Instructions to use nvidia/Mistral-NeMo-Minitron-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Mistral-NeMo-Minitron-8B-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nvidia/Mistral-NeMo-Minitron-8B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Mistral-NeMo-Minitron-8B-Base")
model = AutoModelForCausalLM.from_pretrained("nvidia/Mistral-NeMo-Minitron-8B-Base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Mistral-NeMo-Minitron-8B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Mistral-NeMo-Minitron-8B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Mistral-NeMo-Minitron-8B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nvidia/Mistral-NeMo-Minitron-8B-Base

SGLang

How to use nvidia/Mistral-NeMo-Minitron-8B-Base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nvidia/Mistral-NeMo-Minitron-8B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Mistral-NeMo-Minitron-8B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nvidia/Mistral-NeMo-Minitron-8B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Mistral-NeMo-Minitron-8B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nvidia/Mistral-NeMo-Minitron-8B-Base with Docker Model Runner:
```
docker model run hf.co/nvidia/Mistral-NeMo-Minitron-8B-Base
```

How to efficiently use this model?

by deleted - opened Aug 22, 2024

Discussion

deleted

Aug 22, 2024

Hello! I just wanted to know if there was a specific way to use this model please, because for me it's just generating nonsense and repeating itself very quickly... thank you!

andrewwa-nvidia

Aug 22, 2024

•

edited Aug 22, 2024

Try using top_p = 0.95, temperature = 0.7, and frequency_penalty = 0.5 for less repetitive completions. However, typically, the best way to use this model is to fine-tune it/align it to follow instructions.

gghfez

Aug 22, 2024

Hello! I just wanted to know if there was a specific way to use this model please, because for me it's just generating nonsense and repeating itself very quickly... thank you!

This isn't instruction tuned. It's a base model which people will fine tune on top of.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment