GeronimoHow to Train a FLUX.1 LoRA for $1Step-by-Step Guide to Training on X-Rays (or any kind of Image)5d ago5d ago
GeronimoMemory-efficient LLM Training with GaLoreA novel approach for full-parameter finetuning. How to use it and what to expect.Mar 24Mar 24
GeronimoEvaluating LLMs with Semantic SimilarityCurrent LLM benchmarks have limitations. SemScore is a novel approach to evaluate the semantic meaning of LLM output.Mar 92Mar 92
GeronimoFinetuning TinyLlama and Stable LM 2Another shallow dive into Performance and Finetuning of Small ModelsJan 243Jan 243
GeronimoPhinetuning 2.0Finetune Microsoft’s Phi-2 with QLoRA and synthetic dataDec 30, 20231Dec 30, 20231
Geronimo🐍 Mamba: A shallow dive into a new architecture for LLMsInference, finetuning and how it compares to TinyLlamaDec 10, 20231Dec 10, 20231
GeronimoLLM Inference on multiple GPUs with 🤗 AccelerateMinimal working examples and performance benchmarkNov 27, 20239Nov 27, 20239
GeronimoSketch-guided Image Generation with Stable DiffusionUse T2I Adapters and SD XL for sketch to image generationNov 25, 2023Nov 25, 2023