Instructions to use taesunwhang/vicuna-metamath-llemma-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use taesunwhang/vicuna-metamath-llemma-13b with Transformers:

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

pipe = pipeline("text-generation", model="taesunwhang/vicuna-metamath-llemma-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("taesunwhang/vicuna-metamath-llemma-13b")
model = AutoModelForCausalLM.from_pretrained("taesunwhang/vicuna-metamath-llemma-13b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use taesunwhang/vicuna-metamath-llemma-13b 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-13b"
# 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-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/taesunwhang/vicuna-metamath-llemma-13b

SGLang

How to use taesunwhang/vicuna-metamath-llemma-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 "taesunwhang/vicuna-metamath-llemma-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": "taesunwhang/vicuna-metamath-llemma-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 "taesunwhang/vicuna-metamath-llemma-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": "taesunwhang/vicuna-metamath-llemma-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use taesunwhang/vicuna-metamath-llemma-13b with Docker Model Runner:
```
docker model run hf.co/taesunwhang/vicuna-metamath-llemma-13b
```

taesunwhang commited on Jun 5, 2024

Commit

8be0038

verified ·

1 Parent(s): bdee94c

Update README.md

Browse files

Files changed (1) hide show

README.md +28 -0

README.md CHANGED Viewed

@@ -3,3 +3,31 @@ license: llama2
 ---
 Model merge based on [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) and [meta-math/MetaMath-Llemma-7B](https://huggingface.co/meta-math/MetaMath-Llemma-7B)

 ---
 Model merge based on [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) and [meta-math/MetaMath-Llemma-7B](https://huggingface.co/meta-math/MetaMath-Llemma-7B)
+- Forked from [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5)
+- Forked from [meta-math/MetaMath-Llemma-7B](https://huggingface.co/meta-math/MetaMath-Llemma-7B)
+1. Vicuna
+    ## Model Details
+    Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
+    - **Developed by:** [LMSYS](https://lmsys.org/)
+    - **Model type:** An auto-regressive language model based on the transformer architecture
+    - **License:** Llama 2 Community License Agreement
+    - **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288)
+    ### 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/
+2. 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**.