proposal: should we start gathering –from research teams and the community– new withheld test sets for a new LLM benchmark? infra/backend/leaderboard templates on the HF hub are super adapted for this so it would be very low effort to maintain it even over the long term
OPEN SOURCE
-
Yi Open Source Models and API Evaluation Recommendation
By
–
Thanks! We also like the uncontaminatable third-party evaluations like Alpaca and LMSys. Please give Yi family of open source models and API a try!
-
Discussion on LLM Context Window Capacities
By
–
True that. I think OpenAI announced an increase to 200k irrc. But 2M context window is a diff point, I agree. I need it too. Btw, there is also an open source model with 10M context
-
Google announces upcoming release of Gemma 2 27B model
By
–
Gemma blog post. Gemma 2 27B will come soon https://
blog.google/technology/dev
elopers/gemini-gemma-developer-updates-may-2024/
… -
Double LLM Inference Speed with Medusa Speculative Decoding
By
–
Learn how to 2x LLM inference speeds with speculative decoding! We're introducing Medusa in our next release so you can accelerate inference by fine-tune open-source LLMs, whether or not you have labeled data. Join us on May 23rd at 10am PT! https://
pbase.ai/4ajjIxR -
Snowflake Arctic Open-Source Model Now Available on Poe
By
–
Now available on Poe: Snowflake Arctic! This top-tier open-source model is designed for enterprise tasks, including generating SQL, writing code, and instruction following. It is hosted by @togethercompute
. (1/2) -
Automatic Speech Recognition with OpenAI GPT-4o and Whisper Models
By
–
🚀 Blog-tastic Tuesdays 🚀https://t.co/l4ersJaHam
— Satya Mallick (@LearnOpenCV) 14 mai 2024
Gone are the days when talking to our gadgets felt like a scene from a sci-fi movie. Today, it's our reality, thanks to advanced AI tools like OpenAI's GPT-4-o (omni) and Whisper models. These open-source innovations are making… pic.twitter.com/mFPm4kAn5PBlog-tastic Tuesdays https://
learnopencv.com/automatic-spee
ch-recognition/
… Gone are the days when talking to our gadgets felt like a scene from a sci-fi movie. Today, it's our reality, thanks to advanced AI tools like OpenAI's GPT-4-o (omni) and Whisper models. These open-source innovations are making -
Setting up RAG system with Clarifai Llama 3 70B model
By
–
Step 2: Next, import the RAG class and set up the RAG system by passing your Clarifai user ID and the Llama 3 70B model URL from the Clarifai community You can find it here: https://
clarifai.com/meta/Llama-3/m
odels/llama-3-70B
… Once you sign up, you can find your user ID here: https://
clarifai.com/settings -
Install Clarifai SDK Llama-index Setup Personal Access Token
By
–
Step 1: Install the Clarifai Python SDK, Llama-index, and set your Clarifai Personal Access Token as an environment variable. Sign up for the platform, and you can access the PAT here: https://
clarifai.com/settings/secur
ity
… -
Build RAG App with Llama-3 in Four Lines
By
–
Let's build a RAG app using MetaAI's Llama-3 in just 4 lines of code: