SteeringPolicyReal is an open-weight model from Li Zhiyan. Its published files total 55.7 GB.
Parameters—
Context—
Weights55.6 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- lzy001Yuki/SteeringPolicyReal
- Publisher
- Li Zhiyan
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 9cb303d26d57c15b437353bd6890cefd34cfe007
- First published
- 2026-09-12
- Last updated
- 2026-09-19
Files and Weights
68 files, 55.7 GB in total. The weights are 23 files totalling 55.6 GB in safetensors.
Weights23 files · 55.6 GB
Configuration32 files · 134.8 KB
Tokenizer10 files · 171.9 MB
Documentation1 file · 6.1 KB
Other1 file · 205.8 KB
Repository1 file · 2.1 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| cloth/020000/pretrained_model/model.safetensors | Weights | 9.4 GB | 826e17a5d648 |
| cloth/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 9.3 KB | 59420a4a5b9c |
| cloth/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 9.3 KB | ab2c22b47b89 |
| cloth/020000/training_state/optimizer_state.safetensors | Weights | 2.2 GB | c58e8b95a11f |
| cloth/020000/training_state/rng_state.safetensors | Weights | 15.7 KB | 5834c9826ea6 |
| cup_pingpong/020000/pretrained_model/model.safetensors | Weights | 9.4 GB | a580a5a1f9a3 |
| cup_pingpong/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 9.3 KB | 47905182ea25 |
| cup_pingpong/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 9.3 KB | ba998644658a |
| cup_pingpong/020000/training_state/optimizer_state.safetensors | Weights | 2.2 GB | 6e84da2199cc |
| cup_pingpong/020000/training_state/rng_state.safetensors | Weights | 15.7 KB | 5834c9826ea6 |
| pingpong/020000/pretrained_model/model.safetensors | Weights | 9.4 GB | 3cf6cf5b2661 |
| pingpong/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 9.3 KB | 863b3a3bdfc8 |
| pingpong/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 9.3 KB | 5c51886016e7 |
| pingpong/020000/training_state/optimizer_state.safetensors | Weights | 2.2 GB | d81a89d29a10 |
| pingpong/020000/training_state/rng_state.safetensors | Weights | 15.7 KB | 5834c9826ea6 |
| push_cube/020000/pretrained_model/model.safetensors | Weights | 9.4 GB | 2ddba26ca083 |
| push_cube/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 9.3 KB | 92c984af29d4 |
| push_cube/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 9.3 KB | 26a6e40766c9 |
| push_cube/020000/training_state/optimizer_state.safetensors | Weights | 2.2 GB | 48f6e5b6cc5e |
| push_cube/020000/training_state/rng_state.safetensors | Weights | 15.7 KB | 5834c9826ea6 |
| push_cube_correct/model.safetensors | Weights | 9.4 GB | 3e71df12e76a |
| push_cube_correct/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 9.3 KB | 92c984af29d4 |
| push_cube_correct/policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 9.3 KB | 26a6e40766c9 |
| cloth/020000/pretrained_model/config.json | Configuration | 3.0 KB | — |
| cloth/020000/pretrained_model/policy_postprocessor.json | Configuration | 780 B | — |
| cloth/020000/pretrained_model/policy_preprocessor.json | Configuration | 2.2 KB | — |
| cloth/020000/pretrained_model/train_config.json | Configuration | 9.3 KB | — |
| cloth/020000/training_state/optimizer_param_groups.json | Configuration | 14.1 KB | — |
| cloth/020000/training_state/scheduler_state.json | Configuration | 256 B | — |
| cloth/020000/training_state/training_step.json | Configuration | 225 B | — |
| cup_pingpong/020000/pretrained_model/config.json | Configuration | 3.0 KB | — |
| cup_pingpong/020000/pretrained_model/policy_postprocessor.json | Configuration | 808 B | — |
| cup_pingpong/020000/pretrained_model/policy_preprocessor.json | Configuration | 2.2 KB | — |
| cup_pingpong/020000/pretrained_model/train_config.json | Configuration | 9.3 KB | — |
| cup_pingpong/020000/training_state/optimizer_param_groups.json | Configuration | 14.1 KB | — |
| cup_pingpong/020000/training_state/scheduler_state.json | Configuration | 256 B | — |
| cup_pingpong/020000/training_state/training_step.json | Configuration | 225 B | — |
| pingpong/020000/pretrained_model/config.json | Configuration | 3.0 KB | — |
| pingpong/020000/pretrained_model/policy_postprocessor.json | Configuration | 780 B | — |
| pingpong/020000/pretrained_model/policy_preprocessor.json | Configuration | 2.2 KB | — |
| pingpong/020000/pretrained_model/train_config.json | Configuration | 9.3 KB | — |
| pingpong/020000/training_state/optimizer_param_groups.json | Configuration | 14.1 KB | — |
| pingpong/020000/training_state/scheduler_state.json | Configuration | 256 B | — |
| pingpong/020000/training_state/training_step.json | Configuration | 225 B | — |
| push_cube/020000/pretrained_model/config.json | Configuration | 3.0 KB | — |
| push_cube/020000/pretrained_model/policy_postprocessor.json | Configuration | 780 B | — |
| push_cube/020000/pretrained_model/policy_preprocessor.json | Configuration | 2.2 KB | — |
| push_cube/020000/pretrained_model/train_config.json | Configuration | 9.3 KB | — |
| push_cube/020000/training_state/optimizer_param_groups.json | Configuration | 14.1 KB | — |
| push_cube/020000/training_state/scheduler_state.json | Configuration | 256 B | — |
| push_cube/020000/training_state/training_step.json | Configuration | 225 B | — |
| push_cube_correct/config.json | Configuration | 3.0 KB | — |
| push_cube_correct/policy_postprocessor.json | Configuration | 808 B | — |
| push_cube_correct/policy_preprocessor.json | Configuration | 2.2 KB | — |
| push_cube_correct/train_config.json | Configuration | 9.3 KB | — |
| PI05_STEERING.md | Documentation | 6.1 KB | — |
| push_cube_correct/pi05_push_cube_shovel_correct_loss_0_20k.png | Other | 205.8 KB | 27a0aa4bb807 |
| .gitattributes | Repository | 2.1 KB | — |
| cloth/020000/pretrained_model/tokenizer/tokenizer.json | Tokenizer | 34.4 MB | 7336bb4ce016 |
| cloth/020000/pretrained_model/tokenizer/tokenizer_config.json | Tokenizer | 503 B | — |
| cup_pingpong/020000/pretrained_model/tokenizer/tokenizer.json | Tokenizer | 34.4 MB | 7336bb4ce016 |
| cup_pingpong/020000/pretrained_model/tokenizer/tokenizer_config.json | Tokenizer | 503 B | — |
| pingpong/020000/pretrained_model/tokenizer/tokenizer.json | Tokenizer | 34.4 MB | 7336bb4ce016 |
| pingpong/020000/pretrained_model/tokenizer/tokenizer_config.json | Tokenizer | 503 B | — |
| push_cube/020000/pretrained_model/tokenizer/tokenizer.json | Tokenizer | 34.4 MB | 7336bb4ce016 |
| push_cube/020000/pretrained_model/tokenizer/tokenizer_config.json | Tokenizer | 503 B | — |
| push_cube_correct/tokenizer/tokenizer.json | Tokenizer | 34.4 MB | 7336bb4ce016 |
| push_cube_correct/tokenizer/tokenizer_config.json | Tokenizer | 503 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 55.6 GB
Download from Li Zhiyan
Released by Li Zhiyan through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 55.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.