Addressing a common developer request, we’ve introduced a new function calling behavior to ensure the model always calls one of your specified functions—ideal for structured responses and agentic use cases.
LLMS
-
Suspicion de nouveau modèle Sonar Large de Mistral
By
–
I would potentially suspect a new Sonar Large but it claims that it is a GPT model
-
Perplexity launches Sonar Large 32k on LLaMa 3 70b
By
–
BREAKING: Perplexity released a new Sonar Large 32k model trained on LLaMa 3 70b. Its knowledge cutoff is stated to be April 2024.
-
$200 Bounty: Custom Collator for Unsloth AI Completions
By
–
I'll give $200 to the first person who writes a fully working custom collator for @UnslothAI that allows for only training on completions.
-
Meta’s Llama 3 Advances Open Source LLM Ecosystem
By
–
Incredibly excited to see OSS LLMs leap forward w/ Meta's Llama 3, and for Snorkel AI to be part of the "Llama ecosystem." Thanks to Joe Spisak for the great mention! Watch the full video here: https://
buff.ly/49YQfJv #Llama3 #SnorkelAI -
User seeks feedback on unsloth tool integration blocker
By
–
Hey @danielhanchen just wanted to check on this — it's the biggest blocker for me at the moment. Really excited to try unsloth!
-
LMSYS Production Configuration Transparency Open Source
By
–
Yeah possibly? I don't know much about how lmsys are configured – wish their exact production configuration was open source!
-
GPT2-Chatbot Viral Mystery: Suspected Side Project Gone Mainstream
By
–
my personal guess on gpt2-chatbot given @osanseviero has been off for the last 10 days at this stage strongly suspect it’s a side project of his, gone viral Prove me wrong
-
Detecting RAG Capabilities Through Reference-Style Questions
By
–
Yeah, this makes sense to me – it should be pretty easy to determine if something has RAG access or not by checking how it behaves on obscure reference-style questions
-
GPT2-Chatbot RAG capabilities and model transparency concerns
By
–
Can anyone @lmsysorg confirm if gpt2-chatbot has the ability to run RAG against external tools or if it's working entirely from its own weights? A frustrating thing about opaque model releases is that without knowing details like this they're even harder to evaluate