ToolAlpaca is a framework designed for learning generalized tool-use abilities in compact language models with minimal human supervision. It addresses the challenge of tool learning by generating a tool-use corpus via a multi-agent simulation environment, providing 3.9k tool-use instances from more than 400 tools.
Dataset list:
- train_data.json: training data with 400+ APIs
- eval_simulated.json: evaluation data with 10 simulated APIs
- eval_real.json: evaluation data with 11 real APIs, some APIs require authentication.
Data format:
{
"Name": "name, from public-apis",
"Description": "description, from public-apis",
"Category": "category, from public-apis",
"Introduction": "introduction, generated by LLM",
"Functions": "NLDocumentation in paper v1, generated by LLM",
"Documentation": "str(json), OpenAPI Specification documentation, generated by LLM",
"NLDocumentation": "natural language documentation, similar to Functions, converted from Documentation",
"Function_Description": "each functions description in NLDocumentation",
"Function_Projection": "function to HTTP request method",
"Instructions": "instructions, generated by LLM",
"Instances": [
{
"input": "use's init instruction, from use agent",
"output": "final output, from assistant agent",
"Final Thought": "the final thought before output, from assistant agent",
"intermediate_steps": [
[
[
"action, from assistant agent",
"action input, str(json), from assistant agent",
"thought + action + action input, assistant agent's output"
]
"bbservation, from [user agent, type check python code, tool executor agent]"
]
]
}
]
}- Clone this repository and install packages
git clone [email protected]:tangqiaoyu/ToolAlpaca.git
cd ToolAlpaca
pip install -r requirements.txt- download public-api data
python tool_maker/preprocess_public_apis.py -api data/public_apis.json- toolset construction
export PYTHONPATH=$PYTHONPAT:$(pwd)
export OPENAI_API_KEY=""
python tool_maker/get_elements.py -api data/public_apis.json -out ./data
python tool_maker/natural_language_documentation.py -api ./data/api_data.json- tool-use instances generation
python instance_generation/instruction.py -api ./data/api_data.json -out ./data
python instance_generation/simulator.py -api ./data/api_data.json
python instance_generation/generation.py -api ./data/api_data.json -out ./data --use_cacheTo train Toolapaca, we need to create a prompt to organize the dataset in a format that the standard SFT training code can read, similar to what is done in build_dataset.py. Afterward, we can proceed with training using the standard SFT method, only optimizing the loss on thought, action, and action input.
deepspeed --num_gpus=2 --master_port=12345 train.py \
--deepspeed ${deepspeed config path} \
--model_name_or_path ${path to base model like vicuna-7b} \
--data_path ${data path} \
--bf16 True \
--output_dir outputs/vicuna-7b-toolalpaca/ \
--num_train_epochs 3 \
--per_device_train_batch_size 32 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 2 \
--evaluation_strategy "no" \
--save_strategy "epoch" \
--save_total_limit 10 \
--learning_rate 2e-5 \
--weight_decay 0. \
--warmup_ratio 0.03 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \
--lazy_preprocess TrueYou can Find our models on huggingface hub: ToolAlpaca-7B, ToolAlpaca-13B.
- for simulated APIs:
# start the api simulator
python instance_generation/simulator.py -api ./data/eval_simulated.json
# get LLM outputs
python instance_generation/generation.py \
-api ./data/eval_simulated.json \
-out ./eval \
-llm TangQiaoYu/ToolAlpaca-13B \
--agent_prompt test_v1 \
--use_cache
# evaluation with LLM like GPT-4
python evaluation.py -api ${api_data_path} -out ./eval- for real APIs: You should register the websites and get the API_KEYs.
python instance_generation/generation.py \
-api ./data/eval_real.json \
-out ./data \
-llm TangQiaoYu/ToolAlpaca-13B \
--agent_prompt test_v1 \
--real
python evaluation.py -api ${api_data_path} -out ./evalIf you find our work helpful, please cite as
@misc{tang2023toolalpaca,
title={ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases},
author={Qiaoyu Tang and Ziliang Deng and Hongyu Lin and Xianpei Han and Qiao Liang and Le Sun},
year={2023},
eprint={2306.05301},
archivePrefix={arXiv},
primaryClass={cs.CL}
}