Nexusflow team checking in from #NeurIPS2023. Want to check out fun copilots using our technologies? Come to Booth 423 and hang out with folks behind NexusRaven-V2 (t.ly/LRJrq) and Starling LLMs (t.ly/oipxe). On Friday, Dec. 15, we’ll present

Excited to share that NexusRaven-V2 was featured in AI at Meta's Llama newsletter this morning!📩 If you’re new here, NexusRaven-V2 is a 13B function calling LLM surpassing GPT-4 in real-world zero-shoot tool use. 💻 Learn more about NexusRaven-V2’s capabilities:

Thank you, @deci_ai and harpreet, for featuring NexusRaven-V2 in the top 10 compact & robust models. Stay tuned for what's to come for the community in 2024!

Thank you, Ben Lorica 罗瑞卡 for extending your platform to us and engaging in fantastic conversation!🎙 Excited to contribute to the foundation of #AI Agents! 🎧LISTEN: bit.ly/3vGpU4m

🚀 Exciting breakthrough in LLM reliability! 🧠NexusRaven-V2, our cutting-edge function-calling LLM, has set a new standard in minimizing AI hallucinations, surpassing GPT-4's performance in a recent third-party independent research benchmark. Dive into our latest blog post to

🚀 Presenting Starling-LM-7B-beta, our cutting-edge 7B language model fine-tuned with RLHF! 🌟 Also introducing Starling-RM-34B, a Yi-34B-based reward model trained on our Nectar dataset, surpassing our previous 7B RM in all benchmarks. ✨ We've fine-tuned the latest Openchat

📢 Powerful information extraction app built by Stefano Fiorucci and Haystack team using #NexusRaven-V2 LLM for function calling! 🔥 We are thrilled to empower high-quality Gen AI apps with our compact LLMs and toolings.

🚀 Presenting Starling-LM-7B-beta, our new cutting-edge 7B language model fine-tuned with RLHF! 🌟 Also introducing Starling-RM-34B, the workhorse Reward Model behind the Starling-LM-7B-beta, ranking #1 in the latest RewardBenchmark from Nathan Lambert and the AI2 team.

Have we really squeezed out the capacity of a compact chat model? Thrilled to see our latest open model, Starling-7B, ranks 13th among all models in Chatbot Arena! 🚀 As a 7B model, Starling surpasses larger open and proprietary models, including Claude-2, GPT-3.5-Turbo, Gemini

🔍 What Starling-LM-7B-beta's excellent performance tells us about benchmarks I compared the performance of Nexusflow's model across various benchmarks. In the Chatbot Arena Leaderboard (huggingface.co/spaces/lmsys/c…), this 7B model impressively outperforms many larger models,

Apple MLX: considering the power of Starling-LM-7B-beta from Nexusflow and its ranking on lmsys.org Chatbot Arena Leaderboard, I converted and uploaded 4bit and 8bit versions on HuggingFace mlx-community! Performance 🔥 on M2 Ultra 76GPU: - 4bit: tokens/sec Prompt: 158 -

🆕 Check out the recent update of 𝕎𝕚𝕝𝕕𝔹𝕖𝕟𝕔𝕙! We have included a few more models including DBRX-Instruct Databricks and StarlingLM-beta (7B) Nexusflow which are both super powerful! DBRX-Instruct is indeed the best open LLM; Starling-LM 7B outperforms a lot of even

Super excited to launch this course with Andrew Ng ! Function calling lies at the heart of AI agents but it is tricky to produce highly accurate and reliable results. Come and learn from Venkat !

🚀 Exciting News! Check out our brand new short course on function calling, the foundation for AI agents, created by our CEO Jiantao Jiao and founding engineer Venkat, in collaboration with DeepLearning.AI and the legendary Andrew Ng 🌟 #AI #GenAI #NexusRaven

🎉Big kudos to @MetaAI for advancing open models & tool use! Honored that Nexus Function Calling benchmark powered the evaluation of Llama 3.1 405B. Explore our FC benchmark on GitHub: github.com/nexusflowai/Ne…. Stay tuned for more breakthroughs from us soon! #ToolUse

🎉 Exciting News: Athene-70B Claims #8 Position on Chatbot Arena! In numerous business scenarios, user experience and customer satisfaction are very important. Chatbot Arena has established itself as the gold standard for assessing user preferences for LLMs. As a model

Having worked on RLHF for so long, I know how challenging it is to create an LLM that answers so many difficult questions in a satisfactory manner. Congrats Google DeepMind !