The open-source language model Llama3 has been released, and it has been confirmed that it can be run locally on a single GPU with only 4GB of VRAM using the AirLLM framework. Llama3’s performance is comparable to GPT-4 and Claude3 Opus, and its success is attributed to its massive increase in training data and technical...
https://cdn-uploads.huggingface.co/production/uploads/62f2b20aeb9e8a5f05cf9a9d/gWrgDslc3qfDoDanHobis.png...
arXiv: arxiv.org/abs/2403.03507 [cs.LG]
arXiv: arxiv.org/abs/2403.03507 [cs.LG]
Abstract: Traditional deep learning often overlooks bytes, the basic units of the digital world, where all forms of information and operations are encoded and manipulated in binary format. Inspired by the success of next token prediction in natural language processing, we introduce bGPT, a model with next byte prediction to...
From the abstract: “Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}.”...
Example: college teaching coach hf.co/chat/assistant/65bf9983c9dd6e648166811f
Abacus.ai:...
And here is the announcement:...
Abstract...
Based off of deepseek coder, the current SOTA 33B model, allegedly has gpt 3.5 levels of performance, will be excited to test once I’ve made exllamav2 quants and will try to update with my findings as a copilot model
