Instructions to use athirdpath/NeuralPivot-Mistral-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/NeuralPivot-Mistral-13B with Transformers:

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

pipe = pipeline("text-generation", model="athirdpath/NeuralPivot-Mistral-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athirdpath/NeuralPivot-Mistral-13B")
model = AutoModelForCausalLM.from_pretrained("athirdpath/NeuralPivot-Mistral-13B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use athirdpath/NeuralPivot-Mistral-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athirdpath/NeuralPivot-Mistral-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athirdpath/NeuralPivot-Mistral-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/athirdpath/NeuralPivot-Mistral-13B

SGLang

How to use athirdpath/NeuralPivot-Mistral-13B 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 "athirdpath/NeuralPivot-Mistral-13B" \
    --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": "athirdpath/NeuralPivot-Mistral-13B",
		"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 "athirdpath/NeuralPivot-Mistral-13B" \
        --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": "athirdpath/NeuralPivot-Mistral-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use athirdpath/NeuralPivot-Mistral-13B with Docker Model Runner:
```
docker model run hf.co/athirdpath/NeuralPivot-Mistral-13B
```

What is this?

by bdambrosio - opened Dec 14, 2023

Discussion

bdambrosio

Dec 14, 2023

Can you tell us more about it?
I'm intrigued, but reluctant to download yet another model without more info about it...
thanks!

athirdpath

Owner Dec 14, 2023

An attempt at expanding Mistral 7b. The model is okay, but not any better than my 20b L2 models. If you want a bigger version of Mistral, I'm working on 17b merges right now that are better than this (Lambda-17b. Kappa-17b) but that's still an open line of research.

Generally, you can assume all of my models are an experiment on LLM structure and latent space exploration unless they are in my deployment collection.

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