README.md

---
base_model: tslim1/acemath-convfinqa
library_name: transformers
model_name: acemath-convfinqa
tags:
- generated_from_trainer
- trl
- sft
- mlx
- mlx-my-repo
licence: license
---

# tslim1/acemath-convfinqa-mlx-8Bit

The Model [tslim1/acemath-convfinqa-mlx-8Bit](https://huggingface.co/tslim1/acemath-convfinqa-mlx-8Bit) was converted to MLX format from [tslim1/acemath-convfinqa](https://huggingface.co/tslim1/acemath-convfinqa) using mlx-lm version **0.26.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("tslim1/acemath-convfinqa-mlx-8Bit")

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)
```