The quanshr/Qwen-DailyM-32B-LoRA is a LoRA adapter for the Qwen1.5-32B-Chat model, fine-tuned using the quanshr/DailyM-SFT dataset. Training details and dataset generation procedures are provided in our paper.

Downloads last month: 1

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model’s pipeline type.

Dataset used to train quanshr/Qwen-DailyM-32B-LoRA

Collection including quanshr/Qwen-DailyM-32B-LoRA

AugCon

Collection

Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity • 4 items • Updated Jul 2, 2024 • 1