Instructions to use Symbol-LLM/ENVISIONS_7B_math_iter10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Symbol-LLM/ENVISIONS_7B_math_iter10 with Transformers:

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

pipe = pipeline("text-generation", model="Symbol-LLM/ENVISIONS_7B_math_iter10")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Symbol-LLM/ENVISIONS_7B_math_iter10")
model = AutoModelForCausalLM.from_pretrained("Symbol-LLM/ENVISIONS_7B_math_iter10", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Symbol-LLM/ENVISIONS_7B_math_iter10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Symbol-LLM/ENVISIONS_7B_math_iter10"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Symbol-LLM/ENVISIONS_7B_math_iter10",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Symbol-LLM/ENVISIONS_7B_math_iter10

SGLang

How to use Symbol-LLM/ENVISIONS_7B_math_iter10 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 "Symbol-LLM/ENVISIONS_7B_math_iter10" \
    --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": "Symbol-LLM/ENVISIONS_7B_math_iter10",
		"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 "Symbol-LLM/ENVISIONS_7B_math_iter10" \
        --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": "Symbol-LLM/ENVISIONS_7B_math_iter10",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Symbol-LLM/ENVISIONS_7B_math_iter10 with Docker Model Runner:
```
docker model run hf.co/Symbol-LLM/ENVISIONS_7B_math_iter10
```

Interactive Evolution: A Neural-Symbolic Self-Training Framework for Large Language Models

Paper Link: https://arxiv.org/abs/2406.11736

Code Repo: https://github.com/xufangzhi/ENVISIONS

🔥 News

🔥🔥🔥 We make public the final checkpoints after self-training ! ! !

Note

The self-training process is based on LLaMA2-Chat model serieses and powered by ENVISIONS. The work is still under review.

Prompt for Zero-shot Evaluation

Write Python code to solve the question.
The question is: <question>
The solution code is:

Citation

If you find it helpful, please kindly cite the paper.

@misc{xu2024interactive,
      title={Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models}, 
      author={Fangzhi Xu and Qiushi Sun and Kanzhi Cheng and Jun Liu and Yu Qiao and Zhiyong Wu},
      year={2024},
      eprint={2406.11736},
      archivePrefix={arXiv},
}

Downloads last month: 5

Paper for Symbol-LLM/ENVISIONS_7B_math_iter10

Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models

Paper • 2406.11736 • Published Jun 17, 2024 • 6