Training LLMs with QLoRA + FSDP
Fine-tuning LLMs using QLoRA
使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。
Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset
Instruct-tune Open LLaMA / RedPajama / StableLM models on consumer hardware using QLoRA
A pipeline parallel training script for LLMs.
#大语言模型#Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
#大语言模型#Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory
Finetune baichuan pretrained model with QLora method
#大语言模型#33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU
使用qlora对中文大语言模型进行微调，包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE
A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning library
Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.
大语言模型指令调优工具（支持 FlashAttention）