WaveCut's picture
4c7248025c3e98cefaaae0aaa6fccd3f311a59e0f0359cbc6d13ac9e273a740a
055cce2 verified
|
raw
history blame
954 Bytes
---
license: mit
language:
- multilingual
tags:
- nlp
- mlx
base_model: numind/NuExtract-1.5
pipeline_tag: text-generation
inference: true
---
# mlx-community/numind-NuExtract-1.5-MLX-4bit
The Model [mlx-community/numind-NuExtract-1.5-MLX-4bit](https://huggingface.co/mlx-community/numind-NuExtract-1.5-MLX-4bit) was
converted to MLX format from [numind/NuExtract-1.5](https://huggingface.co/numind/NuExtract-1.5)
using mlx-lm version **0.20.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/numind-NuExtract-1.5-MLX-4bit")
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)
```