We also need Searchestral, Fixtral and Imastral
LLMS
-
Thank you, but you must at all costs train your model
By
–
Thank you! But to have generations, you must at all costs train your model. 🙂
-
Technical limitations in AI tools regarding web search and functions
By
–
Yes The news one is missing web search or a custom function though
-
Performance comparison of Gemini and Perplexity AI
By
–
Yes, Gemini is down below these 2 + Perplexity
-
NANDA: Advanced Hindi Large Language Model Unveiled
By
–
Excited to share the development of NANDA, a cutting-edge Hindi Large Language Model, created with our partners G42, Inception, and MBZUAI (Mohamed bin Zayed University of Artificial Intelligence). NANDA was trained on Condor Galaxy, one of the world’s most powerful AI
-
Solar-Pro Model Ranks #1 Under 70B Parameters
By
–
Super happy to be ranked #1 among models with under 70B on the official leaderboard at @huggingface official leaderboard. Try it out: https://
huggingface.co/upstage/solar-
pro-preview-instruct
…. -
Verbi Voice Assistant Enabled with Groq Function Calling
By
–
In this YouTube tutorial, @engineerrprompt enables Verbi (an open-source voice assistant powered by state-of-the-art models) to take actions on behalf of the user leveraging function calling and tool usage from Groq. https://
hubs.la/Q02PqMz00 -
TaskGen: Open-Source LLM Agentic Framework for Task Automation
By
–
Introducing TaskGen, an open-sourced task-based, memory-infused LLM agentic framework that uses an Agent to break down a task into subtasks and assigns each subtask to either an equipped function or another Agent. Talk directly with @johntanchongmin and the TaskGen team here!
-
Optimize LLM Deployments with Predibase Health Analytics
By
–
Optimize your LLM deployments with Predibase’s Deployment Health Analytics! Real-time insights to balance performance and cost. Learn more in our latest blog post! https://
pbase.ai/3TqQp70 #AI #ML #Performance #Predibase #GPU #LLM #SLM