Running on Zero 32 This Cute Dragon Girl Doesnt Exist π’ 32 Generate unique anime-style dragon girl images from text prompts
iFairy: the First 2-bit Complex LLM with All Parameters in {pm1, pm i} Paper β’ 2508.05571 β’ Published Aug 7, 2025 β’ 1
view post Post 3925 I just released NovaSR, a tiny 52kb audio upsampler that can enhance 3600 seconds of muffled 16khz audio in to clearer 48khz audio in just 1 second!NovaSR can- Enhance TTS model quality.- Restore poor quality datasets.- Work on any device(just 52kb which is smaller than a 3 second audio file!)Model: YatharthS/NovaSRSpace to try it: YatharthS/NovaSRGithub repo: https://github.com/ysharma3501/NovaSR See translation 4 replies Β· π 18 18 π₯ 6 6 + Reply
mradermacher/qwen3-50m-insomnia-therapist-GGUF Text Generation β’ 71.6M β’ Updated Jul 12, 2025 β’ 98 β’ 1
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method β’ 24 items β’ Updated about 11 hours ago β’ 89