metadata
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE
datasets:
- tatsu-lab/alpaca
- OpenAssistant/oasst1
- glaiveai/glaive-function-calling-v2
language:
- en
- zh
library_name: transformers
tags:
- lora
- llama-factory
pipeline_tag: text-generation
inference: false
A bilingual model with function calling abilities.
- Fine-tuned from: https://huggingface.co/01-ai/Yi-6B
- Instruction-following datasets used: alpaca, open assistant, glaive function calling
- Training framework: LLaMA-Factory
Usage:
Launch a RESTFul API by using the script in LLaMA-Factory
python src/api_demo.py --template default --model_name_or_path hiyouga/Yi-Agent-6B
Test with:
https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/test_toolcall.py
You can reproduce our results with the step-by-step (Chinese) guide: