41 lines
1013 B
Markdown
41 lines
1013 B
Markdown
---
|
|
license: apache-2.0
|
|
base_model: sweepai/sweep-next-edit-v2-7B
|
|
tags:
|
|
- code
|
|
- autocomplete
|
|
- next-edit-prediction
|
|
- dpo
|
|
- mlx
|
|
- mlx-my-repo
|
|
language:
|
|
- en
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
# Cyanophyte/sweep-next-edit-v2-7B-mlx-fp16
|
|
|
|
The Model [Cyanophyte/sweep-next-edit-v2-7B-mlx-fp16](https://huggingface.co/Cyanophyte/sweep-next-edit-v2-7B-mlx-fp16) was converted to MLX format from [sweepai/sweep-next-edit-v2-7B](https://huggingface.co/sweepai/sweep-next-edit-v2-7B) using mlx-lm version **0.31.2**.
|
|
|
|
## Use with mlx
|
|
|
|
```bash
|
|
pip install mlx-lm
|
|
```
|
|
|
|
```python
|
|
from mlx_lm import load, generate
|
|
|
|
model, tokenizer = load("Cyanophyte/sweep-next-edit-v2-7B-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)
|
|
```
|