|
--- |
|
tags: |
|
- pytorch |
|
- trl |
|
- sft |
|
- mlx |
|
inference: false |
|
--- |
|
|
|
# mlx-community/omost-llama-3-8b-mlx-8bit |
|
|
|
The Model [mlx-community/omost-llama-3-8b-mlx-8bit](https://huggingface.co/mlx-community/omost-llama-3-8b-mlx-8bit) was converted to MLX format from [lllyasviel/omost-llama-3-8b](https://huggingface.co/lllyasviel/omost-llama-3-8b) using mlx-lm version **0.14.3**. |
|
|
|
## Intended Usage |
|
|
|
Model finetuned specifically for lllyasviel's [Omost project](https://github.com/lllyasviel/Omost) |
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("mlx-community/omost-llama-3-8b-mlx-8bit") |
|
response = generate(model, tokenizer, prompt="hello", verbose=True) |
|
``` |
|
|
