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
```

Context Length

by Sao10K - opened Aug 22, 2024

Discussion

Sao10K

Aug 22, 2024

•

edited Aug 22, 2024

Hmm, is the decreased context length (8k tokens from model config) a side effect of the training done after pruning? This would have been pretty nice if it retained its long context abilities.

pmolchanov

NVIDIA org Aug 23, 2024

This is our plan, to work on longer context. We will update as soon as get results. Hopefully will be able to release the model with 128k context.

pmolchanov changed discussion status to closed Aug 23, 2024

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