Downloads · 30 days
0
tmax-ornith-397b
zhiyuanhusf/tmax-ornith-397b
tmax-ornith-397b is a machine learning model from zhiyuanhusf. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
Full-parameter DPPO checkpoints trained on allenai/tmax-15k-open-instruct.
Access
Public
Updated Jul 19, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 70%
At a glance
- Library
- transformers
- License
- other
- Access
- Public
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026
- SHA
- c8b65ec0
Base models
Model card
From the Hugging Face model README
TMax Ornith-1.0-397B DPPO
Full-parameter DPPO checkpoints trained on allenai/tmax-15k-open-instruct.
global_stepNbranches contain resumable DeepSpeed state. Only the newest five state branches are retained.step_Nbranches contain merged Hugging Face model weights. All merged branches are retained.maincontains metadata only.
Training uses nine 8xH200 learner nodes with ZeRO-3, CPU optimizer offload, and sequence parallelism, plus one 8xH200 tensor-parallel vLLM rollout node. Sampling uses temperature 1.0 and top-p 1.0.
- Library
- transformers
- License
- other
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026