OpenChat (@openchatdev) 's Twitter Profile
OpenChat

@openchatdev

Advancing Open Source LLMs with Mixed Quality Data through offline RL-inspired C-RLFT. ⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀𝗣𝗿𝗼𝗷𝗲𝗰𝘁 𝗟𝗲𝗮𝗱: Guan Wang, @AlpayAriyak

ID: 1675709698333609985

linkhttp://huggingface.co/openchat calendar_today03-07-2023 03:35:14

58 Tweet

1,1K Takipçi

42 Takip Edilen

OpenChat (@openchatdev) 's Twitter Profile Photo

We achieved almost ideal MoE fine-tuning performance (equivalent to a dense model with the same active parameters). <10% overhead

OpenChat (@openchatdev) 's Twitter Profile Photo

🚀Announcing OpenChat-3.5 Update 0106: 𝗪𝗼𝗿𝗹𝗱’𝘀 𝗕𝗲𝘀𝘁 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲 𝟳𝗕 𝗟𝗟𝗠! Experience ChatGPT & Grok-level AI locally 💿! Surpassing Grok-0 (33B) across all 4 benchmarks and Grok-1 (???B) on average and 3/4 benchmarks 🔥. 🎯 This update mainly enhanced

🚀Announcing OpenChat-3.5 Update 0106: 𝗪𝗼𝗿𝗹𝗱’𝘀 𝗕𝗲𝘀𝘁 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲 𝟳𝗕 𝗟𝗟𝗠!

Experience ChatGPT &amp; Grok-level AI locally 💿! 

Surpassing Grok-0 (33B) across all 4 benchmarks and Grok-1 (???B) on average and 3/4 benchmarks 🔥. 

🎯 This update mainly enhanced
OpenChat (@openchatdev) 's Twitter Profile Photo

🚀Kudos to Hugging Face ! OpenChat-3.5 Update 0106 has landed on HuggingChat & Spaces! Explore now! Experience open-source AI at ChatGPT & Grok level! 🤗 HuggingChat: huggingface.co/chat 🌌 Spaces: huggingface.co/spaces/opencha… 🖥️ OpenChat UI: openchat.team

OpenChat (@openchatdev) 's Twitter Profile Photo

🚀 The World's First Gemma fine-tune based on openchat-3.5-0106 data and method (C-RLFT). Almost the same performance as the Mistral-based version. 6T tokens = secret recipe? HuggingFace: huggingface.co/openchat/openc…

OpenChat (@openchatdev) 's Twitter Profile Photo

🚀Introducing OpenChat 3.6 🌟Surpassed official Llama3-Instruct—with 1-2M synthetic data compared to ~10M human labels 🤫GPTs are close to limits—excel at generation but fall short at complex tasks 🎯We are training next gen—capable of deterministic reasoning and planning 🔗

🚀Introducing OpenChat 3.6

🌟Surpassed official Llama3-Instruct—with 1-2M synthetic data compared to ~10M human labels
🤫GPTs are close to limits—excel at generation but fall short at complex tasks
🎯We are training next gen—capable of deterministic reasoning and planning

🔗
OpenChat (@openchatdev) 's Twitter Profile Photo

Thrilled to see RSP featured at AAAI'25! This pioneering concept was a key inspiration for developing OpenChat! 🚀 #AI #AAAI25

Guan Wang (@makingagi) 's Twitter Profile Photo

🚀Introducing Hierarchical Reasoning Model🧠🤖 Inspired by brain's hierarchical processing, HRM delivers unprecedented reasoning power on complex tasks like ARC-AGI and expert-level Sudoku using just 1k examples, no pretraining or CoT! Unlock next AI breakthrough with

🚀Introducing Hierarchical Reasoning Model🧠🤖

Inspired by brain's hierarchical processing, HRM delivers unprecedented reasoning power on complex tasks like ARC-AGI and expert-level Sudoku using just 1k examples, no pretraining or CoT!

Unlock next AI breakthrough with
Guan Wang (@makingagi) 's Twitter Profile Photo

Will Sudoku become the MNIST for reasoning? Simple rules, clear structure, unique solutions—yet surprisingly challenging for modern LLMs, often requiring explicit trial-and-error to solve. huggingface.co/datasets/sapie…