| --- |
| license: other |
| library_name: transformers |
| tags: [meta-reasoning, rl, grpo, qwen3_5, layer-audit, research-checkpoint] |
| --- |
| |
| # mr9b meta-reasoning RL — layer-audit — 8-node/215 checkpoints |
|
|
| Mid-training research checkpoints from a fully-async GRPO run with the |
| **pipelined frozen-E layer audit** enabled (`meta_reasoning.layer_audit.enable=true`). |
|
|
| - **Base:** Qwen3.5 (~9B hybrid, `model_type: qwen3_5`, 32 layers) |
| - **Method:** fully-async GRPO meta-reasoning RL (VERL fully_async_policy) |
| - **Layer audit:** after each completed reasoning layer, a frozen executor audits it |
| (classify explorations as new/refinement/verification/duplicate, diagnose tunnel |
| vision + gaps) and injects one-step control feedback into the next MR step. |
| - **Topology 215:** 2 trainer / 1 rollout / 5 frozen-E nodes (8 nodes, TP8/PP1/DP2) |
| - **Experiment:** `mr9b_layeraudit_8node_215_20260718_231300` |
| - **W&B project:** `meta_reason_rl_h100_5node` |
|
|
| ## Contents |
| Each subfolder is a standalone HF model (weights + tokenizer + chat template): |
| - `global_step_68/` |
| - `global_step_69/` |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| m = AutoModelForCausalLM.from_pretrained("aviralku/mr9b-layeraudit-8node-215", subfolder="global_step_69") |
| t = AutoTokenizer.from_pretrained("aviralku/mr9b-layeraudit-8node-215", subfolder="global_step_69") |
| ``` |
|
|
| _Private research checkpoints; not an official release._ |
|
|
