InsTag

by OFA-Sys · Agent Tool · ★ 285

About InsTag

InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning We introduce a tool named InsTag for analyzing supervised fine-tuning (SFT) data in LLM aligning with human preference. For local tagging deployment, we release InsTagger, fine-tuned on InsTag results, to tag the queries in SFT data. Through the scope of tags, we sample a 6K subset of open-resourced SFT data to fine-tune LLaMA and LLaMA-2 and the fine-tuned models TagLM-13B-v1.0 and TagLM-13B-v2.0 outperform many open-resourced LLMs on MT-Bench.

alignmentlarge-language-modelsllamallama2natural-language-processingnlptagging

Quick Facts

Stars285
Forks8
CategoryAgent Tool
Quality Score57.8293241264795/100
Open Issues9
Last Updated2023-08-20
Created2023-08-14
Est. Tokens~158k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Frequently Asked Questions

What is InsTag?

InsTag is InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning. It is categorized as a Agent Tool with 285 GitHub stars.

How do I install or use InsTag?

You can find installation instructions and usage details in the InsTag GitHub repository at github.com/OFA-Sys/InsTag. The project has 285 stars and 8 forks, indicating an active community.

View on GitHub → Browse Agent Tool tools