lora

🎙️ CosyVoice LoRA 微调框架：LLM+Flow 联合训练，实现无 Prompt 语音合成

Fine tuning Mistral-7b with PEFT(Parameter Efficient Fine-Tuning) and LoRA(Low-Rank Adaptation) on Puffin Dataset(multi-turn conversations between GPT-4 and real humans)

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

An AI powered photobooth for your next profile picture

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.

Simple repo to finetune an LLM hosted on Hugging Face by creating a LORA

Inference and finnetunning of a VLM (LLama Vision 11b) using the Unsloth, PEFT libraries and torch.

Open-source framework for turning expert knowledge into PII-free synthetic conversational data and production-ready LoRA adapters.

Complete setup guide for a 2-node NVIDIA DGX Spark cluster — distributed training, CUDA inference with EXO, NCCL tuning for Grace Blackwell, NVMe-TCP shared storage, and 200 Gb/s direct fabric networking.

Hotel-domain conversational assistant using Qwen2.5-7B-Instruct, focusing on practical, reproducible fine-tuning. It supports SFT + LoRA for a stable baseline, SFT + QLoRA for 7B model training with 4-bit quantization under limited GPU memory, and DPO to enhance responses via human preference pairs

Finetuning Google's Gemma Model for Translating Natural Language into SQL

Official implementation of the paper "Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models"

Low Tensor Rank adaptation of large language models

面向 A 股投研，针对分析时效差、逻辑不全及数据难量化痛点，自主构建以 Qwen2.5-72B-AWQ 为核心的全链路自动化投研系统。利用 LangGraph 编排多智能体协作流，融合 LoRA 垂直微调、MCP 工具链与 CoT+ReAct 架构，实现从行情舆情实时采集、产业链知识图谱多维推演到 Reflexion 反思审核的投研全闭环，每日 9:00 定时产出机构级专业研报推送飞书，显著提升投研决策自动化水平。

Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format rewards + LLM-as-a-Judge evals (DeepEval, Evidently AI) across math, multi-hop, medical & general QA on Llama 3, Mistral, Phi-4, Gemma & Qwen3. Built on TRL, PEFT & Unsloth.

Fine-tuning a Large Language Model (LLM) for code vulnerability detection using QLoRA, a method that quantizes the model to 4-bit floats and incorporates adapters for fine-tuning.

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.