---
base_model: Kortix/FastApply-1.5B-v1.0
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
- fast-apply
- instant-apply
- mlx
- mlx-my-repo
---

# dangerusslee/FastApply-1.5B-v1.0-mlx-fp16

The Model [dangerusslee/FastApply-1.5B-v1.0-mlx-fp16](https://huggingface.co/dangerusslee/FastApply-1.5B-v1.0-mlx-fp16) was converted to MLX format from [Kortix/FastApply-1.5B-v1.0](https://huggingface.co/Kortix/FastApply-1.5B-v1.0) using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("dangerusslee/FastApply-1.5B-v1.0-mlx-fp16")

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)
```