README.md

---
license: apache-2.0
library_name: peft
tags:
- pytorch
- llama-2
pipeline_tag: text-generation
base_model: meta-llama/Llama-2-7b-chat-hf
---
This model is fine-tuned on [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) using [MedQuAD](https://github.com/abachaa/MedQuAD) (Medical Question Answering Dataset).  
If you are interested how to fine-tune Llama-2 or other LLM models, the [repo](https://github.com/yhyu/fine-tune-llm) will tell you.

## Usage

```python
base_model = "meta-llama/Llama-2-7b-chat-hf"
adapter = 'EdwardYu/llama-2-7b-MedQuAD'

tokenizer = AutoTokenizer.from_pretrained(adapter)

model = AutoModelForCausalLM.from_pretrained(
    base_model,
    load_in_4bit=True,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    quantization_config=BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_compute_dtype=torch.bfloat16,
        bnb_4bit_use_double_quant=True,
        bnb_4bit_quant_type='nf4'
    ),
)
model = PeftModel.from_pretrained(model, adapter)

question = 'What are the side effects or risks of Glucagon?'
inputs = tokenizer(question, return_tensors="pt").to("cuda")
outputs = model.generate(inputs=inputs.input_ids, max_length=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

To run model inference faster, you can load in 16-bits without 4-bit quantization.
```python
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)
```