Lucas Vieira

luksamuk's activity

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

liked a model about 12 hours ago

PrunaAI/Pruna-Qwen-Image-2.1

Text-to-Image • Updated about 18 hours ago • 896 • 57

liked a model about 18 hours ago

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

Image-Text-to-Text • 35B • Updated about 6 hours ago • 636 • 2

liked 3 models 1 day ago

audio-cpp/Nemotron-3-Diarization-GGUF

Voice Activity Detection • 99.3M • Updated 1 day ago • 1k • 8

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

Image-Text-to-Text • 36B • Updated about 6 hours ago • 201 • 2

realrebelai/Ming-Image_GGUFs

Text-to-Image • 6B • Updated about 14 hours ago • 3.97k • 11

reacted to medmekk's post with ❤️ 2 days ago

view post

Post

4292

🚀 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 2 days ago

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

Text-to-Image • Updated 3 days ago • 2.53k • 49

Viggle/Qwen-Image-2.1-viggle-turbo

Text-to-Image • 7B • Updated about 4 hours ago • 47.9k • 197

upvoted a collection 3 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 6 models 3 days ago

jaredpalmer/kev-0.5b

Text Classification • Updated 4 days ago • 1.39k • 48

AikidoSec/altar-1

Text Generation • 501B • Updated 5 days ago • 1.32k • 171

convaiinnovations/laya

Text Classification • 0.4B • Updated 1 day ago • 3.5k

SC117/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF

Image-Text-to-Text • 0.4B • Updated Jul 29 • 58.1k • 131

ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUF

Image-Text-to-Text • 9B • Updated 3 days ago • 15.7k • 22

XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B

Image-Text-to-Text • 9B • Updated 3 days ago • 6.65k • 448

liked 5 models 4 days ago

paradigma-inc/limite-1b-violetto

Text Generation • 1B • Updated 3 days ago • 2.32k • 64

UT-IFML/dQwen3.5-2B-Base

Text Generation • 2B • Updated 1 day ago • 1.4k • 5

IFM/K2-Horizon-MoVA-36B-A4B-GGUF

Text Generation • 37B • Updated 3 days ago • 21.2k • 127

moondream/parakeet-redux

Automatic Speech Recognition • 0.1B • Updated 2 days ago • 1.05k • 149

WarmBloodAban/Qwen-Image-2.1-LoRAs

Text-to-Image • Updated 4 days ago • 3.77k • 80