README.md

---
language:
- en
library_name: transformers
license: apache-2.0
tags:
- unsloth
- transformers
- llama
- llama2
- llama-2
- chat
- mlx
base_model: unsloth/llama-2-7b-chat
---

# shashikanth-a/llama-2-7b-chat-4bit

The Model [shashikanth-a/llama-2-7b-chat-4bit](https://huggingface.co/shashikanth-a/llama-2-7b-chat-4bit) was converted to MLX format from [unsloth/llama-2-7b-chat](https://huggingface.co/unsloth/llama-2-7b-chat) using mlx-lm version **0.19.3**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("shashikanth-a/llama-2-7b-chat-4bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```