README.md

---
library_name: transformers
datasets:
- benchang1110/Guanaco-Taide
- benchang1110/TaiwanChat-Taide
- benchang1110/Belle-Taide
- benchang1110/ChatTaiwan
---

## Model Card for Model ID

This model is the instruction finetuning version of [benchang1110/SmolLM-135M-Taiwan](https://huggingface.co/benchang1110/SmolLM-135M-Taiwan).

## Usage
```python
import torch, transformers  
def generate_response():
    model = transformers.AutoModelForCausalLM.from_pretrained("benchang1110/SmolLM-135M-Taiwan-Instruct-v0.1").to(device)
    tokenizer = transformers.AutoTokenizer.from_pretrained("benchang1110/SmolLM-135M-Taiwan-Instruct-v0.1")
    streamer = transformers.TextStreamer(tokenizer,skip_prompt=True)
    while(1):
        prompt = input('USER:')
        if prompt == "exit":
            break
        print("Assistant: ")
        message = [
           {'content': prompt, 'role': 'user'},
        ]
        formatted_chat = tokenizer.apply_chat_template(conversation,tokenize=True,add_generation_prompt=True,return_tensors='pt').to(device)   
        _ = model.generate(formatted_chat,streamer=streamer,use_cache=True,max_new_tokens=512,do_sample=True)

if __name__ == '__main__':
    device = 'cuda' if torch.cuda.is_available() else 'cpu'
    generate_response()        
```