Commit
•
ab62cf0
1
Parent(s):
475f597
Upload Pix2StructForConditionalGeneration
Browse files- README.md +199 -0
- config.json +3 -153
- generation_config.json +1 -1
- model.safetensors +3 -0
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
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 |
-
"
|
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":
|
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 |
-
"
|
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": "4.39.3",
|
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.
|
7 |
"use_cache": false
|
8 |
}
|
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.39.3",
|
7 |
"use_cache": false
|
8 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:064cfa15725dbe410eb595184536b7c64e325de976b836c14c84440002504fcd
|
3 |
+
size 1129177976
|