|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: |
|
- Qwen/Qwen2.5-Coder-3B-Instruct |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
Generates and Edits minimal multi-file python code. Right now consistently generates upto 2-3 files with a runner.sh bash script that orchestrates the file. Maintains the PEP-8 style. |
|
|
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
- **Developed by:** Reshinth Adithyan |
|
- **License:** Apache 2.0 |
|
|
|
### Model Sources [optional] |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** https://github.com/reshinthadithyan/repo-level-code/tree/main |
|
### Usage |
|
```python |
|
import torch |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
import fire |
|
|
|
|
|
def main(model_path:str="./models_dir/repo_coder_v1"): |
|
input_prompt = "###Instruction: {prompt}".format(prompt="Generate a small python repo for matplotlib to visualize timeseries data to read from timeseries.csv file using pandas.") |
|
|
|
def load_model(model_path): |
|
""" |
|
Load the model and tokenizer from the specified path. |
|
""" |
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto") |
|
return model, tokenizer |
|
|
|
|
|
model, tokenizer = load_model(model_path) |
|
print(f"Loaded model from {model_path}.") |
|
|
|
input = tokenizer(input_prompt, return_tensors="pt").to(model.device) |
|
print(input) |
|
with torch.no_grad(): |
|
output = model.generate(**input, max_length=1024, do_sample=True, temperature=0.9, top_p=0.95, top_k=50) |
|
output_text = tokenizer.decode(output[0], skip_special_tokens=True) |
|
print(f"Generated text: {output_text}") |
|
|
|
if __name__ == "__main__": |
|
fire.Fire(main) |
|
``` |
