laurru01 commited on
Commit
79e416b
·
verified ·
1 Parent(s): 9813be9

Upload Idefics3ForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +201 -0
  2. config.json +283 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - trl
5
+ - sft
6
+ ---
7
+
8
+ # Model Card for Model ID
9
+
10
+ <!-- Provide a quick summary of what the model is/does. -->
11
+
12
+
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ <!-- Provide a longer summary of what this model is. -->
19
+
20
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
21
+
22
+ - **Developed by:** [More Information Needed]
23
+ - **Funded by [optional]:** [More Information Needed]
24
+ - **Shared by [optional]:** [More Information Needed]
25
+ - **Model type:** [More Information Needed]
26
+ - **Language(s) (NLP):** [More Information Needed]
27
+ - **License:** [More Information Needed]
28
+ - **Finetuned from model [optional]:** [More Information Needed]
29
+
30
+ ### Model Sources [optional]
31
+
32
+ <!-- Provide the basic links for the model. -->
33
+
34
+ - **Repository:** [More Information Needed]
35
+ - **Paper [optional]:** [More Information Needed]
36
+ - **Demo [optional]:** [More Information Needed]
37
+
38
+ ## Uses
39
+
40
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
41
+
42
+ ### Direct Use
43
+
44
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
45
+
46
+ [More Information Needed]
47
+
48
+ ### Downstream Use [optional]
49
+
50
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Out-of-Scope Use
55
+
56
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
+
58
+ [More Information Needed]
59
+
60
+ ## Bias, Risks, and Limitations
61
+
62
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ### Recommendations
67
+
68
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
69
+
70
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
+
72
+ ## How to Get Started with the Model
73
+
74
+ Use the code below to get started with the model.
75
+
76
+ [More Information Needed]
77
+
78
+ ## Training Details
79
+
80
+ ### Training Data
81
+
82
+ <!-- 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. -->
83
+
84
+ [More Information Needed]
85
+
86
+ ### Training Procedure
87
+
88
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
+
90
+ #### Preprocessing [optional]
91
+
92
+ [More Information Needed]
93
+
94
+
95
+ #### Training Hyperparameters
96
+
97
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
+
99
+ #### Speeds, Sizes, Times [optional]
100
+
101
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
+
103
+ [More Information Needed]
104
+
105
+ ## Evaluation
106
+
107
+ <!-- This section describes the evaluation protocols and provides the results. -->
108
+
109
+ ### Testing Data, Factors & Metrics
110
+
111
+ #### Testing Data
112
+
113
+ <!-- This should link to a Dataset Card if possible. -->
114
+
115
+ [More Information Needed]
116
+
117
+ #### Factors
118
+
119
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Metrics
124
+
125
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
+
127
+ [More Information Needed]
128
+
129
+ ### Results
130
+
131
+ [More Information Needed]
132
+
133
+ #### Summary
134
+
135
+
136
+
137
+ ## Model Examination [optional]
138
+
139
+ <!-- Relevant interpretability work for the model goes here -->
140
+
141
+ [More Information Needed]
142
+
143
+ ## Environmental Impact
144
+
145
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
+
147
+ 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).
148
+
149
+ - **Hardware Type:** [More Information Needed]
150
+ - **Hours used:** [More Information Needed]
151
+ - **Cloud Provider:** [More Information Needed]
152
+ - **Compute Region:** [More Information Needed]
153
+ - **Carbon Emitted:** [More Information Needed]
154
+
155
+ ## Technical Specifications [optional]
156
+
157
+ ### Model Architecture and Objective
158
+
159
+ [More Information Needed]
160
+
161
+ ### Compute Infrastructure
162
+
163
+ [More Information Needed]
164
+
165
+ #### Hardware
166
+
167
+ [More Information Needed]
168
+
169
+ #### Software
170
+
171
+ [More Information Needed]
172
+
173
+ ## Citation [optional]
174
+
175
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
+
177
+ **BibTeX:**
178
+
179
+ [More Information Needed]
180
+
181
+ **APA:**
182
+
183
+ [More Information Needed]
