Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +46 -0
- config.json +39 -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 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags: autotrain
|
3 |
+
language: unk
|
4 |
+
widget:
|
5 |
+
- text: "I love AutoTrain 🤗"
|
6 |
+
datasets:
|
7 |
+
- Amalq/autotrain-data-smm4h_large_roberta_clean
|
8 |
+
co2_eq_emissions: 9.123490454955585
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Binary Classification
|
14 |
+
- Model ID: 874027878
|
15 |
+
- CO2 Emissions (in grams): 9.123490454955585
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
|
19 |
+
- Loss: 0.35724225640296936
|
20 |
+
- Accuracy: 0.8571428571428571
|
21 |
+
- Precision: 0.7637362637362637
|
22 |
+
- Recall: 0.8910256410256411
|
23 |
+
- AUC: 0.9267555361305361
|
24 |
+
- F1: 0.8224852071005917
|
25 |
+
|
26 |
+
## Usage
|
27 |
+
|
28 |
+
You can use cURL to access this model:
|
29 |
+
|
30 |
+
```
|
31 |
+
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/Amalq/autotrain-smm4h_large_roberta_clean-874027878
|
32 |
+
```
|
33 |
+
|
34 |
+
Or Python API:
|
35 |
+
|
36 |
+
```
|
37 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
38 |
+
|
39 |
+
model = AutoModelForSequenceClassification.from_pretrained("Amalq/autotrain-smm4h_large_roberta_clean-874027878", use_auth_token=True)
|
40 |
+
|
41 |
+
tokenizer = AutoTokenizer.from_pretrained("Amalq/autotrain-smm4h_large_roberta_clean-874027878", use_auth_token=True)
|
42 |
+
|
43 |
+
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
|
44 |
+
|
45 |
+
outputs = model(**inputs)
|
46 |
+
```
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "0",
|
16 |
+
"1": "1"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 4096,
|
20 |
+
"label2id": {
|
21 |
+
"0": 0,
|
22 |
+
"1": 1
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-05,
|
25 |
+
"max_length": 256,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "roberta",
|
28 |
+
"num_attention_heads": 16,
|
29 |
+
"num_hidden_layers": 24,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"padding": "max_length",
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.15.0",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50265
|
39 |
+
}
|
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 sha256:505d3aac4944a5e19d85920d3d8699ad8e712e441c7411c53c9187ef9df13354
|
3 |
+
size 1421611309
|
sample_input.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be1151196e79a38b572362fd9f31c4fd722e18dbed8adf749c24e90c262912a3
|
3 |
+
size 5110
|
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
|
|