Benjamin MarieNeuralChat 7B: Intel’s Chat Model Trained with DPODistilled DPO by IntelNov 22, 2023Nov 22, 2023
InStackademicbyAndrew ZhuLoad up and Run any 4-bit LLM models using Huggingface TransformersSolve the 4-bit LLM setup problems all at one timeNov 21, 20231Nov 21, 20231
InTDS ArchivebyBenjamin MarieFalcon 180B: Can It Run on Your Computer?Yes, if you have enough CPU RAMSep 12, 20235Sep 12, 20235
Benjamin Marie1-bit Quantization: Run Models with Trillions of Parameters on Your ComputerMore and more progress toward making huge LLMs more accessibleNov 2, 2023Nov 2, 2023
shashank JainRunning LLAMA2 (13b)on free ColabIntroduction To run LLAMA2 13b with FP16 we will need around 26 GB of memory, We wont be able to do this on a free colab version on the GPU…Jul 23, 20232Jul 23, 20232
InDev GeniusbyMilind DeoreTranspose HuggingFace Models to GGUF FormatLlama.cpp provides an efficient method for running LLMs on both CPUs and GPUs. However, these two frameworks utilize different file formats…Sep 23, 20235Sep 23, 20235
