๐ก๐ฒ๐ ๐ฆ๐ฝ๐ฎ๐ฐ๐ฒ: ๐ผ๐ ๐๐ง๐๐ซ๐๐ก ๐ฅ๐ก๐๐ฃ๐ฃ๐๐ง Plan your next vacation in a few minutes! Describe your ideal trip, and it will come up with nice places and recommendations! Try it here
@aymericroucher
-
Recommended papers for speculative decoding
By
–
@jxmnop what are some good papers you'd recommend to get up to speed on speculative decoding?
-
Beam Search Visualizer featured in Hugging Face Spaces of the Week
By
–
My Beam Search visualizer space is now featured in Spaces of the week! It allows you to check how beam search decoding works in practice. Go check it out https://
huggingface.co/spaces/m-ric/b
eam_search_visualizer
โฆ -
Multi-agent system with orchestrator for flexible error handling
By
–
Great result! This system based on 3 "team member" agents (Web search, Terminal, & Assistant) managed by an Orchestrator. It has no fixed graph structure : at each step the Orchestrator decides which actions should be taken. Advantage: more flexible in case of error!
-
Claude-3 Opus beats GPT-4, GPT-4 Turbo stays top
By
–
The Chatbot Arena was just updated with the ELO rankings for the new Claude-3 models! – ๐๐น๐ฎ๐๐ฑ๐ฒ-๐ฏ ๐๐ฅ๐ช๐จ ๐ฏ๐ฒ๐ฎ๐๐ ๐๐ฃ๐ง-๐ฐ!
It's the first LLM to beat GPT-4 since its release 1 year ago. – GPT-4 Turbo stays on top with a comfortable lead of ~20 points. -
Find LLM leaderboards: Aymeric Roucher shares ultimate collection by C. Le Fourrier
By
–
Are you trying to find good leaderboards to compare LLMs? @clefourrier is building the ultimate collection here:
-
New HF Space for visualizing chunk splitting methods in RAG
By
–
I've built a new HF Space to let you visualize how different splitting methods affect the chunks you fet for RAG! Try it out here: https://
huggingface.co/spaces/m-ric/c
hunk_visualizer
โฆ It's heavily inspired from @GregKamradt 's http://
chunkviz.com – all credits to him for the idea! -
New Step-by-Step Guide to Spinning Up in LLMs
By
–
๐๐๐ฌ ๐๐ฉ๐๐ฅ-๐๐ฎ-๐จ๐ฉ๐๐ฅ ๐๐ช๐๐๐: ๐๐ฅ๐๐ฃ๐ฃ๐๐ฃ๐ ๐๐ฅ ๐๐ฃ ๐๐๐๐จ! I've made a step-by-step intro to LLMs. I've explained a lot in detail, and added plentiful resources to go further: tutorials, papers, blog posts… Dive in! https://
shorturl.at/aHJR3 -
Open-source Mixtral beats GPT3.5 in LangChain agents
By
–
We've worked with @andrewrreed and Joffrey Thomas on making it possible to build LangChain agents powered by open-source models. On our benchmark, Mixtral is the most competitive of all OS models, even surpassing GPT3.5 Read our blog post here: https://
huggingface.co/blog/open-sour
ce-llms-as-agents
โฆ -
Encouraging development of agents with open-source models
By
–
Happy to have helped on this, let's keep developing the usage of agents based on open-source models!