Open-weight model
ps4mas-three-stage-11topo-20261014
by Yitia yinita/ps4mas-three-stage-11topo-20261014
ps4mas-three-stage-11topo-20261014 is an open-weight model from Yitia. Its published files total 4.0 GB.
Rank-16 LoRA adapters on Qwen/Qwen3.5-4B (revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a), three methods: grpoabc, grpoc, grpocurriculumabc.
Parameters—
Context—
Weights2.0 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
Rank-16 LoRA adapters on Qwen/Qwen3.5-4B (revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a), three methods: grpoabc, grpoc, grpocurriculumabc. - /checkpoint-XXXXXX/: adapter, receipt, trainingstate (every 25 GRPO groups + final) - /periodicdev/step-XXXXXX/: periodic dev evaluation (1056 cells, PENGUIN+CASTLE x 11 topologies, JEV-1.13.0 judge); summary.json + results.tar.gz Periodic dev is monitoring only; the fixed final checkpoint is the comparison endpoint. W&B: yinita/ps4mas-0922-training.
Excerpt from the card by Yitia.
Identity and Version
- Repository
- yinita/ps4mas-three-stage-11topo-20261014
- Publisher
- Yitia
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- jev
- Revision
- 00b1764cae09716738305bef14cbbe30f475e8d8
- First published
- 2026-10-16
- Last updated
- 2026-10-18
Files and Weights
206 files, 4.0 GB in total. The weights are 24 files totalling 2.0 GB in safetensors.
Weights24 files · 2.0 GB
Configuration156 files · 2.8 MB
Documentation1 file · 666 B
Other24 files · 1.9 GB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| grpo_abc/checkpoint-000025/adapter_model.safetensors | Weights | 85.0 MB | 4d86dff04c0a |
| grpo_abc/checkpoint-000050/adapter_model.safetensors | Weights | 85.0 MB | 4973c946c58b |
| grpo_abc/checkpoint-000075/adapter_model.safetensors | Weights | 85.0 MB | fb2a5e63bdd6 |
| grpo_abc/checkpoint-000100/adapter_model.safetensors | Weights | 85.0 MB | 89b38644bed1 |
| grpo_abc/checkpoint-000125/adapter_model.safetensors | Weights | 85.0 MB | d78092ce6f7b |
| grpo_abc/checkpoint-000150/adapter_model.safetensors | Weights | 85.0 MB | 3fda925129c6 |
| grpo_abc/checkpoint-000175/adapter_model.safetensors | Weights | 85.0 MB | e58c400fd312 |
| grpo_abc/checkpoint-000198/adapter_model.safetensors | Weights | 85.0 MB | bbb2f52b5132 |
| grpo_c/checkpoint-000025/adapter_model.safetensors | Weights | 85.0 MB | bc1a326383a0 |
| grpo_c/checkpoint-000050/adapter_model.safetensors | Weights | 85.0 MB | a7c11ed45bf8 |
| grpo_c/checkpoint-000075/adapter_model.safetensors | Weights | 85.0 MB | 2ba5ee57bad9 |
| grpo_c/checkpoint-000100/adapter_model.safetensors | Weights | 85.0 MB | f7f1f3c9c57e |
| grpo_c/checkpoint-000125/adapter_model.safetensors | Weights | 85.0 MB | be04d76eb1d2 |
| grpo_c/checkpoint-000150/adapter_model.safetensors | Weights | 85.0 MB | 420c3dbfa1f8 |
| grpo_c/checkpoint-000175/adapter_model.safetensors | Weights | 85.0 MB | ced1f945456c |
| grpo_c/checkpoint-000198/adapter_model.safetensors | Weights | 85.0 MB | 183074a5c225 |
| grpo_curriculum_abc/checkpoint-000025/adapter_model.safetensors | Weights | 85.0 MB | 1be3f1e3807a |
| grpo_curriculum_abc/checkpoint-000050/adapter_model.safetensors | Weights | 85.0 MB | 10a2b9bb2f25 |
| grpo_curriculum_abc/checkpoint-000075/adapter_model.safetensors | Weights | 85.0 MB | 549f07a458d3 |
| grpo_curriculum_abc/checkpoint-000100/adapter_model.safetensors | Weights | 85.0 MB | a07f7722050c |
| grpo_curriculum_abc/checkpoint-000125/adapter_model.safetensors | Weights | 85.0 MB | 4255db83c663 |
| grpo_curriculum_abc/checkpoint-000150/adapter_model.safetensors | Weights | 85.0 MB | c22038b96bd5 |
| grpo_curriculum_abc/checkpoint-000175/adapter_model.safetensors | Weights | 85.0 MB | a8ae23a80624 |
