30 lines
780 B
Markdown
30 lines
780 B
Markdown
|
---
|
||
|
|
base_model: nvidia/Llama-3.1-Minitron-4B-Width-Base
|
||
|
|
datasets:
|
||
|
|
- teknium/OpenHermes-2.5
|
||
|
|
library_name: transformers
|
||
|
|
license: other
|
||
|
|
license_name: nvidia-open-model-license
|
||
|
|
license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- mlx
|
||
|
|
---
|
||
|
|
|
||
|
|
# psx7/llama4B
|
||
|
|
|
||
|
|
The Model [psx7/llama4B](https://huggingface.co/psx7/llama4B) was converted to MLX format from [rasyosef/Llama-3.1-Minitron-4B-Chat](https://huggingface.co/rasyosef/Llama-3.1-Minitron-4B-Chat) using mlx-lm version **0.18.1**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("psx7/llama4B")
|
||
|
|
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
||
|
|
```
|