38 lines
986 B
Markdown
38 lines
986 B
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
license: mit
|
||
|
|
tags:
|
||
|
|
- Explorer SubAgent
|
||
|
|
- Repository Exploration
|
||
|
|
- mlx
|
||
|
|
library_name: transformers
|
||
|
|
base_model: microsoft/FastContext-1.0-4B-SFT
|
||
|
|
---
|
||
|
|
|
||
|
|
# usermma/FastContext-1.0-4B-SFT-mlx-fp16
|
||
|
|
|
||
|
|
The Model [usermma/FastContext-1.0-4B-SFT-mlx-fp16](https://huggingface.co/usermma/FastContext-1.0-4B-SFT-mlx-fp16) was converted to MLX format from [microsoft/FastContext-1.0-4B-SFT](https://huggingface.co/microsoft/FastContext-1.0-4B-SFT) using mlx-lm version **0.31.3**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("usermma/FastContext-1.0-4B-SFT-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)
|
||
|
|
```
|