Open Source

“Smaug-72B – The Best Open Source Model In The World – Top of Hugging LLM LeaderBoard!! Smaug72B from Abacus AI is available now on Hugging Face, is on top of the LLM leaderboard, and is the first model with an average score of 80!! In other words, it is the world’s best… https://t.co/CGHawmLhqI” / X – https://twitter.com/bindureddy/status/1754665925834690907

Meet ‘Smaug-72B’: The new king of open-source AI | VentureBeat – https://venturebeat.com/ai/meet-smaug-72b-the-new-king-of-open-source-ai/

“Alibaba announces Qwen 1.5! 🎊 -> 6 model sizes, from 0.5B upto 72B. -> Beats Claude 2.1, GPT-3.5-Turbo and Mixtral. -> All models support 32K context length. -> Base, chat, and quantized weights available. @ollama run qwen:0.5b 0.5B is lightning fast on my M1 ⚡️ https://t.co/fSBJJgAOI4” / X – https://twitter.com/Prince_Canuma/status/1754566374960107682

“LM Studio v0.2.13 is available now! What’s New: – 🚀 Support for Qwen 1.5! (0.5B, 1.8B, 4B, 7B, 72B) And: – 🤖📌 Pin models to the top of the list – 💬📌 Pin chats, too Download from https://t.co/LSyzX5KStY (Mac / Windows)” / X – https://twitter.com/LMStudioAI/status/1754547632972738978

“🎉Happy to announce the release of Qwen1.5! This time, we directly opensource new models of 6 sizes, 0.5B, 1.8B, 4B, 7B, 14B, and 72B (including base, chat, AWQ, GPTQ, GGUF)! From small to huge! Blog: https://t.co/tsj64ZXuJ7 GitHub: https://t.co/yjcdGalMCD HF:… https://t.co/Cvs1NWAzbV” / X – https://twitter.com/JustinLin610/status/1754538215959335100 

Introducing Qwen1.5 | Qwen – https://qwenlm.github.io/blog/qwen1.5/ 

OpenAI compatibility · Ollama Blog –  

Ollama now has built-in compatibility with the OpenAI Chat Completions API, making it possible to use more tooling and applications with Ollama locally.

https://ollama.com/blog/openai-compatibility

How we got fine-tuning Mistral-7B to not suck: Helix Project Report, Feb 2024 – https://helixml.substack.com/p/how-we-got-fine-tuning-mistral-7b 

Constitutional AI with Open LLMs – https://huggingface.co/blog/constitutional_ai

Open LLM Leaderboard – a Hugging Face Space by HuggingFaceH4 – https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard

[2211.05100] BLOOM: A 176B-Parameter Open-Access Multilingual Language Model – https://arxiv.org/abs/2211.05100 

Open Language Models (OLMos) and the LLM landscape – https://www.interconnects.ai/p/olmo

“.@deepseek_ai is the best open source code generation model. Just announced: their next code model is based on MoE for even more efficient inference. Checkout their 16B MoE Chat performance gap: Now imagine that efficiency jump for code: Honestly, I can’t wait 🙌 https://t.co/jYFdElmtp0” / X – https://twitter.com/RickLamers/status/1755005364498743591 

OLMo: Open Language Model. A State-Of-The-Art, Truly Open LLM and… | by AI2 | Feb, 2024 | AI2 Blog – https://blog.allenai.org/olmo-open-language-model-87ccfc95f580 
Vision models · Ollama Blog – https://ollama.com/blog/vision-models