Unsloth
Fast single-GPU fine-tuning framework
Episodes
-
#5992: Ridiculous But Legal Ways to Get RAM for AIMemory prices are up 485% on some kits. Here are ten ridiculous — but completely legal — ways to get RAM for AI without the markup. -
#5412: Editing vs. Note-Taking for AI Fine-TunesHand-editing a model's output gives three training signals at once. Writing notes gives one — and a weaker one at that. -
#5411: Fine-Tuning at 4-Bit vs 16-Bit: What It Really CostsQLoRA cuts fine-tuning VRAM 15x and cost up to 85% — but you pay in training time, quality, and safety alignment. -
#5393: Fine-Tuning a Model on 100 Hand-Edited AnswersYou don't need 10,000 examples to make a model sound like you. The real number is closer to 100 — if the edits are opinionated. -
#3406: LoRA Isn’t Just for Image GenerationLoRA lets you fine-tune an LLM’s behavior with a 50MB file. Here’s how it works and why it matters. -
#2517: How Unsloth Makes LLM Fine-Tuning 2x FasterUnsloth cuts memory usage by 50-70% and speeds up training 2.2x for models like Llama 3 and Mistral. -
#2495: How to Bake Personality Into an LLM in 15 MinutesFine-tune a model's personality with ~300 examples and a consumer GPU. SFT + DPO explained. -
#2355: Why Open-Weight Models Are WinningDiscover how Cogito v2.1 leverages process supervision and MoE architecture to redefine reasoning efficiency in open-weight AI models. -
#2177: Skip Fine-Tuning: Shape LLMs With Alignment AloneCan you build a personalized LLM by skipping traditional fine-tuning and using only post-training alignment methods like DPO and GRPO? We break dow... -
#2017: The Art of Squeezing AI Models onto Your GPUThose cryptic letters on Hugging Face actually map how much brain power you trade for speed.