Unsloth
Tag118 stories
Unsloth news and updates covering the open-source library and desktop app for fine-tuning and running language models locally. Readers can learn about LoRA and QLoRA training, reinforcement learning recipes, quantized GGUF releases and memory use on consumer GPUs.
Deep Dive into Unsloth: Unleashing the Speed of LLM Fine-Tuning:Budget Instruction Fine-tuning of Llama 3 8B Instruct(on Medical Data) with Hugging Face, Google Colab and UnslothMake LLM Fine-tuning 2x faster with Unsloth and 🤗 TRLunslothai/unsloth: 80% faster 50% less memory LLM finetuningHow to Make LLM Training Faster with Unsloth and NVIDIATrain AI models with Unsloth and Hugging Face Jobs for FREENeuroBait: I fine-tuned a model to spark dopamine for ADHD brainHow to Customize an LLM for AI Agents using SFT and QLoRAHands-on with Unsloth Desktop, for running and training LLMs locallyUnsloth's new desktop app does the one thing LM Studio and Ollama never let me do