49 lines
1.1 KiB
Markdown
49 lines
1.1 KiB
Markdown
|
---
|
||
|
|
base_model: principled-intelligence/scope-guard-4B-q-2601
|
||
|
|
tags:
|
||
|
|
- transformers
|
||
|
|
- safety
|
||
|
|
- guardrails
|
||
|
|
- guardrailing
|
||
|
|
- scope
|
||
|
|
- mlx
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- it
|
||
|
|
- fr
|
||
|
|
- es
|
||
|
|
- de
|
||
|
|
inference: false
|
||
|
|
library_name: mlx
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# ivanfioravanti/scope-guard-4B-q-2601-mlx-bf16
|
||
|
|
|
||
|
|
This model [ivanfioravanti/scope-guard-4B-q-2601-mlx-bf16](https://huggingface.co/ivanfioravanti/scope-guard-4B-q-2601-mlx-bf16) was
|
||
|
|
converted to MLX format from [principled-intelligence/scope-guard-4B-q-2601](https://huggingface.co/principled-intelligence/scope-guard-4B-q-2601)
|
||
|
|
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("ivanfioravanti/scope-guard-4B-q-2601-mlx-bf16")
|
||
|
|
|
||
|
|
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)
|
||
|
|
```
|