| grpo_curriculum_abc/checkpoint-000198/adapter_model.safetensors | Weights | 85.0 MB | d75fcf8b741b |
| grpo_abc/checkpoint-000025/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000025/dev25_milestone.json | Configuration | 176 B | — |
| grpo_abc/checkpoint-000025/receipt.json | Configuration | 310 B | — |
| grpo_abc/checkpoint-000050/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000050/async_dev25_milestone.json | Configuration | 265 B | — |
| grpo_abc/checkpoint-000050/receipt.json | Configuration | 310 B | — |
| grpo_abc/checkpoint-000075/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000075/async_dev25_milestone.json | Configuration | 265 B | — |
| grpo_abc/checkpoint-000075/receipt.json | Configuration | 310 B | — |
| grpo_abc/checkpoint-000100/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000100/async_dev25_milestone.json | Configuration | 266 B | — |
| grpo_abc/checkpoint-000100/receipt.json | Configuration | 311 B | — |
| grpo_abc/checkpoint-000125/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000125/async_dev25_milestone.json | Configuration | 266 B | — |
| grpo_abc/checkpoint-000125/receipt.json | Configuration | 311 B | — |
| grpo_abc/checkpoint-000150/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000150/async_dev25_milestone.json | Configuration | 266 B | — |
| grpo_abc/checkpoint-000150/receipt.json | Configuration | 311 B | — |
| grpo_abc/checkpoint-000175/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000175/async_dev25_milestone.json | Configuration | 266 B | — |
| grpo_abc/checkpoint-000175/receipt.json | Configuration | 311 B | — |
| grpo_abc/checkpoint-000198/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_abc/checkpoint-000198/receipt.json | Configuration | 311 B | — |
| grpo_abc/periodic_dev/step-000025/completion.json | Configuration | 203 B | — |
| grpo_abc/periodic_dev/step-000025/run.json | Configuration | 807 B | — |
| grpo_abc/periodic_dev/step-000025/summary.json | Configuration | 13.4 KB | — |
| grpo_abc/periodic_dev/step-000050/completion.json | Configuration | 203 B | — |
| grpo_abc/periodic_dev/step-000050/run.json | Configuration | 807 B | — |
| grpo_abc/periodic_dev/step-000050/summary.json | Configuration | 13.2 KB | — |
| grpo_abc/periodic_dev/step-000075/completion.json | Configuration | 202 B | — |
| grpo_abc/periodic_dev/step-000075/native_shard_receipt.json | Configuration | 163.1 KB | — |
| grpo_abc/periodic_dev/step-000075/run.json | Configuration | 807 B | — |
| grpo_abc/periodic_dev/step-000075/summary.json | Configuration | 13.2 KB | — |
| grpo_abc/periodic_dev/step-000100/completion.json | Configuration | 204 B | — |
| grpo_abc/periodic_dev/step-000100/native_shard_receipt.json | Configuration | 163.1 KB | — |
| grpo_abc/periodic_dev/step-000100/run.json | Configuration | 808 B | — |
| grpo_abc/periodic_dev/step-000100/summary.json | Configuration | 13.4 KB | — |
| grpo_abc/periodic_dev/step-000125/completion.json | Configuration | 203 B | — |
| grpo_abc/periodic_dev/step-000125/native_shard_receipt.json | Configuration | 163.1 KB | — |
| grpo_abc/periodic_dev/step-000125/run.json | Configuration | 808 B | — |
| grpo_abc/periodic_dev/step-000125/summary.json | Configuration | 13.3 KB | — |
| grpo_abc/periodic_dev/step-000150/completion.json | Configuration | 203 B | — |
| grpo_abc/periodic_dev/step-000150/native_shard_receipt.json | Configuration | 162.6 KB | — |
| grpo_abc/periodic_dev/step-000150/run.json | Configuration | 808 B | — |
| grpo_abc/periodic_dev/step-000150/summary.json | Configuration | 13.3 KB | — |
| grpo_abc/periodic_dev/step-000175/completion.json | Configuration | 203 B | — |
| grpo_abc/periodic_dev/step-000175/native_shard_receipt.json | Configuration | 162.6 KB | — |
| grpo_abc/periodic_dev/step-000175/run.json | Configuration | 808 B | — |
