alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF Image-Text-to-Text ⢠120k ⢠Updated 3 days ago ⢠15.1k ⢠73
ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text ⢠177B ⢠Updated about 5 hours ago ⢠223k ⢠135
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text ⢠177B ⢠Updated 9 days ago ⢠3.08M ⢠690
jan1k/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-NVFP4 Image-Text-to-Text ⢠35B ⢠Updated 15 days ago ⢠572 ⢠1
jan1k/Qwen3.8-27B-Uncensored-Genesis-NVFP4 Text Generation ⢠27B ⢠Updated 15 days ago ⢠629 ⢠3
view post Post 4359 š Introducing Halo 1.0Today, we are open-sourcing Halo, the training framework we use to train every model at White Circle.It comes with: š§ Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillationš¤ Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool useā” ~2.8Ć TRL throughput on 8Ć B300 (EP+FSDPv2, FA4, fp8/fp4)š¤ Dense HF models + 15 MoE families (Qwen, GLM, Mistral, DeepSeek-V4ā¦)š ļø One halo command, prebuilt Docker images, and docs for humans and agentsš» https://github.com/whitecircle/haloTry it and tell us what you're training See translation 1 reply Ā· š 9 9 ā¤ļø 4 4 + Reply
ChrisColeTech/krea2-turbo-uncensored-v1.1-FP8 Image-to-Image ⢠13B ⢠Updated 15 days ago ⢠46.9k ⢠69
abenzerps/Qwen-Image-2.1-Uncensored-GGUF Text-to-Image ⢠7B ⢠Updated 10 days ago ⢠1.82M ⢠3.56k
prism-ml/Ternary-Bonsai-2-27B-mlx-2bit Text Generation ⢠27B ⢠Updated 15 days ago ⢠75.7k ⢠433
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF Image-Text-to-Text ⢠27B ⢠Updated 21 days ago ⢠229k ⢠212
deepseek-ai/DeepSeek-V4.1-Flash Image-Text-to-Text ⢠763B ⢠Updated 7 days ago ⢠1.26M ⢠⢠4.22k
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP Image-Text-to-Text ⢠36B ⢠Updated 20 days ago ⢠349k ⢠203
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF Image-Text-to-Text ⢠35B ⢠Updated 28 days ago ⢠40.3k ⢠93