martinsinnona commited on
Commit
f891bf7
1 Parent(s): e22a56d

Upload Pix2StructForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +201 -0
  2. config.json +3 -153
  3. generation_config.json +1 -1
  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 CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_commit_hash": "8a3e42420c3465a9e98441bdf84fe70b59d57cb8",
3
  "_name_or_path": "google/matcha-base",
4
  "architectures": [
5
  "Pix2StructForConditionalGeneration"
@@ -13,168 +12,19 @@
13
  "model_type": "pix2struct",
14
  "pad_token_id": 0,
15
  "text_config": {
16
- "_name_or_path": "",
17
- "add_cross_attention": false,
18
- "architectures": null,
19
- "bad_words_ids": null,
20
- "begin_suppress_tokens": null,
21
- "bos_token_id": null,
22
- "chunk_size_feed_forward": 0,
23
- "cross_attention_hidden_size": null,
24
- "d_ff": 2048,
25
- "d_kv": 64,
26
- "decoder_start_token_id": 0,
27
- "dense_act_fn": "gelu_new",
28
- "diversity_penalty": 0.0,
29
- "do_sample": false,
30
- "dropout_rate": 0.1,
31
- "early_stopping": false,
32
  "encoder_hidden_size": 768,
33
- "encoder_no_repeat_ngram_size": 0,
34
- "eos_token_id": 1,
35
- "exponential_decay_length_penalty": null,
36
- "finetuning_task": null,
37
- "forced_bos_token_id": null,
38
- "forced_eos_token_id": null,
39
- "hidden_size": 768,
40
- "id2label": {
41
- "0": "LABEL_0",
42
- "1": "LABEL_1"
43
- },
44
- "initializer_factor": 1.0,
45
  "initializer_range": 0.02,
46
- "is_decoder": true,
47
- "is_encoder_decoder": false,
48
- "label2id": {
49
- "LABEL_0": 0,
50
- "LABEL_1": 1
51
- },
52
- "layer_norm_epsilon": 1e-06,
53
- "length_penalty": 1.0,
54
- "max_length": 20,
55
- "min_length": 0,
56
- "model_type": "pix2struct_text_model",
57
- "no_repeat_ngram_size": 0,
58
- "num_beam_groups": 1,
59
- "num_beams": 1,
60
- "num_heads": 12,
61
- "num_layers": 12,
62
- "num_return_sequences": 1,
63
- "output_attentions": false,
64
- "output_hidden_states": false,
65
- "output_scores": false,
66
- "pad_token_id": 0,
67
- "prefix": null,
68
- "problem_type": null,
69
- "pruned_heads": {},
70
- "relative_attention_max_distance": 128,
71
- "relative_attention_num_buckets": 32,
72
- "remove_invalid_values": false,
73
- "repetition_penalty": 1.0,
74
- "return_dict": true,
75
- "return_dict_in_generate": false,
76
- "sep_token_id": null,
77
- "suppress_tokens": null,
78
- "task_specific_params": null,
79
- "temperature": 1.0,
80
- "tf_legacy_loss": false,
81
- "tie_encoder_decoder": false,
82
- "tie_word_embeddings": false,
83
- "tokenizer_class": null,
84
- "top_k": 50,
85
- "top_p": 1.0,
86
- "torch_dtype": null,
87
- "torchscript": false,
88
- "transformers_version": "4.29.2",
89
- "typical_p": 1.0,
90
- "use_bfloat16": false,
91
- "use_cache": false,
92
- "vocab_size": 50244
93
  },
94
  "tie_word_embeddings": false,
95
  "torch_dtype": "float32",
96
- "transformers_version": null,
97
  "vision_config": {
98
- "_name_or_path": "",
99
- "add_cross_attention": false,
100
- "architectures": null,
101
- "attention_dropout": 0.0,
102
- "bad_words_ids": null,
103
- "begin_suppress_tokens": null,
104
- "bos_token_id": null,
105
- "chunk_size_feed_forward": 0,
106
- "cross_attention_hidden_size": null,
107
- "d_ff": 2048,
108
- "d_kv": 64,
109
- "decoder_start_token_id": null,
110
