Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +32 -0
- config.json +177 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- sample_input.pkl +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -25,3 +25,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags: autotrain
|
3 |
+
language: unk
|
4 |
+
widget:
|
5 |
+
- text: "I love AutoTrain 🤗"
|
6 |
+
datasets:
|
7 |
+
- ouiame/autotrain-data-Robertatogpt2
|
8 |
+
co2_eq_emissions: 611.0958349328379
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Summarization
|
14 |
+
- Model ID: 995132944
|
15 |
+
- CO2 Emissions (in grams): 611.0958349328379
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
|
19 |
+
- Loss: 3.8850467205047607
|
20 |
+
- Rouge1: 16.6344
|
21 |
+
- Rouge2: 2.9899
|
22 |
+
- RougeL: 13.5872
|
23 |
+
- RougeLsum: 13.9042
|
24 |
+
- Gen Len: 20.0
|
25 |
+
|
26 |
+
## Usage
|
27 |
+
|
28 |
+
You can use cURL to access this model:
|
29 |
+
|
30 |
+
```
|
31 |
+
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/ouiame/autotrain-Robertatogpt2-995132944
|
32 |
+
```
|
config.json
ADDED
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"architectures": [
|
4 |
+
"EncoderDecoderModel"
|
5 |
+
],
|
6 |
+
"decoder": {
|
7 |
+
"_name_or_path": "gpt2",
|
8 |
+
"activation_function": "gelu_new",
|
9 |
+
"add_cross_attention": true,
|
10 |
+
"architectures": [
|
11 |
+
"GPT2LMHeadModel"
|
12 |
+
],
|
13 |
+
"attn_pdrop": 0.1,
|
14 |
+
"bad_words_ids": null,
|
15 |
+
"bos_token_id": 50256,
|
16 |
+
"chunk_size_feed_forward": 0,
|
17 |
+
"cross_attention_hidden_size": null,
|
18 |
+
"decoder_start_token_id": null,
|
19 |
+
"diversity_penalty": 0.0,
|
20 |
+
"do_sample": false,
|
21 |
+
"early_stopping": false,
|
22 |
+
"embd_pdrop": 0.1,
|
23 |
+
"encoder_no_repeat_ngram_size": 0,
|
24 |
+
"eos_token_id": 50256,
|
25 |
+
"finetuning_task": null,
|
26 |
+
"forced_bos_token_id": null,
|
27 |
+
"forced_eos_token_id": null,
|
28 |
+
"id2label": {
|
29 |
+
"0": "LABEL_0",
|
30 |
+
"1": "LABEL_1"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"is_decoder": true,
|
34 |
+
"is_encoder_decoder": false,
|
35 |
+
"label2id": {
|
36 |
+
"LABEL_0": 0,
|
37 |
+
"LABEL_1": 1
|
38 |
+
},
|
39 |
+
"layer_norm_epsilon": 1e-05,
|
40 |
+
"length_penalty": 1.0,
|
41 |
+
"max_length": 20,
|
42 |
+
"min_length": 0,
|
43 |
+
"model_type": "gpt2",
|
44 |
+
"n_ctx": 1024,
|
45 |
+
"n_embd": 768,
|
46 |
+
"n_head": 12,
|
47 |
+
"n_inner": null,
|
48 |
+
"n_layer": 12,
|
49 |
+
"n_positions": 1024,
|
50 |
+
"no_repeat_ngram_size": 0,
|
51 |
+
"num_beam_groups": 1,
|
52 |
+
"num_beams": 1,
|
53 |
+
"num_return_sequences": 1,
|
54 |
+
"output_attentions": false,
|
55 |
+
"output_hidden_states": false,
|
56 |
+
"output_scores": false,
|
57 |
+
"pad_token_id": null,
|
58 |
+
"prefix": null,
|
59 |
+
"problem_type": null,
|
60 |
+
"pruned_heads": {},
|
61 |
+
"remove_invalid_values": false,
|
62 |
+
"reorder_and_upcast_attn": false,
|
63 |
+
"repetition_penalty": 1.0,
|
64 |
+
"resid_pdrop": 0.1,
|
65 |
+
"return_dict": true,
|
66 |
+
"return_dict_in_generate": false,
|
67 |
+
"scale_attn_by_inverse_layer_idx": false,
|
68 |
+
"scale_attn_weights": true,
|
69 |
+
"sep_token_id": null,
|
70 |
+
"summary_activation": null,
|
71 |
+
"summary_first_dropout": 0.1,
|
72 |
+
"summary_proj_to_labels": true,
|
73 |
+
"summary_type": "cls_index",
|
74 |
+
"summary_use_proj": true,
|
75 |
+
"task_specific_params": {
|
76 |
+
"text-generation": {
|
77 |
+
"do_sample": true,
|
78 |
+
"max_length": 50
|
79 |
+
}
|
80 |
+
},
|
81 |
+