184
+
185
+ ## Glossary [optional]
186
+
187
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
+
189
+ [More Information Needed]
190
+
191
+ ## More Information [optional]
192
+
193
+ [More Information Needed]
194
+
195
+ ## Model Card Authors [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Contact
200
+
201
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,283 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolVLM-Instruct",
3
+ "architectures": [
4
+ "Idefics3ForConditionalGeneration"
5
+ ],
6
+ "image_seq_len": 81,
7
+ "image_token_id": 49153,
8
+ "model_type": "idefics3",
9
+ "quantization_config": {
10
+ "_load_in_4bit": true,
11
+ "_load_in_8bit": false,
12
+ "bnb_4bit_compute_dtype": "bfloat16",
13
+ "bnb_4bit_quant_storage": "uint8",
14
+ "bnb_4bit_quant_type": "nf4",
15
+ "bnb_4bit_use_double_quant": true,
16
+ "llm_int8_enable_fp32_cpu_offload": false,
17
+ "llm_int8_has_fp16_weight": false,
18
+ "llm_int8_skip_modules": null,
19
+ "llm_int8_threshold": 6.0,
20
+ "load_in_4bit": true,
21
+ "load_in_8bit": false,
22
+ "quant_method": "bitsandbytes"
23
+ },
24
+ "scale_factor": 3,
25
+ "text_config": {
26
+ "_attn_implementation_autoset": false,
27
+ "_flash_attn_2_enabled": true,
28
+ "_name_or_path": "/fsx/m4/experiments/local_experiment_dir/s3_async_temporary_checkpoint_folder/tr_324_opt_400/unwrapped_model",
29
+ "add_cross_attention": false,
30
+ "architectures": [
31
+ "VLlama3ForCausalLM"
32
+ ],
33
+ "attention_bias": false,
34
+ "attention_dropout": 0.0,
35
+ "bad_words_ids": null,
36
+ "begin_suppress_tokens": null,
37
+ "bos_token_id": 0,
38
+ "chunk_size_feed_forward": 0,
39
+ "cross_attention_hidden_size": null,
40
+ "decoder_start_token_id": null,
41
+ "diversity_penalty": 0.0,
42
+ "do_sample": false,
43
+ "early_stopping": false,
44
+ "encoder_no_repeat_ngram_size": 0,
45
+ "eos_token_id": 0,
46
+ "exponential_decay_length_penalty": null,
47
+ "finetuning_task": null,
48
+ "forced_bos_token_id": null,
49
+ "forced_eos_token_id": null,
50
+ "head_dim": 64,
51
+ "hidden_act": "silu",
52
+ "hidden_size": 2048,
53
+ "id2label": {
54
+ "0": "LABEL_0",
55
+ "1": "LABEL_1"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 8192,
59
+ "is_decoder": false,
60
+ "is_encoder_decoder": false,
61
+ "label2id": {
62
+ "LABEL_0": 0,
63
+ "LABEL_1": 1
64
+ },
65
+ "length_penalty": 1.0,
66
+ "max_length": 20,
67
+ "max_position_embeddings": 16384,
68
+ "min_length": 0,
69
+ "mlp_bias": false,
70
+ "model_type": "llama",
71
+ "neftune_noise_alpha": 0.0,
72
+ "no_repeat_ngram_size": 0,
73
+ "num_attention_heads": 32,
74
+ "num_beam_groups": 1,
75
+ "num_beams": 1,
76
+ "num_hidden_layers": 24,
77
+ "num_key_value_heads": 32,
78
+ "num_return_sequences": 1,
79
+ "output_attentions": false,
80
+ "output_hidden_states": false,
81
+ "output_scores": false,
82
+ "pad_token_id": 2,
83
+ "perceiver_config": {
84
+ "_attn_implementation_autoset": false,
85
+ "_name_or_path": "",
86
+ "add_cross_attention": false,
87
+ "architectures": null,
88
+ "attention_dropout": 0.0,
89
+ "bad_words_ids": null,
90
+ "begin_suppress_tokens": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "cross_attention_hidden_size": null,
94
+ "decoder_start_token_id": null,
95
+ "diversity_penalty": 0.0,
96
+ "do_sample": false,
97
+ "early_stopping": false,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "eos_token_id": null,
100
+ "exponential_decay_length_penalty": null,
101
+ "finetuning_task": null,
102
+ "forced_bos_token_id": null,
103
+ "forced_eos_token_id": null,
104
+ "hidden_act": "silu",
105
+ "id2label": {
106
+ "0": "LABEL_0",
107
+ "1": "LABEL_1"
108
+ },
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
+ "min_length": 0,
118
+ "model_type": "vllama3",
119
+ "no_repeat_ngram_size": 0,
120
+ "num_beam_groups": 1,
121
+ "num_beams": 1,
122
+ "num_key_value_heads": 1,
123
+ "num_return_sequences": 1,
124
+ "output_attentions": false,
125
+ "output_hidden_states": false,
126
+ "output_scores": false,
127
+ "pad_token_id": null,
128
+ "prefix": null,
129
+ "problem_type": null,
130
+ "pruned_heads": {},
131
+ "qk_layer_norms_perceiver": false,
132
+ "remove_invalid_values": false,
133
+ "repetition_penalty": 1.0,
134
+ "resampler_depth": 6,
135
+ "resampler_head_dim": 96,
136
+ "resampler_n_heads": 16,
137
