robosyn-submission-v2 is an open-weight model from Ouyang Zhenqiu. Its published files total 4.4 GB.
Unified checkpoint collection for the RoboSynChallenge submission (code: https://github.com/OuyangZhenqiu/RoboSynChallenge-submission). One subdirectory per task; run bash eval.sh from the code repo (checkpoints default to checkpoints/, i.e.
Model Card
Unified checkpoint collection for the RoboSynChallenge submission (code: https://github.com/OuyangZhenqiu/RoboSynChallenge-submission). One subdirectory per task; run bash eval.sh from the code repo (checkpoints default to checkpoints/, i.e. these subdirectory names). - All ten tasks are self-trained. sampleloading switched to the AWR advantage-weighted checkpoint on 2026-10-03 (13/90 = 14.4% merged over three 30-ep runs: seed1000 7/30 + 2/30, seed2000 4/30; official ckpt same caliber 3.3%). Single-run spread on this task is large (sim epsilon flips borderline episodes); the merged value is the unbiased estimate. - Self-trained ten-task average 59.1% (nine-task average 60.7%).
Excerpt from the card by Ouyang Zhenqiu.
Identity and Version
- Repository
- oyzq941353193/robosyn-submission-v2
- Publisher
- Ouyang Zhenqiu
- 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
- aa0410349d7c8e9546fd43b9f37a4175ac4ca870
- First published
- 2026-09-22
- Last updated
- 2026-10-03
Files and Weights
56 files, 4.4 GB in total. The weights are 17 files totalling 4.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| act_click_bell_2k_dr_060000/model.safetensors | Weights | 206.6 MB | 8fefaffd13e0 |
| act_click_bell_2k_dr_060000/pretrained_model/model.safetensors | Weights | 206.6 MB | 8fefaffd13e0 |
| act_drawer_open_place_baseline_060000/model.safetensors | Weights | 206.6 MB | 6d388d35c76d |
| act_items_speed3_mix_060000/model.safetensors | Weights | 206.6 MB | 71906bf85b42 |
| act_manipulate_pipette_baseline_060000/model.safetensors | Weights | 206.6 MB | 7c400e62cade |
| act_mixer_operating_baseline_060000/model.safetensors | Weights | 206.6 MB | e573fe293f7d |
| act_table_rearrangement_baseline_060000/model.safetensors | Weights | 206.6 MB | 01a7d8ab57af |
| act_water_pouring_baseline_060000/model.safetensors | Weights | 206.6 MB | 47b61297cc33 |
| smolvla_awr_sample_loading_024000/model.safetensors | Weights | 906.7 MB | 8cd18824f51b |
| smolvla_awr_sample_loading_024000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 15.1 KB | e7cca9c4131f |
| smolvla_awr_sample_loading_024000/policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 15.1 KB | c75b337ce323 |
| smolvla_s3_handle_basket_030000/model.safetensors | Weights | 906.7 MB | c490a22caf1e |
| smolvla_s3_handle_basket_030000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 11.8 KB | 0c5ca47fe3b0 |
| smolvla_s3_handle_basket_030000/policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 11.8 KB | 608c94f6b73a |
| smolvla_v6_item_assembly_300000/model.safetensors | Weights | 906.7 MB | ba8f8fa5568d |
| smolvla_v6_item_assembly_300000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 11.8 KB | 7409b9698d4b |
| smolvla_v6_item_assembly_300000/policy_preprocessor_step_5_normalizer_processor.safetensors | Weights | 11.8 KB | 32f2553624db |
| act_click_bell_2k_dr_060000/config.json | Configuration | 1.7 KB | — |
| act_click_bell_2k_dr_060000/pretrained_model/config.json | Configuration | 1.7 KB | — |
| act_click_bell_2k_dr_060000/pretrained_model/train_config.json | Configuration | 5.5 KB | — |
| act_click_bell_2k_dr_060000/train_config.json | Configuration | 5.5 KB | — |
| act_drawer_open_place_baseline_060000/config.json | Configuration | 2.1 KB | — |
| act_drawer_open_place_baseline_060000/train_config.json | Configuration | 5.5 KB | — |
| act_items_speed3_mix_060000/config.json | Configuration | 2.1 KB | — |
| act_items_speed3_mix_060000/train_config.json | Configuration | 5.5 KB | — |
| act_manipulate_pipette_baseline_060000/config.json | Configuration | 2.1 KB | — |
| act_manipulate_pipette_baseline_060000/train_config.json | Configuration | 5.5 KB | — |
| act_mixer_operating_baseline_060000/config.json | Configuration | 2.1 KB | — |
| act_mixer_operating_baseline_060000/train_config.json | Configuration | 5.5 KB | — |
| act_table_rearrangement_baseline_060000/config.json | Configuration | 2.1 KB | — |
| act_table_rearrangement_baseline_060000/train_config.json | Configuration | 5.5 KB | — |
| act_water_pouring_baseline_060000/config.json | Configuration | 2.1 KB | — |
| act_water_pouring_baseline_060000/train_config.json | Configuration | 5.5 KB | — |
| smolvla_awr_sample_loading_024000/config.json | Configuration | 2.6 KB | — |
| smolvla_awr_sample_loading_024000/policy_postprocessor.json | Configuration | 661 B | — |
| smolvla_awr_sample_loading_024000/policy_preprocessor.json | Configuration | 2.2 KB | — |
| smolvla_awr_sample_loading_024000/train_config.json | Configuration | 9.1 KB | — |
| smolvla_s3_handle_basket_030000/config.json | Configuration | 2.6 KB | — |
| smolvla_s3_handle_basket_030000/policy_postprocessor.json | Configuration | 661 B | — |
| smolvla_s3_handle_basket_030000/policy_preprocessor.json | Configuration | 2.2 KB | — |
| smolvla_s3_handle_basket_030000/train_config.json | Configuration | 9.1 KB | — |
| smolvla_v6_item_assembly_300000/config.json | Configuration | 2.6 KB | — |
| smolvla_v6_item_assembly_300000/policy_postprocessor.json | Configuration | 661 B | — |
| smolvla_v6_item_assembly_300000/policy_preprocessor.json | Configuration | 2.2 KB | — |
| smolvla_v6_item_assembly_300000/train_config.json | Configuration | 9.2 KB | — |
| README.md | Documentation | 2.0 KB | — |
| smolvla_awr_sample_loading_024000/tokenizer/chat_template.jinja | Other | 403 B | — |
| smolvla_s3_handle_basket_030000/tokenizer/chat_template.jinja | Other | 403 B | — |
| smolvla_v6_item_assembly_300000/tokenizer/chat_template.jinja | Other | 403 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| smolvla_awr_sample_loading_024000/tokenizer/tokenizer.json | Tokenizer | 3.5 MB | — |
| smolvla_awr_sample_loading_024000/tokenizer/tokenizer_config.json | Tokenizer | 997 B | — |
| smolvla_s3_handle_basket_030000/tokenizer/tokenizer.json | Tokenizer | 3.5 MB | — |
| smolvla_s3_handle_basket_030000/tokenizer/tokenizer_config.json | Tokenizer | 997 B | — |
| smolvla_v6_item_assembly_300000/tokenizer/tokenizer.json | Tokenizer | 3.5 MB | — |
| smolvla_v6_item_assembly_300000/tokenizer/tokenizer_config.json | Tokenizer | 997 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 4.4 GB
Released by Ouyang Zhenqiu through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.