Instructions to use peiyi9979/math-shepherd-mistral-7b-prm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use peiyi9979/math-shepherd-mistral-7b-prm with Transformers:

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

pipe = pipeline("text-generation", model="peiyi9979/math-shepherd-mistral-7b-prm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("peiyi9979/math-shepherd-mistral-7b-prm")
model = AutoModelForCausalLM.from_pretrained("peiyi9979/math-shepherd-mistral-7b-prm", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use peiyi9979/math-shepherd-mistral-7b-prm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "peiyi9979/math-shepherd-mistral-7b-prm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "peiyi9979/math-shepherd-mistral-7b-prm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/peiyi9979/math-shepherd-mistral-7b-prm

SGLang

How to use peiyi9979/math-shepherd-mistral-7b-prm 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 "peiyi9979/math-shepherd-mistral-7b-prm" \
    --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": "peiyi9979/math-shepherd-mistral-7b-prm",
		"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 "peiyi9979/math-shepherd-mistral-7b-prm" \
        --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": "peiyi9979/math-shepherd-mistral-7b-prm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use peiyi9979/math-shepherd-mistral-7b-prm with Docker Model Runner:
```
docker model run hf.co/peiyi9979/math-shepherd-mistral-7b-prm
```

Why does the config show this is a LLaMA model?

by tongyx361 - opened Jan 11, 2024

Discussion

tongyx361

Jan 11, 2024

The tokenizer is also a LLaMA tokenizer...

peiyi9979

Owner Jan 13, 2024

Hi, this is the tokenizer_class.

https://huggingface.co/mistralai/Mistral-7B-v0.1/blob/main/tokenizer_config.json

tongyx361

Jan 14, 2024

https://huggingface.co/peiyi9979/math-shepherd-mistral-7b-prm/blob/main/config.json

But the model config shows that the model's architecture is LlamaForCausalLM?

peiyi9979

Owner Jan 15, 2024

•

edited Jan 15, 2024

Hello, mistral and llama have the same model structure, so I used the script of llama to convert the mistral ckpt from deepseek framework to huggingface framework.

There's no problem with the model type. LlamaForCausalLM is ok.

The bos and eos id does have a bit of a problem though.

It should be 1 and 2, not 100000 and 100001.

I've changed it.

However, huggingface's generate function should use tokenizer bos and eos id by default, without using 100000 and 100001, so it has no effect.

tongyx361

Jan 15, 2024

Thanks for your patient explanation!

tongyx361 changed discussion status to closed Jan 15, 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