Lucas Vieira

luksamuk's activity

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

liked a model about 10 hours ago

DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF

Text Generation • 3B • Updated 2 days ago • 4.64k • 83

liked a model about 21 hours ago

mudler/Nemotron-3-Diarization-GGUF

99.3M • Updated 1 day ago • 41 • 1

liked a model 1 day ago

SupersonicLabs/Julia-1

Text Classification • 0.1B • Updated 1 day ago • 274 • 184

liked a dataset 2 days ago

XiaomiMiMo/MiMo-V2.6-RL-oss

Viewer • Updated 2 days ago • 7.78k • 8.29k • 421

liked 5 models 2 days ago

Logolabs/agate-preview-001

Text-to-Image • Updated 2 days ago • 80 • 16

AIInstituteLNCC/manaca-1b-instruct

Text Generation • 2B • Updated 16 days ago • 1.44k • 6

AIInstituteLNCC/manaca-1b-base

Text Generation • 2B • Updated 27 days ago • 2.38k • 38

prism-ml/Ternary-Bonsai-2-27B-gguf

Text Generation • 27B • Updated 2 days ago • 3.34M • 2.19k

alibaba-pai/Qwen-Image-2.1-Fun-Acc-LoRAs

Text-to-Image • Updated 3 days ago • 2.76k • 28

liked 2 models 3 days ago

PrunaAI/Pruna-Qwen-Image-2.1

Text-to-Image • Updated 3 days ago • 8.15k • 105

IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF

Image-Text-to-Text • 35B • Updated about 23 hours ago • 1.79k • 4

liked 3 models 4 days ago

audio-cpp/Nemotron-3-Diarization-GGUF

Voice Activity Detection • 99.3M • Updated 1 day ago • 3.77k • 12

IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-NanoPlus-GGUF

Image-Text-to-Text • 36B • Updated about 23 hours ago • 1.19k • 2

realrebelai/Ming-Image_GGUFs

Text-to-Image • 6B • Updated 3 days ago • 4.87k • 15

reacted to medmekk's post with ❤️ 5 days ago

view post

Post

4314

🚀 Introducing Halo 1.0

Today, we are open-sourcing Halo, the training framework we use to train every model at White Circle.

It comes with:
🧠 Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillation
🤖 Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use
⚡ ~2.8× TRL throughput on 8× B300 (EP+FSDPv2, FA4, fp8/fp4)
🤗 Dense HF models + 15 MoE families (Qwen, GLM, Mistral, DeepSeek-V4…)
🛠️ One halo command, prebuilt Docker images, and docs for humans and agents

💻 https://github.com/whitecircle/halo

Try it and tell us what you're training

See translation

• 
• 1 reply

·

🚀

9

9

❤️

4

4

+

Reply

liked 2 models 5 days ago

e-n-v-y/Qwen-Image-2.1-Fix

Text-to-Image • Updated 5 days ago • 4.18k • 56

Viggle/Qwen-Image-2.1-viggle-turbo

Text-to-Image • 7B • Updated 3 days ago • 133k • 337

upvoted a collection 5 days ago

Zeroshot Classifiers

Collection

These are my current best zeroshot classifiers. Some of my older models are downloaded more often, but the models in this collection are newer/better. • 12 items • Updated Jan 6, 2025 • 158

liked 2 models 5 days ago

jaredpalmer/kev-0.5b

Text Classification • Updated 7 days ago • 1.49k • 58

AikidoSec/altar-1

Text Generation • 501B • Updated 7 days ago • 1.62k • 186