Claude Fine Tune Distills - 1B to 42B - reg / uncensored. Collection Qwen, Mistral, Llama, LFM, OpenAI, Ernie and other models fine tuned on Claude Dataset(s) to improve and/or add reasoning/thinking to the model. β’ 44 items β’ Updated 1 day ago β’ 6
view post Post 3252 Made this with ByteDance's Seedance 2.0It's crazyyyyyyπ₯π₯π₯ See translation 1 reply Β· π₯ 9 9 + Reply
DavidAU/Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored Text Generation β’ 24B β’ Updated Jan 30 β’ 114 β’ 15
view post Post 2884 Now also with LTX-2 Detailer (Lightricks/LTX-2-19b-IC-LoRA-Detailer)Try it out: alexnasa/ltx-2-TURBO See translation π₯ 2 2 π 1 1 + Reply
view post Post 4546 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 5 replies Β· π 18 18 π₯ 6 6 + Reply
view post Post 4785 Happy New Years 2026! For next 365 days I will be commit to work on:- Document AI and OCR Automations- Voice Agents- Long Running Tasks - Durable Agents See translation 1 reply Β· π 16 16 + Reply
Dark MOEs - Mixture of Experts - Uncensored Creative Models Collection Listed in terms of most power ; including both GGUF and Source. Link to quants on source pages too. You can dial up or down the number of experts. β’ 23 items β’ Updated 13 days ago β’ 17