|
--- |
|
license: apache-2.0 |
|
widget: |
|
- text: "<|endoftext|>\ndef load_excel(path):\n return pd.read_excel(path)\n# docstring\n\"\"\"" |
|
--- |
|
|
|
## Basic info |
|
|
|
model based [Salesforce/codegen-350M-mono](https://huggingface.co/Salesforce/codegen-350M-mono) |
|
|
|
fine-tuned with data [codeparrot/github-code-clean](https://huggingface.co/datasets/codeparrot/github-code-clean) |
|
|
|
## Usage |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
model_type = 'kdf/python-docstring-generation' |
|
tokenizer = AutoTokenizer.from_pretrained(model_type) |
|
model = AutoModelForCausalLM.from_pretrained(model_type) |
|
|
|
inputs = tokenizer('''<|endoftext|> |
|
def load_excel(path): |
|
return pd.read_excel(path) |
|
|
|
# docstring |
|
"""''', return_tensors='pt') |
|
|
|
doc_max_length = 128 |
|
|
|
generated_ids = model.generate( |
|
**inputs, |
|
max_length=inputs.input_ids.shape[1] + doc_max_length, |
|
do_sample=False, |
|
return_dict_in_generate=True, |
|
num_return_sequences=1, |
|
output_scores=True, |
|
pad_token_id=50256, |
|
eos_token_id=50256 # <|endoftext|> |
|
) |
|
|
|
ret = tokenizer.decode(generated_ids.sequences[0], skip_special_tokens=False) |
|
print(ret) |
|
|
|
``` |