| grpo_abc/periodic_dev/step-000175/summary.json | Configuration | 13.0 KB | — |
| grpo_abc/validation_final/completion.json | Configuration | 143 B | — |
| grpo_abc/validation_final/run.json | Configuration | 767 B | — |
| grpo_abc/validation_final/status.json | Configuration | 79 B | — |
| grpo_c/checkpoint-000025/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000025/dev25_milestone.json | Configuration | 176 B | — |
| grpo_c/checkpoint-000025/receipt.json | Configuration | 310 B | — |
| grpo_c/checkpoint-000050/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000050/async_dev25_milestone.json | Configuration | 263 B | — |
| grpo_c/checkpoint-000050/receipt.json | Configuration | 310 B | — |
| grpo_c/checkpoint-000075/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000075/async_dev25_milestone.json | Configuration | 263 B | — |
| grpo_c/checkpoint-000075/receipt.json | Configuration | 310 B | — |
| grpo_c/checkpoint-000100/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000100/async_dev25_milestone.json | Configuration | 264 B | — |
| grpo_c/checkpoint-000100/receipt.json | Configuration | 311 B | — |
| grpo_c/checkpoint-000125/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000125/async_dev25_milestone.json | Configuration | 263 B | — |
| grpo_c/checkpoint-000125/receipt.json | Configuration | 311 B | — |
| grpo_c/checkpoint-000150/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000150/async_dev25_milestone.json | Configuration | 264 B | — |
| grpo_c/checkpoint-000150/receipt.json | Configuration | 311 B | — |
| grpo_c/checkpoint-000175/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000175/async_dev25_milestone.json | Configuration | 264 B | — |
| grpo_c/checkpoint-000175/receipt.json | Configuration | 311 B | — |
| grpo_c/checkpoint-000198/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_c/checkpoint-000198/receipt.json | Configuration | 311 B | — |
| grpo_c/periodic_dev/step-000025/completion.json | Configuration | 202 B | — |
| grpo_c/periodic_dev/step-000025/run.json | Configuration | 805 B | — |
| grpo_c/periodic_dev/step-000025/summary.json | Configuration | 13.3 KB | — |
| grpo_c/periodic_dev/step-000050/completion.json | Configuration | 202 B | — |
| grpo_c/periodic_dev/step-000050/run.json | Configuration | 805 B | — |
| grpo_c/periodic_dev/step-000050/summary.json | Configuration | 13.2 KB | — |
| grpo_c/periodic_dev/step-000075/completion.json | Configuration | 203 B | — |
| grpo_c/periodic_dev/step-000075/native_shard_receipt.json | Configuration | 163.1 KB | — |
| grpo_c/periodic_dev/step-000075/run.json | Configuration | 805 B | — |
| grpo_c/periodic_dev/step-000075/summary.json | Configuration | 13.4 KB | — |
| grpo_c/periodic_dev/step-000100/completion.json | Configuration | 203 B | — |
| grpo_c/periodic_dev/step-000100/native_shard_receipt.json | Configuration | 162.2 KB | — |
| grpo_c/periodic_dev/step-000100/run.json | Configuration | 806 B | — |
| grpo_c/periodic_dev/step-000100/summary.json | Configuration | 13.2 KB | — |
| grpo_c/periodic_dev/step-000125/completion.json | Configuration | 204 B | — |
| grpo_c/periodic_dev/step-000125/native_shard_receipt.json | Configuration | 162.2 KB | — |
| grpo_c/periodic_dev/step-000125/run.json | Configuration | 806 B | — |
| grpo_c/periodic_dev/step-000125/summary.json | Configuration | 13.2 KB | — |
| grpo_c/periodic_dev/step-000150/completion.json | Configuration | 203 B | — |
| grpo_c/periodic_dev/step-000150/native_shard_receipt.json | Configuration | 163.5 KB | — |
| grpo_c/periodic_dev/step-000150/run.json | Configuration | 806 B | — |
| grpo_c/periodic_dev/step-000150/summary.json | Configuration | 13.1 KB | — |
