Instructions to use kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a with Transformers:

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

pipe = pipeline("text-generation", model="kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a")
model = AutoModelForMultimodalLM.from_pretrained("kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a

SGLang

How to use kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a 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 "kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a" \
    --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": "kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a",
		"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 "kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a" \
        --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": "kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a with Docker Model Runner:
```
docker model run hf.co/kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This model is exclusively available to Pro subscribers of The Kaitchup. To gain access, subscribe to The Kaitchup Pro, subscribe here. If you are already a Pro subscriber, you will find your access token on this page.

Model Details

This is nvidia/Mistral-NeMo-Minitron-8B-Base with a vocabulary reduced to 32k entries using the Minivoc (with average embeddings) approach. The model has been created, tested, and evaluated by The Kaitchup.

All the details about the Minivoc approach and evaluation in this article: Introducing Minivoc: Faster and Memory-Efficient LLMs Through Vocabulary Reduction

Developed by: The Kaitchup
Language(s) (NLP): English

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Collection including kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a

Minivoc

Collection

7 items • Updated Dec 6, 2024