42 lines
907 B
Markdown
42 lines
907 B
Markdown
|
|
---
|
||
|
|
library_name: mlx
|
||
|
|
license: llama2
|
||
|
|
datasets:
|
||
|
|
- uonlp/CulturaX
|
||
|
|
language:
|
||
|
|
- uk
|
||
|
|
- en
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
base_model: tartuNLP/Llama-2-7b-Ukrainian
|
||
|
|
tags:
|
||
|
|
- mlx
|
||
|
|
---
|
||
|
|
|
||
|
|
# mlx-community/Llama-2-7b-Ukrainian
|
||
|
|
|
||
|
|
This model [mlx-community/Llama-2-7b-Ukrainian](https://huggingface.co/mlx-community/Llama-2-7b-Ukrainian) was
|
||
|
|
converted to MLX format from [tartuNLP/Llama-2-7b-Ukrainian](https://huggingface.co/tartuNLP/Llama-2-7b-Ukrainian)
|
||
|
|
using mlx-lm version **0.28.4**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("mlx-community/Llama-2-7b-Ukrainian")
|
||
|
|
|
||
|
|
prompt = "hello"
|
||
|
|
|
||
|
|
if tokenizer.chat_template is not None:
|
||
|
|
messages = [{"role": "user", "content": prompt}]
|
||
|
|
prompt = tokenizer.apply_chat_template(
|
||
|
|
messages, add_generation_prompt=True
|
||
|
|
)
|
||
|
|
|
||
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||
|
|
```
|