specimba

specimba's activity

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

New activity in specimba/nexus-os-v2-dualmode 5 days ago

Re: Final Followup

4

#2 opened 9 days ago by

Phase-Technologies

New activity in build-small-hackathon/NEXUS-Visual-Weaver 7 days ago

Update app.py

#5 opened 7 days ago by

specimba

Update app.py

#4 opened 7 days ago by

specimba

Upload 6 files

#3 opened 7 days ago by

specimba

New activity in caiovicentino1/wandering-arc-papers 7 days ago

The WANDERING arc: where an agent's decision to stop is known vs. controllable (6 papers + a tool)

🚀 1

1

#2 opened 8 days ago by

caiovicentino1

New activity in build-small-hackathon/NEXUS-Visual-Weaver 9 days ago

Upgrade to FLUX.2-klein-4B (Apache, 4B, sub-second) via Flux2KleinPipeline

#2 opened 9 days ago by

specimba

Fix ZeroGPU crash: import spaces first, real @spaces.GPU, FLUX.1-schnell

#1 opened 9 days ago by

specimba

New activity in Trendyol/Trendyol-TTS 9 days ago

HF Space Demo

❤️ 3

4

#1 opened 9 days ago by

atasoglu

New activity in specimba/nexus-os-v2-dualmode 10 days ago

Subject: Collaboration / Joining Xerv: Building Qubik (5B Edge Search Brain)

👀 1

3

#1 opened 10 days ago by

Phase-Technologies

commented a paper 10 days ago

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published Jan 28 • 50 •

6

New activity in build-small-hackathon/Darwin-35B-A3B-Opus 11 days ago

Fix Darwin 35B load: CPU offload flag + spaces pkg + persistent cache

#6 opened 11 days ago by

specimba

New activity in build-small-hackathon/Darwin-35B-A3B-Opus 12 days ago

Fix: add spaces dependency + force rebuild

#5 opened 12 days ago by

specimba

Fix: Move model load inside @spaces.GPU to prevent CPU OOM crash

#4 opened 12 days ago by

specimba

New activity in K0D3IN/gemma-3-1B-it-heretic 13 days ago

keep going on

1

#1 opened 13 days ago by

specimba

New activity in prism-ml/bonsai-image-binary-4B-mlx-1bit 13 days ago

Hmm, pretty fast on RTX 3090 24 GB VRAM, though why censored?

2

#1 opened 13 days ago by

JLouisBiz

New activity in cb1c7/minicpm5-twitch-chat-style-space 13 days ago

need intelligence

1

#1 opened 13 days ago by

specimba

New activity in prism-ml/Bonsai-Image-Demo 19 days ago

Impressive, but...

1

#1 opened 19 days ago by

Gershwin69

New activity in huihui-ai/Huihui-gemma-4-E4B-it-abliterated 20 days ago

Model Repack

3

#1 opened 21 days ago by

Matthew3179

New activity in build-small-hackathon/Darwin-35B-A3B-Opus 22 days ago

PR #2 requirements: Remove llama.cpp, add transformers and full ML stack

1

#3 opened 24 days ago by

specimba

PR #2: Replace llama.cpp with transformers + spaces.GPU + temp grid

1

#2 opened 24 days ago by

specimba