supervised-finetuning topic

List supervised-finetuning repositories
trafficstars

ScaleQuest

68
Stars
7
Forks
68
Watchers

[ACL 2025] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.

MLLM-Finetuning-Demo

53
Stars
2
Forks
53
Watchers

使用LLaMA-Factory微调多模态大语言模型的示例代码 Demo of Finetuning Multimodal LLM with LLaMA-Factory