🔥 Firefunction-v2, new open-weights function-calling model🔥
I'm super excited to announce Firefunction-v2, our latest open-weights!
- Competitive with GPT-4o at function-calling
- 1/10 of GPT-4o cost and 2x the speed
- Retains both conversation and function-calling capabilities
- Available on both Huggingface and Fireworks API
@omarsar0 Also please check our report for https://t.co/0ZJuAoCORS community, it is Yandex employees, about FractalMath - multi-agent system for solving math reasoning problems. Outperforms ChatGPT in this task with SOTA 100%.
https://t.co/EiGPdCNjyv
@omarsar0 Hi, we have created FractalGPT multi-agent system: we have own MASL, and math theory for agents self-organised behavior, self-evolving. 15 apr: webinar about our research, with demos (RAG and FractalMath) and metrics. https://t.co/oFEeEJj1F9
Вышел наш доклад в сообществе YNDX Family!
За 30 минут очень подробно рассказали о возможностях FractalMath - ИИ агентов в решении задачек, которые даже ChatGPT тянет нестаби��ьно.
Материал подготовлен на основе онлайн-встречи YNDX Family
https://t.co/EiGPdCNjyv
Introducing FractalGPT multi-agent Ai technology capable to build cooperative, decentralised Ai landscape. Check video with step by step historical Ai agents review, our agentic RAG system, metrics of efficiency
https://t.co/oFEeEJj1F9
@Lomashuk Cool. We at FractalGPT on the way to truly autonomous agents, not based on prompting. I just got back from Tbilisi yesterday, where I gave a report on our multi-agent system that solves math problems accurately at the https://t.co/WdEaQmBNwT AI conference.
AGI is coming.
Will it uplift humanity or centralize power? How can we create empowering, ethical AGI for all?
Let's explore a vision of trillions of decentralized AI agents working interconnectedly with people, forming what we call a Cybereconomy.
by @sgershuni 🧵👇
@omarsar0 Curious why FractalGPT is not here. FractalMath multi-agent Ai system has been accepted on OpenTalks international conference, with SOTA accuracy 100% on MultiArith dataset, outperforming ChatGPT with ANY prompting technique (arithmetic reasoning).
https://t.co/cZdDcFlUun
FractalMath multi-agent Ai system has been accepted on OpenTalks international conference, as first with SOTA accuracy 100% on MultiArith dataset, outperforming ChatGPT with ANY prompting technique (arithmetic reasoning).
https://t.co/v4ZT4Yrat6
@arankomatsuzaki Aran, do you know that FractalMath multi-agent Ai system has been accepted on OpenTalks international conference, as first with SOTA accuracy 100% on MultiArith dataset, outperforming ChatGPT with ANY prompting technique (arithmetic reasoning).
https://t.co/v4ZT4Yrat6
LLMs for Mathematical Reasoning
Introduces an overview of research developments in LLMs for mathematical reasoning.
Discusses advancements, capabilities, limitations, and applications to inspire ongoing research on LLMs for Mathematics.
@omarsar0 Elvis, do you know that FractalMath has been accepted on OpenTalks Ai conference, as first multi-agent system for Arithmetic reasoning. I assume you should add it to review. Here agenda:
https://t.co/tKYbt9LDSG