| grpo_c/periodic_dev/step-000175/completion.json | Configuration | 204 B | — |
| grpo_c/periodic_dev/step-000175/native_shard_receipt.json | Configuration | 162.6 KB | — |
| grpo_c/periodic_dev/step-000175/run.json | Configuration | 806 B | — |
| grpo_c/periodic_dev/step-000175/summary.json | Configuration | 13.2 KB | — |
| grpo_c/validation_final/completion.json | Configuration | 143 B | — |
| grpo_c/validation_final/run.json | Configuration | 765 B | — |
| grpo_c/validation_final/status.json | Configuration | 79 B | — |
| grpo_curriculum_abc/checkpoint-000025/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000025/dev25_milestone.json | Configuration | 176 B | — |
| grpo_curriculum_abc/checkpoint-000025/receipt.json | Configuration | 310 B | — |
| grpo_curriculum_abc/checkpoint-000050/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000050/dev25_milestone.json | Configuration | 176 B | — |
| grpo_curriculum_abc/checkpoint-000050/receipt.json | Configuration | 310 B | — |
| grpo_curriculum_abc/checkpoint-000075/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000075/async_dev25_milestone.json | Configuration | 276 B | — |
| grpo_curriculum_abc/checkpoint-000075/receipt.json | Configuration | 310 B | — |
| grpo_curriculum_abc/checkpoint-000100/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000100/async_dev25_milestone.json | Configuration | 277 B | — |
| grpo_curriculum_abc/checkpoint-000100/receipt.json | Configuration | 311 B | — |
| grpo_curriculum_abc/checkpoint-000125/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000125/async_dev25_milestone.json | Configuration | 276 B | — |
| grpo_curriculum_abc/checkpoint-000125/receipt.json | Configuration | 311 B | — |
| grpo_curriculum_abc/checkpoint-000150/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000150/async_dev25_milestone.json | Configuration | 277 B | — |
| grpo_curriculum_abc/checkpoint-000150/receipt.json | Configuration | 311 B | — |
| grpo_curriculum_abc/checkpoint-000175/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000175/async_dev25_milestone.json | Configuration | 277 B | — |
| grpo_curriculum_abc/checkpoint-000175/receipt.json | Configuration | 311 B | — |
| grpo_curriculum_abc/checkpoint-000198/adapter_config.json | Configuration | 1.3 KB | — |
| grpo_curriculum_abc/checkpoint-000198/receipt.json | Configuration | 311 B | — |
| grpo_curriculum_abc/periodic_dev/step-000025/completion.json | Configuration | 203 B | — |
| grpo_curriculum_abc/periodic_dev/step-000025/run.json | Configuration | 818 B | — |
| grpo_curriculum_abc/periodic_dev/step-000025/summary.json | Configuration | 13.4 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000050/completion.json | Configuration | 203 B | — |
| grpo_curriculum_abc/periodic_dev/step-000050/run.json | Configuration | 818 B | — |
| grpo_curriculum_abc/periodic_dev/step-000050/summary.json | Configuration | 13.3 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000075/completion.json | Configuration | 203 B | — |
| grpo_curriculum_abc/periodic_dev/step-000075/native_shard_receipt.json | Configuration | 162.6 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000075/run.json | Configuration | 818 B | — |
| grpo_curriculum_abc/periodic_dev/step-000075/summary.json | Configuration | 13.4 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000100/completion.json | Configuration | 203 B | — |
| grpo_curriculum_abc/periodic_dev/step-000100/native_shard_receipt.json | Configuration | 163.1 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000100/run.json | Configuration | 819 B | — |
| grpo_curriculum_abc/periodic_dev/step-000100/summary.json | Configuration | 13.1 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000125/completion.json | Configuration | 204 B | — |
