Jacob Morrison

yacan1585's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 10 days ago

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Collection

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes. • 42 items • Updated about 13 hours ago • 26

liked a Space 18 days ago

Running

38

NSFW ERP Benchmark

🌍

38

Testing local LLM models for unhinged Erotic Role-Play

upvoted a collection about 1 month ago

Gemma 3 - Reasoning/Thinking Models (incl uncensored)

Collection

Fine tunes (most uncensored) of Gemma3s to add reasoning/thinking. Increases output and image processing quality and general model metrics. • 26 items • Updated 18 days ago • 14

upvoted a collection about 2 months ago

Abliterated models

Collection

14 items • Updated 20 days ago • 4

reactedto YatharthS's post with 🚀 2 months ago

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/NovaSR
Space to try it: YatharthS/NovaSR
Github repo: https://github.com/ysharma3501/NovaSR

See translation

• 
• 
• 
• 5 replies

·

🚀

18

18

🔥

6

6

+

Reply

upvoted a collection 4 months ago

The Bestiary

Collection

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated Nov 16, 2025 • 105

upvoted a collection 8 months ago

VoiceCore

Collection

VoiceCore - Next-Gen Japanese Voice AI Agent model • 4 items • Updated Aug 12, 2025 • 1