+ "resampler_n_latents": 64,
138
+ "return_dict": true,
139
+ "return_dict_in_generate": false,
140
+ "sep_token_id": null,
141
+ "suppress_tokens": null,
142
+ "task_specific_params": null,
143
+ "temperature": 1.0,
144
+ "tf_legacy_loss": false,
145
+ "tie_encoder_decoder": false,
146
+ "tie_word_embeddings": true,
147
+ "tokenizer_class": null,
148
+ "top_k": 50,
149
+ "top_p": 1.0,
150
+ "torch_dtype": null,
151
+ "torchscript": false,
152
+ "transformers_version": "4.46.0",
153
+ "typical_p": 1.0,
154
+ "use_bfloat16": false
155
+ },
156
+ "prefix": null,
157
+ "pretraining_tp": 1,
158
+ "problem_type": null,
159
+ "pruned_heads": {},
160
+ "qk_layer_norms": false,
161
+ "remove_invalid_values": false,
162
+ "repetition_penalty": 1.0,
163
+ "return_dict": true,
164
+ "return_dict_in_generate": false,
165
+ "rms_norm_eps": 1e-05,
166
+ "rope_scaling": null,
167
+ "rope_theta": 273768.0,
168
+ "sep_token_id": null,
169
+ "suppress_tokens": null,
170
+ "task_specific_params": null,
171
+ "temperature": 1.0,
172
+ "tf_legacy_loss": false,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": false,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": "bfloat16",
179
+ "torchscript": false,
180
+ "typical_p": 1.0,
181
+ "use_bfloat16": false,
182
+ "use_cache": true,
183
+ "use_resampler": false,
184
+ "vocab_size": 49155
185
+ },
186
+ "tie_word_embeddings": false,
187
+ "torch_dtype": "float32",
188
+ "transformers.js_config": {
189
+ "dtype": {
190
+ "decoder_model_merged": "q4",
191
+ "embed_tokens": "auto",
192
+ "vision_encoder": "auto"
193
+ },
194
+ "kv_cache_dtype": {
195
+ "fp16": "float16",
196
+ "q4f16": "float16"
197
+ }
198
+ },
199
+ "transformers_version": "4.46.2",
200
+ "use_cache": true,
201
+ "vision_config": {
202
+ "_attn_implementation_autoset": false,
203
+ "_name_or_path": "",
204
+ "add_cross_attention": false,
205
+ "architectures": null,
206
+ "attention_dropout": 0.0,
207
+ "bad_words_ids": null,
208
+ "begin_suppress_tokens": null,
209
+ "bos_token_id": null,
210
+ "chunk_size_feed_forward": 0,
211
+ "cross_attention_hidden_size": null,
212
+ "decoder_start_token_id": null,
213
+ "diversity_penalty": 0.0,
214
+ "do_sample": false,
215
+ "early_stopping": false,
216
+ "encoder_no_repeat_ngram_size": 0,
217
+ "eos_token_id": null,
218
+ "exponential_decay_length_penalty": null,
219
+ "finetuning_task": null,
220
+ "forced_bos_token_id": null,
221
+ "forced_eos_token_id": null,
222
+ "hidden_act": "gelu_pytorch_tanh",
223
+ "hidden_size": 1152,
224
+ "id2label": {
225
+ "0": "LABEL_0",
226
+ "1": "LABEL_1"
227
+ },
228
+ "image_size": 384,
229
+ "initializer_range": 0.02,
230
+ "intermediate_size": 4304,
231
+ "is_decoder": false,
232
+ "is_encoder_decoder": false,
233
+ "label2id": {
234
+ "LABEL_0": 0,
235
+ "LABEL_1": 1
236
+ },
237
+ "layer_norm_eps": 1e-06,
238
+ "length_penalty": 1.0,
239
+ "max_image_size": {
240
+ "longest_edge": 384
241
+ },
242
+ "max_length": 20,
243
+ "min_length": 0,
244
+ "model_type": "idefics3",
245
+ "no_repeat_ngram_size": 0,
246
+ "num_attention_heads": 16,
247
+ "num_beam_groups": 1,
248
+ "num_beams": 1,
249
+ "num_channels": 3,
250
+ "num_hidden_layers": 27,
251
+ "num_return_sequences": 1,
252
+ "output_attentions": false,
253
+ "output_hidden_states": false,
254
+ "output_scores": false,
255
+ "pad_token_id": null,
256
+ "patch_size": 14,
257
+ "prefix": null,
258
+ "problem_type": null,
259
+ "pruned_heads": {},
260
+ "remove_invalid_values": false,
261
+ "repetition_penalty": 1.0,
262
+ "return_dict": true,
263
+ "return_dict_in_generate": false,
264
+ "sep_token_id": null,
265
+ "size": {
266
+ "longest_edge": 1920
267
+ },
268
+ "suppress_tokens": null,
269
+ "task_specific_params": null,
270
+ "temperature": 1.0,
271
+ "tf_legacy_loss": false,
272
+ "tie_encoder_decoder": false,
273
+ "tie_word_embeddings": false,
274
+ "tokenizer_class": null,
275
+ "top_k": 50,
276
+ "top_p": 1.0,
277
+ "torch_dtype": null,
278
+ "torchscript": false,
279
+ "typical_p": 1.0,
280
+ "use_bfloat16": false
281
+ },
282
+ "vocab_size": 49155
283
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 49154,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.46.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1324f389f6d3bcb9bace4e8bf4549e6a910d6f63f9c72729717ab3a53d3cd3b0
3
+ size 1510488542