README.md

---
base_model: luzimu/WebGen-LM-7B
datasets:
- luzimu/WebGen-Bench
language:
- en
library_name: mlx
license: mit
metrics:
- accuracy
pipeline_tag: text-generation
tags:
- code-generation
- mlx
---

# cyan2k/WebGen-LM-7B-mlx-8bit

This model [cyan2k/WebGen-LM-7B-mlx-8bit](https://huggingface.co/cyan2k/WebGen-LM-7B-mlx-8bit) was
converted to MLX format from [luzimu/WebGen-LM-7B](https://huggingface.co/luzimu/WebGen-LM-7B)
using mlx-lm version **0.27.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("cyan2k/WebGen-LM-7B-mlx-8bit")

prompt = "hello"

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

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