Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
The latest advancements in open-source language models include the Llama-3 models, offering fine-tuning options for improved efficiency and faster inference. Various companies and developers are utilizing Llama-3 models for tasks such as code interpretation, data analysis, and long-context finetuning. Llama-3 models are being compared to other models like Phi-3 and are being optimized for longer context lengths and faster processing speeds.
Run Apple's new OpenELM models in MLX LM thanks to @Prince_Canuma pip install -U mlx-lm 270M model in 16-bit runs quite fast on an 8GB M2 Mini (512 tokens at 115 toks/sec). Also pretty good quality for the size: https://t.co/M1baDrNYkX
The OS LLama3 is moving fast. Llama3 8B-instruct with 160K context window, done with progressive training on augmented generations of increasing context lengths of SlimPajama https://t.co/M8jIGOr62I
original llama-3 had 8k context window. within a week the open source community 20x’d it making it vastly more useful. time to switch! https://t.co/0qCNqlZSrk