- "dense_act_fn": "gelu_new",
111
- "diversity_penalty": 0.0,
112
- "do_sample": false,
113
- "dropout_rate": 0.0,
114
- "early_stopping": false,
115
- "encoder_no_repeat_ngram_size": 0,
116
- "eos_token_id": null,
117
- "exponential_decay_length_penalty": null,
118
- "finetuning_task": null,
119
- "forced_bos_token_id": null,
120
- "forced_eos_token_id": null,
121
- "hidden_size": 768,
122
- "id2label": {
123
- "0": "LABEL_0",
124
- "1": "LABEL_1"
125
- },
126
- "initializer_factor": 1.0,
127
  "initializer_range": 0.02,
128
- "is_decoder": false,
129
- "is_encoder_decoder": false,
130
- "label2id": {
131
- "LABEL_0": 0,
132
- "LABEL_1": 1
133
- },
134
  "layer_norm_bias": false,
135
- "layer_norm_eps": 1e-06,
136
- "length_penalty": 1.0,
137
- "max_length": 20,
138
- "min_length": 0,
139
  "model_type": "pix2struct_vision_model",
140
- "no_repeat_ngram_size": 0,
141
- "num_attention_heads": 12,
142
- "num_beam_groups": 1,
143
- "num_beams": 1,
144
  "num_channels": 3,
145
- "num_hidden_layers": 12,
146
- "num_return_sequences": 1,
147
- "output_attentions": false,
148
- "output_hidden_states": false,
149
- "output_scores": false,
150
- "pad_token_id": null,
151
- "patch_embed_hidden_size": 768,
152
  "patch_size": 16,
153
- "prefix": null,
154
- "problem_type": null,
155
- "projection_dim": 768,
156
- "pruned_heads": {},
157
- "relative_attention_max_distance": 128,
158
- "relative_attention_num_buckets": 32,
159
- "remove_invalid_values": false,
160
- "repetition_penalty": 1.0,
161
- "return_dict": true,
162
- "return_dict_in_generate": false,
163
- "sep_token_id": null,
164
- "seq_len": 4096,
165
- "suppress_tokens": null,
166
- "task_specific_params": null,
167
- "temperature": 1.0,
168
- "tf_legacy_loss": false,
169
- "tie_encoder_decoder": false,
170
- "tie_word_embeddings": true,
171
- "tokenizer_class": null,
172
- "top_k": 50,
173
- "top_p": 1.0,
174
- "torch_dtype": null,
175
- "torchscript": false,
176
- "transformers_version": "4.29.2",
177
- "typical_p": 1.0,
178
- "use_bfloat16": false
179
  }
180
  }
 
1
  {
 
2
  "_name_or_path": "google/matcha-base",
3
  "architectures": [
4
  "Pix2StructForConditionalGeneration"
 
12
  "model_type": "pix2struct",
13
  "pad_token_id": 0,
14
  "text_config": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "encoder_hidden_size": 768,
 
 
 
 
 
 
 
 
 
 
 
 
16
  "initializer_range": 0.02,
17
+ "model_type": "pix2struct_text_model"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  },
19
  "tie_word_embeddings": false,
20
  "torch_dtype": "float32",
21
+ "transformers_version": "4.38.1",
22
  "vision_config": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "initializer_range": 0.02,
 
 
 
 
 
 
24
  "layer_norm_bias": false,
 
 
 
 
25
  "model_type": "pix2struct_vision_model",
 
 
 
 
26
  "num_channels": 3,
 
 
 
 
 
 
 
27
  "patch_size": 16,
28
+ "projection_dim": 768
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  }
30
  }
generation_config.json CHANGED
@@ -3,6 +3,6 @@
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.29.2",
7
  "use_cache": false
8
  }
 
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.38.1",
7
  "use_cache": false
8
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a00e596f0e2529af1c34c15c84b491bdc3b974d7f05d6523432c74d80851c7
3
+ size 1129177976