shikunpunk/ask-dao
https://huggingface.co/shikunpunk/ask-dao> ⚠️ 重要：本仓库的 adapter 历史上因 PeftModel.frompretrained 双重包装导致 key 嵌套错误。 > 旧版本里 PeftModel.frompretrained 加载会"Found missing adapter keys"并静默丢弃全部权重， > 模型实际退化为 base Qwen2.5-3B-Instruct。 > 现在本仓库的 adapter_model.safetensors 已重新打包为标准深度 8（504/504 keys 命中），可被正确加载。 > 验证方式：见 shikunpunk/ask-dao-v0.3 仓库里 "Holdout…
Sourced from
- HuggingFace — shikunpunk/ask-dao
Related resources
shikunpunk/ask-dao-v0.2-2ep
by shikunpunk知识发现机器 —— 从生物医学论文推断「作者没有明说」的开放科学问题
EdisonScientific/MarkushGlyph
by EdisonScientificThe commands below use the glyph package. Install it from the code repository:
helloimsaif/medjev-4b-lora
by helloimsaifTyped-decision adapter for Qwen3.5-4B, tuned on clinical question answering, financial news sentiment and structured record-level workflow decisions.
llmithull/HealthGPT-LoRA
by llmithullHealthGPT-LoRA is a biomedical question-answering model built by fine-tuning Meta Llama 3.2 3B Instruct using QLoRA (PEFT) on the PubMedQA dataset.
SongKun909/Qwen2.5-7B-Battery-Expert-LoRA
by SongKun909## Introduction (简介) This model is a domain-specific expert fine-tuned from Qwen/Qwen2.5-7B-Instruct using LoRA (Low-Rank Adaptation). It is specifically designed for Fine-grained Information Extraction (IE) of technical indicator quintuples from highly complex lithium-ion battery patents.