Add files using upload-large-folder tool

README.md

@@ -0,0 +1,33 @@
+---
+license: cc-by-nc-4.0
+tags: [world-model, sokoban, vlm-gym, bagel-7b-mot]
+---
+# sokoban_easy_cot_chunk_k3_world_model_20260622_perseg  (EMA, bf16)
+
+Fine-tuned **BAGEL-7B-MoT** action-conditioned visual world model — step-5000 EMA weights,
+**cast fp32 → bfloat16** (inference runs in bf16 autocast, so this is lossless for inference).
+Inference / eval artifact only: **no optimizer state**, not a training-resume checkpoint.
+
+- **Load into** the BAGEL-7B-MoT architecture (base: `ByteDance-Seed/BAGEL-7B-MoT`); this is the
+  EMA state dict (`ema.safetensors`).
+- **Training data:** `ultrastar111/sokoban_easy_v8_cot_chunk_k3_world_model_20260622_perseg` (see manifest).
+- **Recipe:** lr 2e-5, cosine, warmup 300, 5000 steps, tokens 40k, EMA 0.993, cold-start from vanilla BAGEL.
+- Eval contract: per-segment decoder (`BAGEL_DECODER=perseg`), CFG off, stop-required success.
+- License: CC-BY-NC-4.0 (research use).
+
+<details><summary>training_data_manifest.txt</summary>
+
+```
+STUDY:               GT ENV-FEEDBACK CoT chunk world model (Structure A; re-ground on real frame every K)
+chunk_size_K:        3
+date_tag:            20260622_perseg
+data_root:           /data/home/raychai/hf_datasets/sokoban_easy_v8_cot_chunk_k3_world_model_20260622_perseg/training
+dataset_config_yaml: ./data/configs/vlm_gym_sokoban_easy_imagined_cot_envfb_v8_res256_train.yaml (EnvFB loader 'interleaved_cot_envfb', data-dir overridden)
+format:              user(rules+cadence,frame0 ctx); assistant(<think> a<img>...K... </think> {K actions}); user("Env Feedback:" + REAL frame, loss0 INPUT) between chunks
+loss:                CE on assistant text; MSE on per-step imagined frames; Env-Feedback frame + label = loss=0 INPUT; frame0/instruction = context
+init_from:           VANILLA /home/jiaxin/unified_world_model/pretrained/BAGEL-7B-MoT (EMA)
+hparams:             lr 2e-5, warmup 300, cosine, total 5000, tokens 40000, ema 0.993, save_every 2500 (== self-rollout study)
+git_rev:             0d99b8708bfc601355d9ad1a93ac678770fa3ba9
+
+```
+</details>

ema.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4dd5e945e151e171328402d2ffebbf1c55a0d0831a0d33a10ac57d944abae44
+size 29214685424

training_data_manifest.txt

@@ -0,0 +1,10 @@
+STUDY:               GT ENV-FEEDBACK CoT chunk world model (Structure A; re-ground on real frame every K)
+chunk_size_K:        3
+date_tag:            20260622_perseg
+data_root:           /data/home/raychai/hf_datasets/sokoban_easy_v8_cot_chunk_k3_world_model_20260622_perseg/training
+dataset_config_yaml: ./data/configs/vlm_gym_sokoban_easy_imagined_cot_envfb_v8_res256_train.yaml (EnvFB loader 'interleaved_cot_envfb', data-dir overridden)
+format:              user(rules+cadence,frame0 ctx); assistant(<think> a<img>...K... </think> {K actions}); user("Env Feedback:" + REAL frame, loss0 INPUT) between chunks
+loss:                CE on assistant text; MSE on per-step imagined frames; Env-Feedback frame + label = loss=0 INPUT; frame0/instruction = context
+init_from:           VANILLA /home/jiaxin/unified_world_model/pretrained/BAGEL-7B-MoT (EMA)
+hparams:             lr 2e-5, warmup 300, cosine, total 5000, tokens 40000, ema 0.993, save_every 2500 (== self-rollout study)
+git_rev:             0d99b8708bfc601355d9ad1a93ac678770fa3ba9