54 lines
1.0 KiB
Markdown
54 lines
1.0 KiB
Markdown
|
---
|
||
|
|
tags:
|
||
|
|
- chat
|
||
|
|
- mlx
|
||
|
|
base_model: Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
language:
|
||
|
|
- multilingual
|
||
|
|
- en
|
||
|
|
- es
|
||
|
|
- fr
|
||
|
|
- pt
|
||
|
|
- it
|
||
|
|
- ar
|
||
|
|
- ko
|
||
|
|
- id
|
||
|
|
- ru
|
||
|
|
- vi
|
||
|
|
- de
|
||
|
|
- th
|
||
|
|
- ja
|
||
|
|
- zh
|
||
|
|
library_name: mlx
|
||
|
|
license: mit
|
||
|
|
---
|
||
|
|
|
||
|
|
# mlx-community/JOSIE-1.1-4B-Thinking-bfloat16
|
||
|
|
|
||
|
|
This model [mlx-community/JOSIE-1.1-4B-Thinking-bfloat16](https://huggingface.co/mlx-community/JOSIE-1.1-4B-Thinking-bfloat16) was
|
||
|
|
converted to MLX format from [Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking](https://huggingface.co/Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking)
|
||
|
|
using mlx-lm version **0.31.0**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("mlx-community/JOSIE-1.1-4B-Thinking-bfloat16")
|
||
|
|
|
||
|
|
prompt = "hello"
|
||
|
|
|
||
|
|
if tokenizer.chat_template is not None:
|
||
|
|
messages = [{"role": "user", "content": prompt}]
|
||
|
|
prompt = tokenizer.apply_chat_template(
|
||
|
|
messages, add_generation_prompt=True, return_dict=False,
|
||
|
|
)
|
||
|
|
|
||
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||
|
|
```
|