With 480 downloads and 53 likes, it's gaining traction. The Gemma license ensures responsible use. If you need accurate Vietnamese ASR with streaming, this model is a solid choice. Try it out!
Meet QUAN-Transcribe-1.0: a new ASR model built for Vietnamese! It handles streaming audio and packs a CTC architecture on top of EmbeddingGemma-2. Perfect for real-time speech apps. #AI#SpeechRecognition
Why it matters: 5M parameters means fast inference and low resource use, perfect for edge or real-time apps. With 2.5k downloads and growing, it's proving to be a go-to for accessible time-series forecasting. Give it a try!
Meet Timestral-5M: a tiny but mighty time-series forecasting model from the team at Mistral AI. With 5M parameters, it's built to predict the future from your data, and it's already getting love with 2.5k downloads. Ready to dive in?
Why it matters: zero-shot classification with multimodal input is rare. Get fast, intuitive decisions without fine-tuning. 300 downloads show growing trust. Perfect for prototyping or production where speed and flexibility win.
Built on Qwen3.5 architecture with safetensors for safe loading. Feature extraction and zero-shot classification in one model. Multimodal vision means it handles images and text together. System-one style for fast, intuitive decisions.
Meet vllm-sr/d3-turbo: a zero-shot classification model built on Qwen3.5. With vision and multimodal support, it's a decision-making powerhouse for system-one thinking. 300 downloads and 55 likes already! 🚀
Use it for instant categorization without training data. Classify images, text, or both in one go. Perfect for content moderation, smart tagging, or real-time decision systems. Zero-shot means you define labels on the fly!
With 9,369 downloads and 62 likes, it's a rising star for uncensored AI. Runs smoothly on llama.cpp, integrates with Open WebUI, and delivers conversational depth. Try it for your next unfiltered project!
Meet Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF: a 27B powerhouse tuned for raw, unfiltered conversations. If you crave reasoning without guardrails, this GGUF model is your new playground. 9k+ downloads and counting!
160 Followers 1K FollowingOne equal temper of heroic hearts,
Made weak by time and fate, but strong in will
To strive, to seek, to find, and not to yield.
📸 Leica Q3 | 📱 Pixel 11 P
4K Followers 15 FollowingSoul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 (https://t.co/GSHup0ofja). Maintained by @cosmicstack
109K Followers 0 FollowingThe official home of Google's Gemma. Lightweight, state-of-the-art open models by Google DeepMind, built on Gemini tech. What will you build? 🚀💻
28K Followers 1K FollowingLLM. Local AI addict. Building @BenchLocalAI
DGX Spark workbench https://t.co/WN4i7q2y5m
Builds things nobody asked for. Benchmarks things for fun.
13K Followers 31 Followinghttps://t.co/zI71a4QB1W
https://t.co/QFKNuHms1N
[email protected]
Donation: Support our work on Ko-fi (https://t.co/gAtHKPSCHH)!
90K Followers 1K FollowingCo-founder and CTO at @huggingface 🤗. ML/AI for everyone, building products to propel communities fwd. @Stanford + @Polytechnique
83K Followers 144 FollowingHave questions, or building something cool with Cloudflare's Developer products? We're here to help. For help with your account please try @CloudflareHelp
82K Followers 145 FollowingAnnouncing new open source releases, exploring projects, sharing how we approach FOSS, and supporting communities around the world.
342K Followers 66 FollowingWe're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github