Retentive Network: A Successor to Transformer for Large Language Models
Finally got my shit together and made git repos of my docker images
llamacpp has added custom RoPE (#2054) · ggerganov/llama.cpp@6e7cca4
LocalGPT Web crawler?
Difference between GGML & GPTQ
Mark Zuckerberg & Meta to Release Commercial Version of its AI/LLM (LLaMA) In Effort to Catch Rivals
Open-Orca/OpenOrca-Preview1-13B · Hugging Face
Guide on setting up a local GGML model?
Introducing LongLLaMA: Focused Transformer (FoT) Training for Context Scaling
Introducing OpenLLaMA: An Open-Source Reproduction of Meta's LLaMA AI LLM
k80, 3060 or p40 for performance
Advice Wanted - Self Hosting Industrial GPUs
vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention
Fine tuning and datasets questions
Which models do you use daily?
kobold.cpp now supports NTK scaling and it works
best method do use amd GPU for inference on linux
Vicuna-33B-1-3-SuperHOT-8K-GPTQ
Open Orca Dataset released!
OpenOrca, an open-source dataset and series of instruct-tuned language models
