huseinzol05 commited on
Commit
b46d219
1 Parent(s): d39777c

Upload MM_LLMs

Browse files
Files changed (4) hide show
  1. README.md +201 -0
  2. config.json +302 -0
  3. generation_config.json +4 -0
  4. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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]
200
+
201
+
config.json ADDED
@@ -0,0 +1,302 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vision-alignment-tinyllama-siglip-large/checkpoint-7300",
3
+ "architectures": [
4
+ "MM_LLMs"
5
+ ],
6
+ "image_config": {
7
+ "_name_or_path": "google/siglip-large-patch16-384",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "SiglipModel"
11
+ ],
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_factor": 1.0,
32
+ "is_decoder": false,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "min_length": 0,
41
+ "model_type": "siglip",
42
+ "no_repeat_ngram_size": 0,
43
+ "num_beam_groups": 1,
44
+ "num_beams": 1,
45
+ "num_return_sequences": 1,
46
+ "output_attentions": false,
47
+ "output_hidden_states": false,
48
+ "output_scores": false,
49
+ "pad_token_id": null,
50
+ "prefix": null,
51
+ "problem_type": null,
52
+ "pruned_heads": {},
53
+ "remove_invalid_values": false,
54
+ "repetition_penalty": 1.0,
55
+ "return_dict": true,
56
+ "return_dict_in_generate": false,
57
+ "sep_token_id": null,
58
+ "suppress_tokens": null,
59
+ "task_specific_params": null,
60
+ "temperature": 1.0,
61
+ "text_config": {
62
+ "_name_or_path": "",
63
+ "add_cross_attention": false,
64
+ "architectures": null,
65
+ "attention_dropout": 0.0,
66
+ "bad_words_ids": null,
67
+ "begin_suppress_tokens": null,
68
+ "bos_token_id": 49406,
69
+ "chunk_size_feed_forward": 0,
70
+ "cross_attention_hidden_size": null,
71
+ "decoder_start_token_id": null,
72
+ "diversity_penalty": 0.0,
73
+ "do_sample": false,
74
+ "early_stopping": false,
75
+ "encoder_no_repeat_ngram_size": 0,
76
+ "eos_token_id": 49407,
77
+ "exponential_decay_length_penalty": null,
78
+ "finetuning_task": null,
79
+ "forced_bos_token_id": null,
80
+ "forced_eos_token_id": null,
81
+ "hidden_act": "gelu_pytorch_tanh",
82
+ "hidden_size": 1024,
83
+ "id2label": {
84
+ "0": "LABEL_0",
85
+ "1": "LABEL_1"
86
+ },
87
+ "intermediate_size": 4096,
88
+ "is_decoder": false,
89
+ "is_encoder_decoder": false,
90
+ "label2id": {
91
+ "LABEL_0": 0,
92
+ "LABEL_1": 1
93
+ },
94
+ "layer_norm_eps": 1e-06,
95
+ "length_penalty": 1.0,
96
+ "max_length": 20,
97
+ "max_position_embeddings": 64,
98
+ "min_length": 0,
99
+ "model_type": "siglip_text_model",
100
+ "no_repeat_ngram_size": 0,
101
+ "num_attention_heads": 16,
102
+ "num_beam_groups": 1,
103
+ "num_beams": 1,
104
+ "num_hidden_layers": 24,
105
+ "num_return_sequences": 1,
106
+ "output_attentions": false,
107
+ "output_hidden_states": false,
108
+ "output_scores": false,
109
+ "pad_token_id": 1,
110
+ "prefix": null,
111
+ "problem_type": null,
112
+ "pruned_heads": {},
113
+ "remove_invalid_values": false,
114
+ "repetition_penalty": 1.0,
115
+ "return_dict": true,
116
+ "return_dict_in_generate": false,
117
+ "sep_token_id": null,
118
+ "suppress_tokens": null,
119
+ "task_specific_params": null,
120
+ "temperature": 1.0,
121
+ "tf_legacy_loss": false,
122
+ "tie_encoder_decoder": false,
123
+ "tie_word_embeddings": true,
124
+ "tokenizer_class": null,
125
+ "top_k": 50,
126
+ "top_p": 1.0,
127
+ "torch_dtype": null,
128
+ "torchscript": false,
129
+ "typical_p": 1.0,
130
+ "use_bfloat16": false,
131
+ "vocab_size": 32000
132
+ },
133
+ "tf_legacy_loss": false,
134
+ "tie_encoder_decoder": false,
135
+ "tie_word_embeddings": true,
136
+ "tokenizer_class": null,
137
+ "top_k": 50,
138
+ "top_p": 1.0,
139
+ "torch_dtype": "float32",
140
+ "torchscript": false,
141
+ "typical_p": 1.0,
142
+ "use_bfloat16": false,
143
+ "vision_config": {
144
+ "_name_or_path": "",
145
+ "add_cross_attention": false,
146
+ "architectures": null,
147
+ "attention_dropout": 0.0,
148
+ "bad_words_ids": null,
149
+ "begin_suppress_tokens": null,
150
+ "bos_token_id": null,
151
+ "chunk_size_feed_forward": 0,
152
+ "cross_attention_hidden_size": null,
153
+ "decoder_start_token_id": null,
154
+ "diversity_penalty": 0.0,
155
+ "do_sample": false,
156
+ "early_stopping": false,
157
+ "encoder_no_repeat_ngram_size": 0,
158
+ "eos_token_id": null,
159
