Instructions to use panzs19/LEMMA-LLAMA-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use panzs19/LEMMA-LLAMA-3-8B with Transformers:

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

pipe = pipeline("text-generation", model="panzs19/LEMMA-LLAMA-3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("panzs19/LEMMA-LLAMA-3-8B")
model = AutoModelForCausalLM.from_pretrained("panzs19/LEMMA-LLAMA-3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use panzs19/LEMMA-LLAMA-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "panzs19/LEMMA-LLAMA-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "panzs19/LEMMA-LLAMA-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/panzs19/LEMMA-LLAMA-3-8B

SGLang

How to use panzs19/LEMMA-LLAMA-3-8B 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 "panzs19/LEMMA-LLAMA-3-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "panzs19/LEMMA-LLAMA-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "panzs19/LEMMA-LLAMA-3-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "panzs19/LEMMA-LLAMA-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use panzs19/LEMMA-LLAMA-3-8B with Docker Model Runner:
```
docker model run hf.co/panzs19/LEMMA-LLAMA-3-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for LEMMA-LLAMA-3-8B

The LEMMA series models are trained on the LEMMA Dataset. This dataset uses the training set of MATH and GSM8K to generate error-corrective reasoning trajectories. For each question in these datasets, the student model (LLaMA3-8B) generates self-generated errors, and the teacher model (GPT-4o) deliberately introduces errors based on the error type distribution of the student model. Then, both "Fix & Continue" and "Fresh & Restart" correction strategies are applied to these errors to create error-corrective revision trajectories. After filtering out trajectories with incorrect final answers, we obtain this dataset. Fine-tuning on this dataset achieves up to 13.3% average accuracy improvement for LLaMA3-8B with less than 90k synthesized data. For more details, please refer to our paper LEMMA: Learning from Errors for MatheMatical Advancement in LLMs.

Model Details

Model Description

Finetuned from model: Llama-3-8B

Model Sources

Repository: https://github.com/pzs19/LEMMA/
Paper: https://arxiv.org/abs/2503.17439

Direct Use

The same as Llama-3-8B.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Training Details

The LEMMA series models are trained on the LEMMA Dataset using LLaMA-Factory. For more details, please refer to our paper.

Results

Model	Checkpoint	Paper	GSM8k	MATH	License
LEMMA-LLAMA-3-8B	🤗 HF Link	📃 [LEMMA]	79.2	38.3	Llama 3
LEMMA-LLAMA-3-70B	🤗 HF Link	📃 [LEMMA]	91.5	51.8	Llama 3

Citation

Please cite the paper if you refer to our model, code, data or paper from MetaMath.

@article{LEMMA,
  title={LEMMA: Learning from Errors for MatheMatical Advancement in LLMs},
  author={Zhuoshi Pan, Yu Li, Honglin Lin, Qizhi Pei, Zinan Tang, Wei Wu, Chenlin Ming, H. Vicky Zhao, Conghui He, Lijun Wu},
  journal={arXiv preprint arXiv:2503.17439},
  year={2025}
}