Downloads · 30 days
17
6% of all-time downloads
deepswe-k8s-sync-S0b16-c256-replace-tokenexact-step175
aqbond/deepswe-k8s-sync-S0b16-c256-replace-tokenexact-step175
deepswe-k8s-sync-S0b16-c256-replace-tokenexact-step175 is a text generation model from aqbond. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
FSDP-merged Hugging Face weights after training step 175.
All-time downloads
281
Public
Parameters
32.8B
65.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors65.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026
- SHA
- 8498680a
Try a prompt
Base models
Model card
From the Hugging Face model README
deepswe-k8s-sync-S0b16 replace-tokenexact step 175
FSDP-merged Hugging Face weights after training step 175.
- Experiment:
deepswe-k8s-sync-S0b16-c256-replace-tokenexact-141to179-20260826-111352 - Recipe: same-step trajectory repair (gpt-5.5 key-fork + antidrown, 4 failures × k=4) then S0b16 sync PPO
- Checkpoint source:
outputs_all/checkpoints/.../global_step_175/actor - Paired baseline repo:
aqbond/deepswe-k8s-sync-S0b16-c256-step140to180-step175
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026