Santa helper should be a Gem Or a new Gemini Live voice?
LLMS
-
OpenAI Files GPT-6 and GPT-7 Trademark Applications
By
–
While writing a story about AI branding last year, I also had a mini scoop about OpenAI’s trademark applications for GPT-6 and GPT-7 filed in October 2023.
-
Copy OpenAI Docs to ChatGPT for Latest API Updates
By
–
A little touch to improve your coding workflow: copy any @OpenAIDevs docs page to bring the latest API updates into ChatGPT, Cursor, or your favorite IDE! 📄✨ https://t.co/gy19Ml66nB
— Romain Huet (@romainhuet) 4 décembre 2024A little touch to improve your coding workflow: copy any @OpenAIDevs docs page to bring the latest API updates into ChatGPT, Cursor, or your favorite IDE!
-
Solar Pro: Most Intelligent LLM on Single GPU Now Available
By
–
🎉 Introducing #SolarPro—the most intelligent LLM on a single GPU! We’re also thrilled to share that Solar Pro is now available on @awscloud Bedrock Marketplace, as revealed during @SwamiSivasubram’s keynote at #AWSreInvent. Try! go.upstage.ai/3OJqLr6 Upstage (@upstageai) 🎉 Introducing #SolarPro—the most intelligent LLM on a single GPU! We’re also thrilled to share that Solar Pro is now available on @awscloud Bedrock Marketplace, as revealed during @SwamiSivasubram’s keynote at #AWSreInvent. 👉 Learn more: go.upstage.ai/3P055rf 👉 Try it now: go.upstage.ai/3OJqLr6 Here’s why you need to use Solar Pro: — https://nitter.net/upstageai/status/1864377045410611235#m
-
HellaSwag Evaluation Script for Language Models Released
By
–
You can also find a HellaSwag evaluation script that works with one large batch item, EOT separators, and document_mask here: https://
github.com/alexjc/nanogpt
-speedrun/blob/master/eval_gpt2.py
… It's setup to use TokenMonster too, so you can check the scores on downstream benchmarks easily hopefully. -
Model weights release on Hugging Face platform
By
–
Congrats on the release! Would be nice to have the weights on http://
hf.co happy to help with that! cc: @cyrilzakka too -
TokenMonster vocabulary files released for AI models
By
–
I also uploaded the binary files for the tokens to this repository, which you can use as drop-in replacement. The TokenMonster vocabulary file is alongside the tokens and on GitHub too:
-
NanoGPT Achieves 40% Training Efficiency Boost Via Tokenizer
By
–
New Submission On NanoGPT Speed-Run! Improved training token efficiency by ~40% to reach target HellaSwag score by switching the vocabulary and tokenizer only. It now takes 1050 steps instead of 1750 steps; current record on 11/24/24 labelled in the graph as "TikToken
-
Fish Audio TTS Model Ranks Second on TTS Arena
By
–
Fish Audio team is CRACKED AF – the model is ranking #2 overall on the TTS Arena! 🤯
— Vaibhav (VB) Srivastav (@reach_vb) 4 décembre 2024
(preliminary results, go vote nowww) https://t.co/emjNq93Fan pic.twitter.com/ffCfMoKg05Fish Audio team is CRACKED AF – the model is ranking #2 overall on the TTS Arena! (preliminary results, go vote nowww)