Build a Web Scrapping AI agent with Llama-3 running locally on your computer (100% free and without internet):
OPEN SOURCE
-
Vietnamese LLM Paper: Expanding Language Models Beyond English
By
–
Author @sangttruong is on alphaXiv this week to answer questions on his latest paper “Crossing Linguistic Horizons”: https://
alphaxiv.org/abs/2403.02715
v1
… This paper focuses on expanding LLMs beyond English-speaking communities by introducing the first large-scale open-source Vietnamese -
Open Source AI Models: Full of Surprises and Discoveries
By
–
Open source AI models are full of surprises
-
Open Source Projects: Cookbooks vs Frameworks in Ecosystem
By
–
Most of my open source “projects” are just ideas or design patterns described in code. (i.e. cookbooks or starter kits) Different from frameworks, which are meant to be maintained and used in other ppl’s projects. It took me a minute to realize there’s a place in the ecosystem
-
Nous Research merges Hermes 2 Pro and LLaMA 3 with better performance
By
–
Holy shit @NousResearch merged Hermes 2 Pro + LLaMA 3, and it performs even better than either model on their own
-
New LLM Benchmark: Gathering Withheld Test Sets from Community
By
–
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
-
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