File size: 1,203 Bytes
d464972 7cb17ce d464972 7cb17ce |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
---
license: apache-2.0
widget:
- text: "<|endoftext|>\nfunction getDateAfterNDay(n){\n return moment().add(n, 'day')\n}\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)
data filter by JavaScript and TypeScript
## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model_type = 'kdf/javascript-docstring-generation'
tokenizer = AutoTokenizer.from_pretrained(model_type)
model = AutoModelForCausalLM.from_pretrained(model_type)
inputs = tokenizer('''<|endoftext|>
function getDateAfterNDay(n){
return moment().add(n, 'day')
}
// 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)
``` |