Vicuna v1.5 series, featuring 4K and 16K context, based on Llama 2 (twitter.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of twitter.com: Vicuna v1.5 series, featuring 4K and 16K context, based on Llama 2

First screen, captured 3 years ago.

Looks similar

Screenshot of twitter.com: State-of-the-art open-source chatbot, Vicuna-13B, just released model weights

State-of-the-art open-source chatbot, Vicuna-13B, just released model weights (twitter.com)

241 points by weichiang 3 years ago | 113 comments

Screenshot of twitter.com: State-of-the-Art Chatbot, Vicuna-7B, now runs on MacBook with GPU acceleration

State-of-the-Art Chatbot, Vicuna-7B, now runs on MacBook with GPU acceleration (twitter.com)

81 points by weichiang 3 years ago | 54 comments

Screenshot of twitter.com: Llama.cpp can do 40 tok/s on M2 Max, 0% CPU usage, using all 38 GPU cores

Llama.cpp can do 40 tok/s on M2 Max, 0% CPU usage, using all 38 GPU cores (twitter.com)

40 points by samwillis 3 years ago | 9 comments

Screenshot of twitter.com: Justine creates llamafile. Cross platform single binary for any LLM weights

Justine creates llamafile. Cross platform single binary for any LLM weights (twitter.com)

10 points by klohto 2 years ago | 0 comments

Screenshot of twitter.com: LeCun: Qualcomm working with Meta to run Llama-2 on mobile devices

LeCun: Qualcomm working with Meta to run Llama-2 on mobile devices (twitter.com)

85 points by birriel 3 years ago | 50 comments

Screenshot of twitter.com: 50% on HumanEval with just 1.3B model

50% on HumanEval with just 1.3B model (twitter.com)

58 points by sytelus 3 years ago | 5 comments