Serveurperso's picture

Serveurperso PRO

Serveurperso

·

https://www.serveurperso.com/ia

ServeurpersoCom

AI & ML interests

None yet

Recent Activity

updated a bucket about 17 hours ago

Serveurperso/install.sh

published a bucket 1 day ago

Serveurperso/install.sh

reacted to RiverRider's post with 🔥 7 days ago

🧠 New Space: MindReader-NLA — ask a frozen LM what it's thinking, in plain English. A trained Activation Verbalizer (~5–13M params, frozen backbone) over Qwen-2.5-7B, Llama-3.2-3B, and Gemma-2-2B. Three demos in one Space: Playground — sample K verbalizations of the layer-L hidden state and score how well each reproduces the original activation when fed back through the same frozen model (raw + anisotropy-centred cosine FVE). Live Thought Trace — stream a verbalization per token as the model writes, side-by-side with the generation. Steer-by-Editing — edit the verbalized thought, project it back into hidden-state space, and watch the continuation change. Runs on ZeroGPU. Try it: https://huggingface.co/spaces/RiverRider/srt-nla-demo Paper + code: https://github.com/space-bacon/SRT

View all activity

Organizations

buckets 1

Serveurperso/install.sh

models 5

Serveurperso/Qwen3-TTS-GGUF

Text-to-Speech • 0.9B • Updated 18 days ago • 3.38k • 2

Serveurperso/OmniVoice-GGUF

Text-to-Speech • 0.6B • Updated 29 days ago • 13.4k • 19

Serveurperso/ACE-Step-1.5-GGUF

0.7B • Updated Apr 14 • 51k • 64

Serveurperso/presets

Serveurperso/gemma-2-2b-it-LoRA

20.8M • Updated Mar 1, 2025 • 24

datasets 0

None public yet