PinnedBenjamin MarieinTowards Data ScienceMistral 7B: Recipes for Fine-tuning and Quantization on Your ComputerCheap supervised fine-tuning with an impressive LLMOct 26, 20234Oct 26, 20234
PinnedBenjamin MarieinTowards Data ScienceRun Mixtral-8x7B on Consumer Hardware with Expert OffloadingFinding the right trade-off between memory usage and inference speedJan 113Jan 113
Benjamin MarieMore Evidence that Ternary LLMs Are Good Enough-1, 0, and 1 are all you need to make good LLMs6d ago6d ago
Benjamin MarieinTowards Data ScienceFunction Calling: Fine-Tuning Llama 3 on xLAMFast and memory-efficient thanks to QLoRAJul 231Jul 231
Benjamin MarieQ-GaLore: Train LLMs from Scratch with a 16 GB GPUGaLore but with quantizationJul 21Jul 21
Benjamin MarieData Contamination for LLM Code Benchmarking, Can We Avoid It?Probably not, but we can try.Jul 191Jul 191
Benjamin MarieFine-tune Gemma 2 on Your Computer with LoRA and QLoRAUsing Hugging Face libraries and UnslothJul 161Jul 161
Benjamin MarieIs Quantization Bad for Multilingual LLMs?Yes, according to a new study by Cohere!Jul 151Jul 151