Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Paper β’ 2502.06703 β’ Published 18 days ago β’ 140
Running on Zero 1.84k 1.84k Chat With Janus-Pro-7B π A unified multimodal understanding and generation model.
Running 223 223 Llama 3.2 Reasoning WebGPU π§ Small and powerful reasoning LLM that runs in your browser
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B Text Generation β’ Updated 5 days ago β’ 1.26M β’ β’ 954
Running 133 133 SmolLM 360M Instruct WebGPU π A blazingly fast and powerful AI chatbot that runs locally.
view post Post 5965 Reasoning SmolLM2 ππ―Fine-tuning SmolLM2 on a lightweight synthetic reasoning dataset for reasoning-specific tasks. Future updates will focus on lightweight, blazing-fast reasoning models. Until then, check out the blog for fine-tuning details.π₯Blog : https://huggingface.co/blog/prithivMLmods/smollm2-ftπΌ Models :+ SmolLM2-CoT-360M : prithivMLmods/SmolLM2-CoT-360M+ Reasoning-SmolLM2-135M : prithivMLmods/Reasoning-SmolLM2-135M+ SmolLM2-CoT-360M-GGUF : prithivMLmods/SmolLM2-CoT-360M-GGUFπ€ Other Details :+ Demo : prithivMLmods/SmolLM2-CoT-360M+ Fine-tune nB : prithivMLmods/SmolLM2-CoT-360M See translation π 19 19 π₯ 13 13 β€οΈ 7 7 π 5 5 + Reply