"temperature": 1.0,
|
82 |
+
"tie_encoder_decoder": false,
|
83 |
+
"tie_word_embeddings": true,
|
84 |
+
"tokenizer_class": null,
|
85 |
+
"top_k": 50,
|
86 |
+
"top_p": 1.0,
|
87 |
+
"torch_dtype": null,
|
88 |
+
"torchscript": false,
|
89 |
+
"transformers_version": "4.15.0",
|
90 |
+
"use_bfloat16": false,
|
91 |
+
"use_cache": true,
|
92 |
+
"vocab_size": 50257
|
93 |
+
},
|
94 |
+
"decoder_start_token_id": 0,
|
95 |
+
"encoder": {
|
96 |
+
"_name_or_path": "roberta-base",
|
97 |
+
"add_cross_attention": false,
|
98 |
+
"architectures": [
|
99 |
+
"RobertaForMaskedLM"
|
100 |
+
],
|
101 |
+
"attention_probs_dropout_prob": 0.1,
|
102 |
+
"bad_words_ids": null,
|
103 |
+
"bos_token_id": 0,
|
104 |
+
"chunk_size_feed_forward": 0,
|
105 |
+
"classifier_dropout": null,
|
106 |
+
"cross_attention_hidden_size": null,
|
107 |
+
"decoder_start_token_id": null,
|
108 |
+
"diversity_penalty": 0.0,
|
109 |
+
"do_sample": false,
|
110 |
+
"early_stopping": false,
|
111 |
+
"encoder_no_repeat_ngram_size": 0,
|
112 |
+
"eos_token_id": 2,
|
113 |
+
"finetuning_task": null,
|
114 |
+
"forced_bos_token_id": null,
|
115 |
+
"forced_eos_token_id": null,
|
116 |
+
"hidden_act": "gelu",
|
117 |
+
"hidden_dropout_prob": 0.1,
|
118 |
+
"hidden_size": 768,
|
119 |
+
"id2label": {
|
120 |
+
"0": "LABEL_0",
|
121 |
+
"1": "LABEL_1"
|
122 |
+
},
|
123 |
+
"initializer_range": 0.02,
|
124 |
+
"intermediate_size": 3072,
|
125 |
+
"is_decoder": false,
|
126 |
+
"is_encoder_decoder": false,
|
127 |
+
"label2id": {
|
128 |
+
"LABEL_0": 0,
|
129 |
+
"LABEL_1": 1
|
130 |
+
},
|
131 |
+
"layer_norm_eps": 1e-05,
|
132 |
+
"length_penalty": 1.0,
|
133 |
+
"max_length": 20,
|
134 |
+
"max_position_embeddings": 514,
|
135 |
+
"min_length": 0,
|
136 |
+
"model_type": "roberta",
|
137 |
+
"no_repeat_ngram_size": 0,
|
138 |
+
"num_attention_heads": 12,
|
139 |
+
"num_beam_groups": 1,
|
140 |
+
"num_beams": 1,
|
141 |
+
"num_hidden_layers": 12,
|
142 |
+
"num_return_sequences": 1,
|
143 |
+
"output_attentions": false,
|
144 |
+
"output_hidden_states": false,
|
145 |
+
"output_scores": false,
|
146 |
+
"pad_token_id": 1,
|
147 |
+
"position_embedding_type": "absolute",
|
148 |
+
"prefix": null,
|
149 |
+
"problem_type": null,
|
150 |
+
"pruned_heads": {},
|
151 |
+
"remove_invalid_values": false,
|
152 |
+
"repetition_penalty": 1.0,
|
153 |
+
"return_dict": true,
|
154 |
+
"return_dict_in_generate": false,
|
155 |
+
"sep_token_id": null,
|
156 |
+
"task_specific_params": null,
|
157 |
+
"temperature": 1.0,
|
158 |
+
"tie_encoder_decoder": false,
|
159 |
+
"tie_word_embeddings": true,
|
160 |
+
"tokenizer_class": null,
|
161 |
+
"top_k": 50,
|
162 |
+
"top_p": 1.0,
|
163 |
+
"torch_dtype": null,
|
164 |
+
"torchscript": false,
|
165 |
+
"transformers_version": "4.15.0",
|
166 |
+
"type_vocab_size": 1,
|
167 |
+
"use_bfloat16": false,
|
168 |
+
"use_cache": true,
|
169 |
+
"vocab_size": 50265
|
170 |
+
},
|
171 |
+
"eos_token_id": 2,
|
172 |
+
"is_encoder_decoder": true,
|
173 |
+
"model_type": "encoder-decoder",
|
174 |
+
"pad_token_id": 1,
|
175 |
+
"torch_dtype": "float32",
|
176 |
+
"transformers_version": null
|
177 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00bcd0f2b333e22a1d4dc851316f4b8d61da020c8a05ceda76b405536bf8d900
|
3 |
+
size 1135171497
|
sample_input.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da1cfc4c2cae754c7ce94558ec7e6310f2c5a24c1428310a473a683493534c7e
|
3 |
+
size 55047
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "AutoTrain", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|