40 lines
838 B
Markdown
40 lines
838 B
Markdown
|
---
|
||
|
|
base_model: unsloth/gemma-2-2b-it
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
library_name: transformers
|
||
|
|
license: gemma
|
||
|
|
tags:
|
||
|
|
- unsloth
|
||
|
|
- transformers
|
||
|
|
- gemma2
|
||
|
|
- gemma
|
||
|
|
- mlx
|
||
|
|
---
|
||
|
|
|
||
|
|
# TeunS/Geert
|
||
|
|
|
||
|
|
The Model [TeunS/Geert](https://huggingface.co/TeunS/Geert) was converted to MLX format from [unsloth/gemma-2-2b-it](https://huggingface.co/unsloth/gemma-2-2b-it) using mlx-lm version **0.19.3**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("TeunS/Geert")
|
||
|
|
|
||
|
|
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)
|
||
|
|
```
|