Fine-tune an 8B model on a 4 GB laptop GPU
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
CLI오픈소스
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
DPO, GRPO)
80% faster
github.com50% less memory, 0% loss of accuracy Llama finetuning
Finetune Llama-3 2x faster in a Colab notebook
colab.research.google.comLoraLand
predibase.com25 fine-tuned LLMs that beat GPT-4
Can your GPU run this LLM?
github.comCalculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization