ "chunk_size_feed_forward": 0,
75
+ "cross_attention_hidden_size": null,
76
+ "cross_attention_layers": [
77
+ 3,
78
+ 8,
79
+ 13,
80
+ 18,
81
+ 23,
82
+ 28,
83
+ 33,
84
+ 38
85
+ ],
86
+ "decoder_start_token_id": null,
87
+ "diversity_penalty": 0.0,
88
+ "do_sample": false,
89
+ "dropout": 0,
90
+ "early_stopping": false,
91
+ "encoder_no_repeat_ngram_size": 0,
92
+ "eos_token_id": [
93
+ 128001,
94
+ 128008,
95
+ 128009
96
+ ],
97
+ "exponential_decay_length_penalty": null,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "hidden_act": "silu",
102
+ "hidden_size": 4096,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 14336,
109
+ "is_decoder": false,
110
+ "is_encoder_decoder": false,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1
114
+ },
115
+ "length_penalty": 1.0,
116
+ "max_length": 20,
117
+ "max_position_embeddings": 131072,
118
+ "min_length": 0,
119
+ "model_type": "mllama_text_model",
120
+ "no_repeat_ngram_size": 0,
121
+ "num_attention_heads": 32,
122
+ "num_beam_groups": 1,
123
+ "num_beams": 1,
124
+ "num_hidden_layers": 40,
125
+ "num_key_value_heads": 8,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": 128004,
131
+ "prefix": null,
132
+ "problem_type": null,
133
+ "pruned_heads": {},
134
+ "remove_invalid_values": false,
135
+ "repetition_penalty": 1.0,
136
+ "return_dict": true,
137
+ "return_dict_in_generate": false,
138
+ "rms_norm_eps": 1e-05,
139
+ "rope_scaling": {
140
+ "factor": 8.0,
141
+ "high_freq_factor": 4.0,
142
+ "low_freq_factor": 1.0,
143
+ "original_max_position_embeddings": 8192,
144
+ "rope_type": "llama3"
145
+ },
146
+ "rope_theta": 500000.0,
147
+ "sep_token_id": null,
148
+ "suppress_tokens": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tf_legacy_loss": false,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": false,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": "bfloat16",
158
+ "torchscript": false,
159
+ "typical_p": 1.0,
160
+ "use_bfloat16": false,
161
+ "use_cache": true,
162
+ "vocab_size": 128256
163
+ },
164
+ "torch_dtype": "bfloat16",
165
+ "transformers_version": "4.46.3",
166
+ "unsloth_fixed": true,
167
+ "vision_config": {
168
+ "_attn_implementation_autoset": false,
169
+ "_name_or_path": "",
170
+ "add_cross_attention": false,
171
+ "architectures": null,
172
+ "attention_heads": 16,
173
+ "bad_words_ids": null,
174
+ "begin_suppress_tokens": null,
175
+ "bos_token_id": null,
176
+ "chunk_size_feed_forward": 0,
177
+ "cross_attention_hidden_size": null,
178
+ "decoder_start_token_id": null,
179
+ "diversity_penalty": 0.0,
180
+ "do_sample": false,
181
+ "early_stopping": false,
182
+ "encoder_no_repeat_ngram_size": 0,
183
+ "eos_token_id": null,
184
+ "exponential_decay_length_penalty": null,
185
+ "finetuning_task": null,
186
+ "forced_bos_token_id": null,
187
+ "forced_eos_token_id": null,
188
+ "hidden_act": "gelu",
189
+ "hidden_size": 1280,
190
+ "id2label": {
191
+ "0": "LABEL_0",
192
+ "1": "LABEL_1"
193
+ },
194
+ "image_size": 560,
195
+ "initializer_range": 0.02,
196
+ "intermediate_layers_indices": [
197
+ 3,
198
+ 7,
199
+ 15,
200
+ 23,
201
+ 30
202
+ ],
203
+ "intermediate_size": 5120,
204
+ "is_decoder": false,
205
+ "is_encoder_decoder": false,
206
+ "label2id": {
207
+ "LABEL_0": 0,
208
+ "LABEL_1": 1
209
+ },
210
+ "length_penalty": 1.0,
211
+ "max_length": 20,
212
+ "max_num_tiles": 4,
213
+ "min_length": 0,
214
+ "model_type": "mllama_vision_model",
215
+ "no_repeat_ngram_size": 0,
216
+ "norm_eps": 1e-05,
217
+ "num_beam_groups": 1,
218
+ "num_beams": 1,
219
+ "num_channels": 3,
220
+ "num_global_layers": 8,
221
+ "num_hidden_layers": 32,
222
+ "num_return_sequences": 1,
223
+ "output_attentions": false,
224
+ "output_hidden_states": false,
225
+ "output_scores": false,
226
+ "pad_token_id": null,
227
+ "patch_size": 14,
228
+ "prefix": null,
229
+ "problem_type": null,
230
+ "pruned_heads": {},
231
+ "remove_invalid_values": false,
232
+ "repetition_penalty": 1.0,
233
+ "return_dict": true,
234
+ "return_dict_in_generate": false,
235
+ "sep_token_id": null,
236
+ "supported_aspect_ratios": [
237
+ [
238
+ 1,
239
+ 1
240
+ ],
241
+ [
242
+ 1,
243
+ 2
244
+ ],
245
+ [
246
+ 1,
247
+ 3
248
+ ],
249
+ [
250
+ 1,
251
+ 4
252
+ ],
253
+ [
254
+ 2,
255
+ 1
256
+ ],
257
+ [
258
+ 2,
259
+ 2
260
+ ],
261
+ [
262
+ 3,
263
+ 1
264
+ ],
265
+ [
266
+ 4,
267
+ 1
268
+ ]
269
+ ],
270
+ "suppress_tokens": null,
271
+ "task_specific_params": null,
272
+ "temperature": 1.0,
273
+ "tf_legacy_loss": false,
274
+ "tie_encoder_decoder": false,
275
+ "tie_word_embeddings": true,
276
+ "tokenizer_class": null,
277
+ "top_k": 50,
278
+ "top_p": 1.0,
279
+ "torch_dtype": "bfloat16",
280
+ "torchscript": false,
281
+ "typical_p": 1.0,
282
+ "use_bfloat16": false,
283
+ "vision_output_dim": 7680
284
+ }
285
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "pad_token_id": 128004,
10
+ "temperature": 0.6,
11
+ "top_p": 0.9,
12
+ "transformers_version": "4.46.3"
13
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df871653461fc0de46e87c4ee385e4aa992867ca244439ca7ba52798299e64e5
3
+ size 4990770382
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd435129de51a39511eef736db475e561c794a0011910e1f96cf5c5ebd844f8d
3
+ size 2974910239
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff