Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+---
+license: apache-2.0
+tags:
+  - robotics
+  - vla
+  - pi0
+  - droid
+---
+
+# MolmoBot-Pi0-DROID-absjoint-reasoninit
+
+MolmoBot-Pi0 (PaliGemma-decoder VLA) **full fine-tune** on the equad DROID data
+(`shrg7/droid-equad-stage-1`), with **absolute joint-pose** action targets
+(`arm[t] = q[t+1]`, 7 joints + gripper).
+
+**Reasoning-init variant:** before full fine-tuning, a frozen reasoning LoRA
+(trained reasoning-only on the same DROID data) is folded into the PaliGemma
+decoder weights in-place, so the full-FT starts from a reasoning-initialized
+backbone (a weight-space prior), rather than plain base weights.
+
+- Config: `molmobot_pi0_lerobot_droid_absjoint`
+- **Checkpoint: step 2000 (intermediate — training in progress)**, held-out
+  `val_action_loss = 0.0199`.
+- Contents: `model.safetensors` (flat, full model), `metadata.pt`,
+  `assets/droid_equad/norm_stats.json`, `assets/train_config.pkl`.
+  Optimizer state omitted.

assets/droid_equad/norm_stats.json

@@ -0,0 +1,88 @@
+{
+  "norm_stats": {
+    "state": {
+      "mean": [
+        0.21224477887153625,
+        0.17455638945102692,
+        0.08217453211545944,
+        -2.2301878929138184,
+        -0.3177533447742462,
+        2.1893584728240967,
+        0.5952492952346802,
+        0.22651995718479156
+      ],
+      "std": [
+        0.1868240088224411,
+        0.4287582337856293,
+        0.16963618993759155,
+        0.3406936824321747,
+        0.514870285987854,
+        0.398303359746933,
+        0.9257502555847168,
+        0.33563897013664246
+      ],
+      "q01": [
+        -0.10885760933160782,
+        -0.6000549793243408,
+        -0.20411832630634308,
+        -2.6167612075805664,
+        -0.9322788119316101,
+        1.625175952911377,
+        -0.5099077224731445,
+        -9.884697227402484e-11
+      ],
+      "q99": [
+        0.46970000863075256,
+        0.6144798994064331,
+        0.33503517508506775,
+        -1.8341015577316284,
+        0.36206528544425964,
+        2.7228288650512695,
+        1.7108533382415771,
+        0.832818329334259
+      ]
+    },
+    "actions": {
+      "mean": [
+        0.21224477887153625,
+        0.17455638945102692,
+        0.08217453211545944,
+        -2.2301878929138184,
+        -0.3177533447742462,
+        2.1893584728240967,
+        0.5952492952346802,
+        0.2692590653896332
+      ],
+      "std": [
+        0.1868240088224411,
+        0.4287582337856293,
+        0.16963618993759155,
+        0.3406936824321747,
+        0.514870285987854,
+        0.398303359746933,
+        0.9257502555847168,
+        0.3966350555419922
+      ],
+      "q01": [
+        -0.10885760933160782,
+        -0.6000549793243408,
+        -0.20411832630634308,
+        -2.6167612075805664,
+        -0.9322788119316101,
+        1.625175952911377,
+        -0.5099077224731445,
+        -9.884697227402484e-11
+      ],
+      "q99": [
+        0.46970000863075256,
+        0.6144798994064331,
+        0.33503517508506775,
+        -1.8341015577316284,
+        0.36206528544425964,
+        2.7228288650512695,
+        1.7108533382415771,
+        0.9533857107162476
+      ]
+    }
+  }
+}

assets/train_config.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025f507e7c8f0d7cb753f9bf1c6eca541b90e6ec7b549fbcac683328f75739a8
+size 1691

metadata.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56cf90a614fdd2e32ea6e352c05b545f484360f11de7e943c3b5e49d8a9b19d
+size 2931

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c394e7d6a0218a31460fb7caf68510f46bbe66f9be692cfcbd555d4d17a2ab
+size 7011248944