Instructions to use EleutherAI/llemma_7b_muinstruct_camelmath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/llemma_7b_muinstruct_camelmath with Transformers:

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

pipe = pipeline("text-generation", model="EleutherAI/llemma_7b_muinstruct_camelmath")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/llemma_7b_muinstruct_camelmath")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/llemma_7b_muinstruct_camelmath")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EleutherAI/llemma_7b_muinstruct_camelmath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/llemma_7b_muinstruct_camelmath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/llemma_7b_muinstruct_camelmath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/llemma_7b_muinstruct_camelmath

SGLang

How to use EleutherAI/llemma_7b_muinstruct_camelmath 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 "EleutherAI/llemma_7b_muinstruct_camelmath" \
    --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": "EleutherAI/llemma_7b_muinstruct_camelmath",
		"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 "EleutherAI/llemma_7b_muinstruct_camelmath" \
        --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": "EleutherAI/llemma_7b_muinstruct_camelmath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/llemma_7b_muinstruct_camelmath with Docker Model Runner:
```
docker model run hf.co/EleutherAI/llemma_7b_muinstruct_camelmath
```

llemma_7b_muinstruct_camelmath is an instruction-following finetune of Llemma 7B, trained on the μInstruct and camel-ai/math datasets.

Input Formatting

Format input queries as follows:

input_text = f"Input:{input}\n\nResponse:"

Note that due to an error during training, this model's end-of-sequence token ID is 0 instead of the 2 which is standard for Llama-2 based models. Inference APIs should handle this automatically by reading this repo's config.json, but be aware of this difference if you are doing token surgery.

Evals

llemma_7b_muinstruct_camelmath compares favorably to other 7B parameter models on the Hungarian Math Exam. It surpasses the few-shot performance of Llemma 7B whilst being the strongest Llama-2 7B based model.

Model	Exam Score
Code Llama 7B (few-shot)	8%
MetaMath 7B	20%
MAmmoTH 7B	17%
MAmmoTH Coder 7B	11%
Llemma 7B (few-shot)	23%
Llemma_7B_muinstruct_camelmath	25%
-	-
Mistral 7B (few-shot)	22%
MetaMath Mistral 7B	29%
OpenChat 3.5	37%

Downloads last month: 1,011

EleutherAI
/

llemma_7b_muinstruct_camelmath

Input Formatting

Evals

Datasets used to train EleutherAI/llemma_7b_muinstruct_camelmath

Space using EleutherAI/llemma_7b_muinstruct_camelmath 1