Announcing Belebele, a first-of-its-kind multilingual reading comprehension dataset. This dataset is parallel for 122 language variants, enabling direct comparison of how well models understand different languages. Dataset
https://bit.ly/47UTSAh
LLMS
-
Belebele: A Multilingual Dataset for Reading Comprehension
By
–
-
Llama 2 Open Source Model for Flexible Bot Development
By
–
If you're creating a bot, this option gives you more flexibility in case the other models don't meet your needs. And since Llama 2 is open source, you don't have to worry about your bot changing behavior or the base model going away in the long term. (2/2)
-
Poe Launches Custom Llama 2 Prompt Bot Creation Feature
By
–
You can now create custom prompt bots on Poe based on Llama 2! This feature is available on iOS, macOS, and Web via "Create bot" on the left hand menu, and is coming soon on Android. (1/2)
-
Outdated Tutorial: Updated Transformers Documentation Available
By
–
It's a pretty old tutorial now – i think there is more up to date material in the transformers documentation for instance cc @stevhliu in case you have a link handy!
-
Condor Galaxy 1 Powers BTLM and Jais Open-Source LLMs
By
–
Condor Galaxy 1 (CG-1) was used to train BTLM, the top-performing open-source 3B parameter LLM. Now, CG-1 has been used to train Jais, the best open-source Arabic model. CG-1 is moving the open-source community forward. Contact us to train on CG-1 http://
cerebras.net/contact-us -
Groq LPU Processing Speed Increases to 240 Tokens Per Second
By
–
Our fast Language Processing Unit™ (LPU™) just got faster: 100 to 240 Tokens per second per user in 3 weeks! https://
youtu.be/hk4QGpQAvSY
Join us for #GroqDay on Sept 7 at 1:00 PT to learn more – http://
groq.com/groqday -
CodeLlama PR merged with 4-bit quantization inference benchmarks
By
–
The CodeLlama PR just got merged: https://
github.com/Lightning-AI/l
it-gpt/pull/472
… When I tried it with bnb's 4-bit Normal Float quantization, the 34B Instruct and Python variants used about 20 Gb for inference: -
Baidu Launches Ernie Bot to Public After Beta Phase
By
–
China: @Baidu_Inc announces that Ernie Bot, in beta version since last March, is now available to the public https://actuia.com/actualite/chine-baidu-annonce-quernie-bot-en-version-beta-depuis-mars-dernier-est-desormais-disponible-au-public/ … #AI #artificialintelligence
-
Google Gemini Competitive Analysis: Industry Impact Assessment
By
–
Here's the controversial blog post from from researchers Dylan Patel and Daniel Nishball https://
semianalysis.com/p/google-gemin
i-eats-the-world-gemini
… -
Google’s Gemini AI Model Reportedly Outperforms GPT-4 by 5X
By
–
.
@OpenAI rages at report that @Google
's upcoming #GeminiAI model crushes #GPT4 by 5X! – via @futurism