4f23fbc1b2
Model: sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview-MLX Source: Original Platform
40 lines
1.1 KiB
Markdown
40 lines
1.1 KiB
Markdown
---
|
|
base_model: sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
- mlx
|
|
---
|
|
> [!WARNING]
|
|
> **Tinkering in progress!**
|
|
>
|
|
> This model is a work in progress and likely is not yet returning valid output.
|
|
# sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview-MLX
|
|
|
|
The Model [sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview-MLX](https://huggingface.co/sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview-MLX) was
|
|
converted to MLX format from [sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview](https://huggingface.co/sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview)
|
|
using mlx-lm version **0.22.0**.
|
|
|
|
## Use with mlx
|
|
|
|
```bash
|
|
pip install mlx-lm
|
|
```
|
|
|
|
```python
|
|
from mlx_lm import load, generate
|
|
|
|
model, tokenizer = load("sealad886/FuseO1-DeepSeekR1-Qwen2.5-Coder-7B-Preview-MLX")
|
|
|
|
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)
|
|
```
|