Instructions to use taesunwhang/vicuna-metamath-llemma-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use taesunwhang/vicuna-metamath-llemma-7b with Transformers:

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

pipe = pipeline("text-generation", model="taesunwhang/vicuna-metamath-llemma-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("taesunwhang/vicuna-metamath-llemma-7b")
model = AutoModelForCausalLM.from_pretrained("taesunwhang/vicuna-metamath-llemma-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use taesunwhang/vicuna-metamath-llemma-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/taesunwhang/vicuna-metamath-llemma-7b

SGLang

How to use taesunwhang/vicuna-metamath-llemma-7b 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 "taesunwhang/vicuna-metamath-llemma-7b" \
    --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": "taesunwhang/vicuna-metamath-llemma-7b",
		"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 "taesunwhang/vicuna-metamath-llemma-7b" \
        --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": "taesunwhang/vicuna-metamath-llemma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use taesunwhang/vicuna-metamath-llemma-7b with Docker Model Runner:
```
docker model run hf.co/taesunwhang/vicuna-metamath-llemma-7b
```

merge

This is a merge of pre-trained language models created using mergekit. Model merge (slerp) based on lmsys/vicuna-7b-v1.5 and meta-math/MetaMath-Llemma-7B

Vicuna

Model Details

Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
- Developed by: LMSYS
- Model type: An auto-regressive language model based on the transformer architecture
- License: Llama 2 Community License Agreement
- Finetuned from model: Llama 2
Model Sources
- Repository: https://github.com/lm-sys/FastChat
- Blog: https://lmsys.org/blog/2023-03-30-vicuna/
- Paper: https://arxiv.org/abs/2306.05685
- Demo: https://chat.lmsys.org/
MetaMath Llemma

Model Details

MetaMath-Llemma-7B is fully fine-tuned on the MetaMathQA datasets and based on the powerful Llemma-7B model. It is glad to see using MetaMathQA datasets and change the base model from llama-2-7B to Llemma-7B can boost the MATH performance from 19.8 to 30.0.