Vecteus-v1-4bit / README.md
osuta's picture
5442cc5f7f52a04aa8d2668501f40a44509451dfe318baf43eb670888699b39c
550d122 verified
|
raw
history blame
645 Bytes
---
language:
- en
- ja
license: apache-2.0
library_name: transformers
tags:
- finetuned
- mlx
pipeline_tag: text-generation
---
# mlx-community/Vecteus-v1-4bit
The Model [mlx-community/Vecteus-v1-4bit](https://huggingface.co/mlx-community/Vecteus-v1-4bit) was converted to MLX format from [Local-Novel-LLM-project/Vecteus-v1](https://huggingface.co/Local-Novel-LLM-project/Vecteus-v1) using mlx-lm version **0.14.2**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Vecteus-v1-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```