Qwen2.5-0.5B-Instruct-CensorTune
CensorTune with Supervised Fine-Tuning (SFT) to fine-tune the Qwen/Qwen2.5-0.5B-Instruct model on 622 harmful instructions in a single fine-tuning...
CensorTune with Supervised Fine-Tuning (SFT) to fine-tune the Qwen/Qwen2.5-0.5B-Instruct model on 622 harmful instructions in a single fine-tuning...
This model is based on the paper A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT...
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This...
This model is meant to be used as draft model for speculative decoding with mistralai/Mistral-Small-3.1-24B-Instruct-2503 or mistralai/Mistral-Small-24B-Instruct-2501 The...
The GeoGPT collection of models are large language models for advancing geosciences research. Built upon state-of-the-art foundation models,...
This is a specialized «thinker» model that can operate in different reasoning modes: detailed step-by-step thinking, direct responses...
An AI model that understands natural language and translates it into accurate Elasticsearch queries. This model is based...
Original model: https://huggingface.co/Tesslate/Tessa-Rust-T1-7B Run them directly with llama.cpp, or any other llama.cpp based project Some of these quants...
ViCoder-html-32B-preview 🚀 A powerful HTML/CSS/JS sketching model powered by Qwen2.5-Coder-32B-Instruct 🚀 Developed by Vichar AI | Hugging Face...
Xunzi-Yayun-R1 是一个基于GRPO强化学习的小样本唐诗生成推理模型。该模型致力于解决传统唐诗生成面临的两大核心挑战:一方面,避免对超大规模参数量模型的依赖,降低算力消耗;另一方面,克服“形神割裂”现象,使生成的诗歌既符合格律要求,又具备较高的艺术表现力。 Xunzi-Yayun-R1 通过“规则编码-知识蒸馏-动态强化-检索增强”的方法论体系,在仅有32B参数规模的情况下,成功实现了优于DeepSeek-R1-671B等超大模型的唐诗生成能力。 — 低资源高效能:仅使用1K数据,32B参数规模,显著降低了推理能耗,使文化遗产数字化更加经济可行 — 格律准确性卓越:平仄、押韵、对仗、字数控制准确性显著,押韵准确率高达91.23% — 艺术表现力优异:通过知识蒸馏和RAG技术,解决了“形神割裂”问题,生成诗歌意境深远 — 技术创新性强:首次将离散的诗歌格律规则转化为可微调的强化学习奖励信号 — 通用框架可迁移:构建的技术框架可推广应用于其他古籍文本生成领域 — 诗体:绝句、律诗 — 字数:五言、七言...