+ "exponential_decay_length_penalty": null,
160
+ "finetuning_task": null,
161
+ "forced_bos_token_id": null,
162
+ "forced_eos_token_id": null,
163
+ "hidden_act": "gelu_pytorch_tanh",
164
+ "hidden_size": 1024,
165
+ "id2label": {
166
+ "0": "LABEL_0",
167
+ "1": "LABEL_1"
168
+ },
169
+ "image_size": 384,
170
+ "intermediate_size": 4096,
171
+ "is_decoder": false,
172
+ "is_encoder_decoder": false,
173
+ "label2id": {
174
+ "LABEL_0": 0,
175
+ "LABEL_1": 1
176
+ },
177
+ "layer_norm_eps": 1e-06,
178
+ "length_penalty": 1.0,
179
+ "max_length": 20,
180
+ "min_length": 0,
181
+ "model_type": "siglip_vision_model",
182
+ "no_repeat_ngram_size": 0,
183
+ "num_attention_heads": 16,
184
+ "num_beam_groups": 1,
185
+ "num_beams": 1,
186
+ "num_channels": 3,
187
+ "num_hidden_layers": 24,
188
+ "num_return_sequences": 1,
189
+ "output_attentions": false,
190
+ "output_hidden_states": false,
191
+ "output_scores": false,
192
+ "pad_token_id": null,
193
+ "patch_size": 16,
194
+ "prefix": null,
195
+ "problem_type": null,
196
+ "pruned_heads": {},
197
+ "remove_invalid_values": false,
198
+ "repetition_penalty": 1.0,
199
+ "return_dict": true,
200
+ "return_dict_in_generate": false,
201
+ "sep_token_id": null,
202
+ "suppress_tokens": null,
203
+ "task_specific_params": null,
204
+ "temperature": 1.0,
205
+ "tf_legacy_loss": false,
206
+ "tie_encoder_decoder": false,
207
+ "tie_word_embeddings": true,
208
+ "tokenizer_class": null,
209
+ "top_k": 50,
210
+ "top_p": 1.0,
211
+ "torch_dtype": null,
212
+ "torchscript": false,
213
+ "typical_p": 1.0,
214
+ "use_bfloat16": false
215
+ }
216
+ },
217
+ "llm_config": {
218
+ "_name_or_path": "mesolitica/malaysian-tinyllama-1.1b-16k-instructions-v3",
219
+ "add_cross_attention": false,
220
+ "architectures": [
221
+ "LlamaForCausalLM"
222
+ ],
223
+ "attention_bias": false,
224
+ "attention_dropout": 0.0,
225
+ "bad_words_ids": null,
226
+ "begin_suppress_tokens": null,
227
+ "bos_token_id": 1,
228
+ "chunk_size_feed_forward": 0,
229
+ "cross_attention_hidden_size": null,
230
+ "decoder_start_token_id": null,
231
+ "diversity_penalty": 0.0,
232
+ "do_sample": false,
233
+ "early_stopping": false,
234
+ "encoder_no_repeat_ngram_size": 0,
235
+ "eos_token_id": 2,
236
+ "exponential_decay_length_penalty": null,
237
+ "finetuning_task": null,
238
+ "forced_bos_token_id": null,
239
+ "forced_eos_token_id": null,
240
+ "hidden_act": "silu",
241
+ "hidden_size": 2048,
242
+ "id2label": {
243
+ "0": "LABEL_0",
244
+ "1": "LABEL_1"
245
+ },
246
+ "initializer_range": 0.02,
247
+ "intermediate_size": 5632,
248
+ "is_decoder": false,
249
+ "is_encoder_decoder": false,
250
+ "label2id": {
251
+ "LABEL_0": 0,
252
+ "LABEL_1": 1
253
+ },
254
+ "length_penalty": 1.0,
255
+ "max_length": 20,
256
+ "max_position_embeddings": 32768,
257
+ "min_length": 0,
258
+ "model_type": "llama",
259
+ "no_repeat_ngram_size": 0,
260
+ "num_attention_heads": 32,
261
+ "num_beam_groups": 1,
262
+ "num_beams": 1,
263
+ "num_hidden_layers": 22,
264
+ "num_key_value_heads": 4,
265
+ "num_return_sequences": 1,
266
+ "output_attentions": false,
267
+ "output_hidden_states": false,
268
+ "output_scores": false,
269
+ "pad_token_id": null,
270
+ "prefix": null,
271
+ "pretraining_tp": 1,
272
+ "problem_type": null,
273
+ "pruned_heads": {},
274
+ "remove_invalid_values": false,
275
+ "repetition_penalty": 1.0,
276
+ "return_dict": true,
277
+ "return_dict_in_generate": false,
278
+ "rms_norm_eps": 1e-05,
279
+ "rope_scaling": null,
280
+ "rope_theta": 10000.0,
281
+ "sep_token_id": null,
282
+ "suppress_tokens": null,
283
+ "task_specific_params": null,
284
+ "temperature": 1.0,
285
+ "tf_legacy_loss": false,
286
+ "tie_encoder_decoder": false,
287
+ "tie_word_embeddings": false,
288
+ "tokenizer_class": null,
289
+ "top_k": 50,
290
+ "top_p": 1.0,
291
+ "torch_dtype": "bfloat16",
292
+ "torchscript": false,
293
+ "typical_p": 1.0,
294
+ "use_bfloat16": false,
295
+ "use_cache": true,
296
+ "vocab_size": 32004
297
+ },
298
+ "model_type": "mm_llms",
299
+ "torch_dtype": "bfloat16",
300
+ "transformers_version": "4.37.2",
301
+ "vision_select_layer": -2
302
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.2"
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d8481aef0cebbf2869b27f18637919c7401631e7e11860f5ddbf82916beac0
3
+ size 3517809868