Instructions to use TencentARC/Mistral_Pro_8B_v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TencentARC/Mistral_Pro_8B_v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="TencentARC/Mistral_Pro_8B_v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TencentARC/Mistral_Pro_8B_v0.1")
model = AutoModelForCausalLM.from_pretrained("TencentARC/Mistral_Pro_8B_v0.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TencentARC/Mistral_Pro_8B_v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TencentARC/Mistral_Pro_8B_v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TencentARC/Mistral_Pro_8B_v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TencentARC/Mistral_Pro_8B_v0.1

SGLang

How to use TencentARC/Mistral_Pro_8B_v0.1 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 "TencentARC/Mistral_Pro_8B_v0.1" \
    --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": "TencentARC/Mistral_Pro_8B_v0.1",
		"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 "TencentARC/Mistral_Pro_8B_v0.1" \
        --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": "TencentARC/Mistral_Pro_8B_v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TencentARC/Mistral_Pro_8B_v0.1 with Docker Model Runner:
```
docker model run hf.co/TencentARC/Mistral_Pro_8B_v0.1
```

GGUF format?

by toranb - opened Feb 27, 2024

Discussion

toranb

Feb 27, 2024

Anyone else interested in a f16 GGUF of this model?

toranb

Feb 28, 2024

•

edited Mar 3, 2024

With the latest llama cpp I was able to generate a GGUF quick with this command after downloading the files

git clone --depth=1 https://github.com/ggerganov/llama.cpp.git cpp
cd cpp
make clean && LLAMA_CUBLAS=1 make -j

python3 -m venv env
source env/bin/activate
pip install -r requirements/requirements-convert.txt

python3 convert.py Mistral_Pro_8B_v0.1 --outfile mistralpro.gguf --outtype f16

Here is a 3min video of the process end to end

https://vimeo.com/918854010

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