50 lines
1.0 KiB
Markdown
50 lines
1.0 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- 'no'
|
||
|
|
- nb
|
||
|
|
- nn
|
||
|
|
- en
|
||
|
|
tags:
|
||
|
|
- llama
|
||
|
|
- notram
|
||
|
|
- norwegian
|
||
|
|
- bokmål
|
||
|
|
- nynorsk
|
||
|
|
- multilingual
|
||
|
|
- conversational
|
||
|
|
- text-generation
|
||
|
|
- mlx
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
license: llama3.1
|
||
|
|
base_model: NbAiLab/nb-notram-llama-3.1-8b-instruct
|
||
|
|
library_name: mlx
|
||
|
|
---
|
||
|
|
|
||
|
|
# SlimGroove/nb-notram-llama-3.1-8b-instruct-mlx
|
||
|
|
|
||
|
|
This model [SlimGroove/nb-notram-llama-3.1-8b-instruct-mlx](https://huggingface.co/SlimGroove/nb-notram-llama-3.1-8b-instruct-mlx) was
|
||
|
|
converted to MLX format from [NbAiLab/nb-notram-llama-3.1-8b-instruct](https://huggingface.co/NbAiLab/nb-notram-llama-3.1-8b-instruct)
|
||
|
|
using mlx-lm version **0.29.1**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("SlimGroove/nb-notram-llama-3.1-8b-instruct-mlx")
|
||
|
|
|
||
|
|
prompt = "hello"
|
||
|
|
|
||
|
|
if tokenizer.chat_template is not None:
|
||
|
|
messages = [{"role": "user", "content": prompt}]
|
||
|
|
prompt = tokenizer.apply_chat_template(
|
||
|
|
messages, add_generation_prompt=True
|
||
|
|
)
|
||
|
|
|
||
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||
|
|
```
|