prince-canuma's picture
ad9b7cbdddaf216d6a7068c0f5535ed38df50e6c73140d873ada6723226bfdaa
898c12f verified
|
raw
history blame
1.14 kB
---
base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
datasets:
- nvidia/HelpSteer2
language:
- en
library_name: transformers
license: llama3.1
pipeline_tag: text-generation
tags:
- nvidia
- llama3.1
- mlx
inference: false
fine-tuning: false
---
# mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit
The Model [mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit](https://huggingface.co/mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit) was converted to MLX format from [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) using mlx-lm version **0.19.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit")
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)
```