Downloads · 30 days
8
27% of all-time downloads
egopi-axis2-native28-human-fp24-split-30k-mlxp-20260923
junbrro/egopi-axis2-native28-human-fp24-split-30k-mlxp-20260923
egopi-axis2-native28-human-fp24-split-30k-mlxp-20260923 is a machine learning model from junbrro. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Final step: 30000. Source: junhyeong-axis2-native-human-split-30k-260923-r1.
All-time downloads
30
Public
Parameters
6.9B
13.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.8 GB · 100%
At a glance
- Model type
- RLDX-1
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- ee90090d
Model card
From the Hugging Face model README
Arm 2 native OpenArm and Human FP24 separate-embodiment cotrain
Final step: 30000. Source: junhyeong-axis2-native-human-split-30k-260923-r1.
Final model weights and configuration only; optimizer/RNG state excluded. Original configuration is preserved, including source-cluster paths. Remap paths before use. Bundled actlat/ contains the action tokenizer when applicable.
PT-IMG. Robot native28 general_embodiment slot 0; Human HaWoR FP24 slot 35. No action tokenizer, cog adapter, CogAlign, or persistent language. Robot deploy uses native28; do not use the PRQ or FP24 robot decoder.
- Type
- RLDX-1
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026