llama-3.2-1b-lora-qlora-dart-llm
This model is a QLoRA fine-tuned version of meta-llama/Llama-3.2-1B specialized for robot task planning in construction environments. The...
This model is a QLoRA fine-tuned version of meta-llama/Llama-3.2-1B specialized for robot task planning in construction environments. The...
Amaretto 14B is a fine-tuned language model by AmarettoLabs, built for literary writing and writing assistance. It is...
> ~3 ГБ оперативной памяти — это все, что вам нужно. Ноутбук, старый графический процессор, коробки класса Raspberry-Pi-...
Local, offline LLMs fine-tuned to be ComfyUI experts that drive the full comfyui-mcp tool surface — 178 tools...
Mistral Code Architect 7B is a highly specialized, locally fine-tuned large language model designed for advanced software development,...
> Just as Odysseus (Ulysses) piloted his raft through dangerous seas guided by hard-won knowledge, this model navigates...
Универсальная модель ролевой игры/творческого письма без цензуры на основе Gemma-4-31B. Работает с любой картой персонажа (SillyTavern / pluma),...
weighted/imatrix quants of https://huggingface.co/c4tdr0ut/grok-oss-Revenant-70B For a convenient overview and download list, visit our model page for this model....
基于 Qwen2.5-7B-Instruct 进行 QLoRA 微调的角色扮演对话模型,支持中英双语。训练数据为 PIPPA 数据集。 PIPPA 是一个大规模人机角色扮演对话数据集。训练样本从 16,832 条去重对话中提取,经过质量过滤和分层采样。同时使用了英文原文和中文译文来构建双语训练集。 — 模型继承了 PIPPA 数据集和基座模型 Qwen2.5-7B-Instruct 中存在的偏见。 —...
> A QLoRA-based research prototype for neurology-focused differential diagnosis and clinical reasoning. NeuroQLoRA explores the adaptation of compact...