| grpo_curriculum_abc/periodic_dev/step-000125/native_shard_receipt.json | Configuration | 162.6 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000125/run.json | Configuration | 819 B | — |
| grpo_curriculum_abc/periodic_dev/step-000125/summary.json | Configuration | 13.4 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000150/completion.json | Configuration | 204 B | — |
| grpo_curriculum_abc/periodic_dev/step-000150/native_shard_receipt.json | Configuration | 162.6 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000150/run.json | Configuration | 819 B | — |
| grpo_curriculum_abc/periodic_dev/step-000150/summary.json | Configuration | 13.3 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000175/completion.json | Configuration | 204 B | — |
| grpo_curriculum_abc/periodic_dev/step-000175/native_shard_receipt.json | Configuration | 163.1 KB | — |
| grpo_curriculum_abc/periodic_dev/step-000175/run.json | Configuration | 819 B | — |
| grpo_curriculum_abc/periodic_dev/step-000175/summary.json | Configuration | 13.3 KB | — |
| grpo_curriculum_abc/validation_final/completion.json | Configuration | 143 B | — |
| grpo_curriculum_abc/validation_final/run.json | Configuration | 778 B | — |
| grpo_curriculum_abc/validation_final/status.json | Configuration | 79 B | — |
| README.md | Documentation | 666 B | — |
| grpo_abc/periodic_dev/step-000025/results.tar.gz | Other | 58.5 MB | 476fc9ce5c50 |
| grpo_abc/periodic_dev/step-000050/results.tar.gz | Other | 68.3 MB | 7323aeec94ba |
| grpo_abc/periodic_dev/step-000075/results.tar.gz | Other | 81.4 MB | f4b6e27738e5 |
| grpo_abc/periodic_dev/step-000100/results.tar.gz | Other | 93.8 MB | de615a3bd1de |
| grpo_abc/periodic_dev/step-000125/results.tar.gz | Other | 100.1 MB | 37cb26d91ba7 |
| grpo_abc/periodic_dev/step-000150/results.tar.gz | Other | 109.5 MB | bcd956efc359 |
| grpo_abc/periodic_dev/step-000175/results.tar.gz | Other | 119.4 MB | c3cafd7742bd |
| grpo_abc/validation_final/results.tar.gz | Other | 132.7 MB | ce2e592a3121 |
| grpo_c/periodic_dev/step-000025/results.tar.gz | Other | 56.4 MB | b928e591a689 |
| grpo_c/periodic_dev/step-000050/results.tar.gz | Other | 62.9 MB | 0c54d9576384 |
| grpo_c/periodic_dev/step-000075/results.tar.gz | Other | 68.8 MB | fc7bfa02803e |
| grpo_c/periodic_dev/step-000100/results.tar.gz | Other | 75.0 MB | ba05a1ec509d |
| grpo_c/periodic_dev/step-000125/results.tar.gz | Other | 71.8 MB | f075f7f6a77d |
| grpo_c/periodic_dev/step-000150/results.tar.gz | Other | 74.8 MB | 58bcf34d4adc |
| grpo_c/periodic_dev/step-000175/results.tar.gz | Other | 86.8 MB | ee3721187df4 |
| grpo_c/validation_final/results.tar.gz | Other | 95.0 MB | 9609dab95888 |
| grpo_curriculum_abc/periodic_dev/step-000025/results.tar.gz | Other | 44.8 MB | 09468c66ccd0 |
| grpo_curriculum_abc/periodic_dev/step-000050/results.tar.gz | Other | 49.2 MB | 52ef25a54135 |
| grpo_curriculum_abc/periodic_dev/step-000075/results.tar.gz | Other | 59.6 MB | b22e049b3d52 |
| grpo_curriculum_abc/periodic_dev/step-000100/results.tar.gz | Other | 70.0 MB | 49ca4852062b |
| grpo_curriculum_abc/periodic_dev/step-000125/results.tar.gz | Other | 87.7 MB | 9d8db7020830 |
| grpo_curriculum_abc/periodic_dev/step-000150/results.tar.gz | Other | 84.6 MB | 484047b85d34 |
| grpo_curriculum_abc/periodic_dev/step-000175/results.tar.gz | Other | 92.2 MB | 9cdb234dfd8e |
| grpo_curriculum_abc/validation_final/results.tar.gz | Other | 99.3 MB | b382fc948283 |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.0 GB
Download from Yitia
Released by Yitia through its official repository on Hugging Face.
Built From
- Adapter of Qwen/Qwen3.5-4B
- Derived from Qwen/Qwen3.5-4B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.