Update README.md
Browse files
README.md
CHANGED
@@ -3,3 +3,44 @@ license: apache-2.0
|
|
3 |
widget:
|
4 |
- text: "<|endoftext|>\ndef load_excel(path):\n return pd.read_excel(path)\n# docstring\n\"\"\""
|
5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
widget:
|
4 |
- text: "<|endoftext|>\ndef load_excel(path):\n return pd.read_excel(path)\n# docstring\n\"\"\""
|
5 |
---
|
6 |
+
|
7 |
+
## Basic info
|
8 |
+
|
9 |
+
model based [Salesforce/codegen-350M-mono](https://huggingface.co/Salesforce/codegen-350M-mono)
|
10 |
+
|
11 |
+
fine-tuned with data [codeparrot/github-code-clean](https://huggingface.co/datasets/codeparrot/github-code-clean)
|
12 |
+
|
13 |
+
## Usage
|
14 |
+
|
15 |
+
```python
|
16 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
17 |
+
|
18 |
+
model_type = 'kdf/python-docstring-generation'
|
19 |
+
tokenizer = AutoTokenizer.from_pretrained(model_type)
|
20 |
+
model = AutoModelForCausalLM.from_pretrained(model_type)
|
21 |
+
|
22 |
+
inputs = tokenizer('''<|endoftext|>
|
23 |
+
def load_excel(path):
|
24 |
+
return pd.read_excel(path)
|
25 |
+
|
26 |
+
# docstring
|
27 |
+
"""''', return_tensors='pt')
|
28 |
+
|
29 |
+
doc_max_length = 128
|
30 |
+
|
31 |
+
generated_ids = model.generate(
|
32 |
+
**inputs,
|
33 |
+
max_length=inputs.input_ids.shape[1] + doc_max_length,
|
34 |
+
do_sample=False,
|
35 |
+
return_dict_in_generate=True,
|
36 |
+
top_p = 0.9,
|
37 |
+
num_return_sequences=1,
|
38 |
+
output_scores=True,
|
39 |
+
pad_token_id=50256,
|
40 |
+
eos_token_id=50256 # <|endoftext|>
|
41 |
+
)
|
42 |
+
|
43 |
+
ret = tokenizer.decode(generated_ids.sequences[0], skip_special_tokens=False)
|
44 |
+
print(ret)
|
45 |
+
|
46 |
+
```
|