MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases Paper β’ 2402.14905 β’ Published Feb 22, 2024 β’ 134 β’ 13
view article Article The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare +1 Apr 19, 2024 β’ 189
view post Post 5373 Yet another rewarding week in Open Source AI:1. Google dropped Gemma 27B & 9B - The best open (commercially permissive) LLM out there, according to LYMSYS. google/gemma-2-release-667d6600fd5220e7b967f3152. Mars5 TTS - Text to Speech with insane prosodies control & voice cloning. CAMB-AI/MARS5-TTS3. Meta shipped LLM Compiler - beats GPT 4 on code optimisation and compiler reasoning. facebook/llm-compiler-667c5b05557fe99a9edd25cb4. Arcee-Spark - Qwen2 7B (w/ merging) fine-tuned further to beat GPT 3.5 on MT Bench. arcee-ai/Arcee-Spark5. Gemini Nano out in the wild in Chrome - On device LLM with just 2 lines of code (fully offline)6. Fal released a fully Open Source GAN based Super-Resolution model (with second version already cooking) fal/AuraSR7. NYU release Cambrian 1 - Vision Multimodal LLM that beats pretty much all other closed source competition 8-34B model size nyu-visionx And.. much more like Open LLM Leaderboard got a major update, LYMSYS released Chat Vision Arena, OpenAI released a paper on CriticGPT!What a lovely week, canβt wait for the next to see what the community is up to! Put it down in comments if I missed something π₯ 1 reply Β· π₯ 22 22 π 4 4 + Reply
Running Featured 558 Vision Arena (Testing VLMs side-by-side) πΌ 558 Display image analysis results
Runtime error Featured 161 DocOwl π 161 Interact with documents and images to get explanations and answers
HuggingFaceM4/idefics-80b-instruct Text Generation β’ 80B β’ Updated Oct 12, 2023 β’ 2.18k β’ 189
Running on Zero Featured 608 StoryDiffusion π 608 Generate images from text prompts with optional reference images
Running on Zero Featured 5.34k IllusionDiffusion π 5.34k Generate stunning high quality illusion artwork
Running Featured 1.12k OpenVoice π€ 1.12k Generate customized speech from text using a reference audio