XiaomiMiMo/MiMo-V2.6-RL-oss
Viewer ā¢ Updated ā¢ 7.78k ā¢ 99.3k ā¢ 873
yes
Gamination
AI & ML interests
None yet
Recent Activity
liked a dataset 10 days ago
XiaomiMiMo/MiMo-V2.6-RL-oss liked a model 12 days ago
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF liked a model 14 days ago
ukisai/Swift-Bonsai-2-GGUFOrganizations
None yet
liked a
dataset 10 days ago
liked a
model 12 days ago
liked a
model 14 days ago
liked 2
models 15 days ago
liked a
model 16 days ago
reacted to medmekk's post with ā¤ļø 17 days ago
Post
4363
š 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:
š§ Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillation
š¤ Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use
ā” ~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 agents
š» https://github.com/whitecircle/halo
Try it and tell us what you're training
Today, 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, distillation
š¤ Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use
ā” ~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 agents
š» https://github.com/whitecircle/halo
Try it and tell us what you're training
- 1 reply
liked a
model 17 days ago
liked 2
models 20 days ago
liked 2
models 21 days ago
liked a
model 23 days ago
liked a
model 24 days ago
liked a
model 26 days ago
liked 2
models 27 days ago
liked 2
models 29 days ago
its THE model for 8gb vram users
ā¤ļø 1
8
#11 opened about 1 month ago
by Gamination