39 lines
892 B
Markdown
39 lines
892 B
Markdown
---
|
|
license: apache-2.0
|
|
library_name: mlx
|
|
tags:
|
|
- language
|
|
- granite-4.1
|
|
- mlx
|
|
base_model: ibm-granite/granite-4.1-8b
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
# theophilusowiti/granite4.1-8b-Q4
|
|
|
|
This model [theophilusowiti/granite4.1-8b-Q4](https://huggingface.co/theophilusowiti/granite4.1-8b-Q4) was
|
|
converted to MLX format from [ibm-granite/granite-4.1-8b](https://huggingface.co/ibm-granite/granite-4.1-8b)
|
|
using mlx-lm version **0.31.3**.
|
|
|
|
## Use with mlx
|
|
|
|
```bash
|
|
pip install mlx-lm
|
|
```
|
|
|
|
```python
|
|
from mlx_lm import load, generate
|
|
|
|
model, tokenizer = load("theophilusowiti/granite4.1-8b-Q4")
|
|
|
|
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)
|
|
```
|