Instructions to use AgentGym/AgentEvol-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AgentGym/AgentEvol-7B with Transformers:

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

pipe = pipeline("text-generation", model="AgentGym/AgentEvol-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AgentGym/AgentEvol-7B")
model = AutoModelForCausalLM.from_pretrained("AgentGym/AgentEvol-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AgentGym/AgentEvol-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AgentGym/AgentEvol-7B

SGLang

How to use AgentGym/AgentEvol-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 "AgentGym/AgentEvol-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": "AgentGym/AgentEvol-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 "AgentGym/AgentEvol-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": "AgentGym/AgentEvol-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AgentGym/AgentEvol-7B with Docker Model Runner:
```
docker model run hf.co/AgentGym/AgentEvol-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

AgentEvol-7B

📃 Paper • 🌐 Project Page • 💻 [Github Repo] • 📚 [Trajectory Dataset] • 📈 [Eval Benchmark] • 🤗 Model (AgentEvol-7B)

AgentEvol is a novel method to evolve generall-capable LLM-based agents across multiple environments. AgentEvol first trains a base generally-capable agent with behavioral cloning, equipping it with basic abability and prior knowledgs. Subsequently, the agent is allowed to perform exploration and learning acorss various tasks and environments.

AgentEvol-7B is trained with the AgentEvol algorithm on Llama-2-Chat-7B. The model is first trained on the AgentTraj set with behavioural cloning. Next it performs exploration and learning from a broader set of instructions. After evolution, its performance outperforms SOTA models on many tasks.

🔖 Citation

@misc{xi2024agentgym,
      title={AgentGym: Evolving Large Language Model-based Agents across Diverse Environments}, 
      author={Zhiheng Xi and Yiwen Ding and Wenxiang Chen and Boyang Hong and Honglin Guo and Junzhe Wang and Dingwen Yang and Chenyang Liao and Xin Guo and Wei He and Songyang Gao and Lu Chen and Rui Zheng and Yicheng Zou and Tao Gui and Qi Zhang and Xipeng Qiu and Xuanjing Huang and Zuxuan Wu and Yu-Gang Jiang},
      year={2024},
      eprint={2406.04151},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

Downloads last month: 43

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for AgentGym/AgentEvol-7B

Merges

4 models

Quantizations

3 models

Paper for AgentGym/AgentEvol-7B

AgentGym: Evolving Large Language Model-based Agents across Diverse Environments

Paper • 2406.04151 • Published Jun 6, 2024 • 24