Update model card with Qwen Bridge 29K common start

README.md

@@ -5,13 +5,14 @@ tags:
   - robotics
   - vision-language-action
   - florence-2
+  - qwen3-vl
   - bridge
   - importance-sampling
 ---
 
-# ReTime / OPTR — Florence–Bridge handoff
+# ReTime / OPTR — Florence–Bridge and Qwen–Bridge handoff
 
-This package contains the server-authoritative Florence–Bridge OPTR code, a complete 20K common-start training state, and the Uniform/Residual-OPTR 20.5K evaluation snapshots.
+This package contains the server-authoritative Florence–Bridge OPTR code, its complete 20K common-start state and Uniform/Residual-OPTR 20.5K evaluation snapshots. It also contains the complete Qwen3-VL-4B–Bridge 29K common-start state and the environment/seed contract needed for paired multi-seed continuation experiments.
 
 ## What is included
 
@@ -23,9 +24,19 @@ This package contains the server-authoritative Florence–Bridge OPTR code, a co
 - `configs/`, `scripts/`, `starVLA/`: portable training and evaluation code.
 - `EXPERIMENT_CONTRACT.md`: exact experimental contract and results.
 - `AGENTS.md`: fast handoff instructions for an AI coding agent.
+- `qwen_bridge_common_start_29k/checkpoints/steps_29000_pytorch_model.pt`: Qwen3-VL-4B–Bridge 29K model parameters.
+- `qwen_bridge_common_start_29k/checkpoints/steps_29000_training_state.pt`: complete optimizer, scheduler, Python/NumPy/PyTorch/CUDA RNG and data-order state.
+- `qwen_bridge_common_start_29k/config.full.yaml`: server-authoritative configuration that produced the 29K common start.
+- `qwen_bridge_common_start_29k/ENVIRONMENT.md`: exact Qwen software and training environment.
+- `qwen_bridge_common_start_29k/MULTISEED_PROTOCOL.md`: strict separation of common-start, continuation-training and evaluation seeds.
+- `qwen_bridge_common_start_29k/AGENTS.md`: Qwen handoff constraints for an AI coding agent.
 
 The 20.5K files are sufficient for evaluation but **not** for exact optimizer/RNG continuation. Any new branch must resume from the complete 20K state.
 
+For Qwen–Bridge, exact continuation requires **both** 29K `.pt` files. The common-start training seed is `42`. Historical exact-state continuation does not actively reseed; the planned paired continuation seeds are `117465`, `239217`, `533389`, and `587008`. Formal evaluation always uses policy seeds `518957`, `765353`, `686765`, and `516408` (four tasks × 24 episodes = 384 rollouts per checkpoint). The planned Qwen multi-seed panel is a protocol, not a claim that those runs are already complete.
+
+This release does not use implementation, code-path, absolute-path, current-manifest or self-referential SHA gates. Experimental identity is enforced through loadability and semantic model/data/episode/anchor/support/batch/budget checks.
+
 ## Headline result
 
 Fixed no-video SimplerEnv WidowX/Bridge panel: four policy seeds (`518957`, `765353`, `686765`, `516408`) × four tasks × 24 episodes = 384 rollouts.