Roy T

Aexand's activity

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

liked a model about 21 hours ago

alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF

Image-Text-to-Text • 120k • Updated 1 day ago • 3.72k • 45

liked 2 models 6 days ago

ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Image-Text-to-Text • 177B • Updated 12 days ago • 186k • 115

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Image-Text-to-Text • 177B • Updated 7 days ago • 2.24M • 621

liked 4 models 13 days ago

jan1k/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-NVFP4

Image-Text-to-Text • 35B • Updated 13 days ago • 557 • 1

jan1k/Qwen3.8-27B-Uncensored-Genesis-NVFP4

Text Generation • 27B • Updated 13 days ago • 599 • 3

Altworld/Hemmingway-1

Text Generation • 27B • Updated 4 days ago • 10.2k • 836

convaiinnovations/laya

Text Classification • 0.4B • Updated 2 days ago • 11.7k • 5.25k

reacted to medmekk's post with 🚀 13 days ago

view post

Post

4349

🚀 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 13 days ago

ChrisColeTech/krea2-turbo-uncensored-v1.1-FP8

Image-to-Image • 13B • Updated 13 days ago • 46.1k • 66

pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF

8B • Updated 12 days ago • 202k • 342

liked a model 14 days ago

abenzerps/Qwen-Image-2.1-Uncensored-GGUF

Text-to-Image • 7B • Updated 8 days ago • 1.64M • 3.28k

liked a model 18 days ago

prism-ml/Ternary-Bonsai-2-27B-mlx-2bit

Text Generation • 27B • Updated 13 days ago • 73.3k • 428

liked 2 models 20 days ago

apodex/Apodex-1.1-mini-NVFP4

Text Generation • 20B • Updated Aug 26 • 7.17k • 36

apodex/Apodex-1.1-mini

Text Generation • 36B • Updated Aug 26 • 4.62k • 152

liked a model 25 days ago

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF

Image-Text-to-Text • 27B • Updated 19 days ago • 225k • 212

liked 4 models 26 days ago

deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated 5 days ago • 869k • • 4.13k

peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP

Image-Text-to-Text • 36B • Updated 18 days ago • 289k • 193

peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated 26 days ago • 36.4k • 87

agentionai/Signal-3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated 20 days ago • 27.8k • 98

liked a model 27 days ago

nex-agi/Nex-N2.5-mini

Text Generation • 35B • Updated 28 days ago • 10.4k • 854