36 lines
808 B
Markdown
36 lines
808 B
Markdown
|
---
|
||
|
|
base_model: nvidia/Nemotron-Orchestrator-8B
|
||
|
|
library_name: mlx
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- mlx
|
||
|
|
---
|
||
|
|
|
||
|
|
# trast-ai/Orchestrator-8B-MLX
|
||
|
|
|
||
|
|
This model [trast-ai/Orchestrator-8B-MLX](https://huggingface.co/trast-ai/Orchestrator-8B-MLX) was
|
||
|
|
converted to MLX format from [nvidia/Orchestrator-8B](https://huggingface.co/nvidia/Orchestrator-8B)
|
||
|
|
using mlx-lm version **0.28.3**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("trast-ai/Orchestrator-8B-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)
|
||
|
|
```
|