Update checkpoint: pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos.

README.md

@@ -25,7 +25,7 @@ datasets:
 
 Building upon InternVL3 and Qwen3-VL, we instantiate InternVLA-A1 at 2B and 3B parameter scales. Covering different model scales and pre-training data configurations, we release the InternVLA-A1 series:
 
-- [x]  [InternVLA-A1-3B](https://huggingface.co/InternRobotics/InternVLA-A1-3B): pretrained on the large-scale, high-fidelity simulation data [InternData-A1](https://huggingface.co/datasets/InternRobotics/InternData-A1), together with open-source robot data (e.g. Agibot-World)
+- [x]  [InternVLA-A1-3B](https://huggingface.co/InternRobotics/InternVLA-A1-3B): pretrained on heterogeneous data sources over real-robot data, synthetic simulation data, and human videos
 - [x]  [InternVLA-A1-3B-RoboTwin](https://huggingface.co/InternRobotics/InternVLA-A1-3B-RoboTwin): finetuned on RoboTwin 2.0 benchmark
 - [ ] [InternVLA-A1-3B-Pretrain-InternData-A1](https://huggingface.co/InternRobotics/InternVLA-A1-3B-Pretrain-InternData-A1): pretrained on InternData-A1 only
 - [ ] [InternVLA-A1-2B-Pretrain-InternData-A1](https://huggingface.co/InternRobotics/InternVLA-A1-2B-Pretrain-InternData-A1): pretrained on InternData-A1 only

config.json

@@ -20,11 +20,11 @@
     "device": "cuda",
     "use_amp": false,
     "push_to_hub": false,
-    "repo_id": "jcaiaq/qwena1",
+    "repo_id": "lerobot_lab/qwena1",
     "private": null,
     "tags": null,
     "license": null,
-    "pretrained_path": null,
+    "pretrained_path": "outputs/qwena1/2026_01_26_13_29_09-qwena1-a1_robotwin_egodex_agibotworld-delta-pretrain-agibotworld_wo_act_loss/checkpoints/01310000/pretrained_model",
     "qwen3_vl_variant": "qwen3_vl_28l",
     "action_expert_variant": "qwen3_28l",
     "dtype": "bfloat16",
@@ -61,7 +61,7 @@
     "optimizer_weight_decay": 0.01,
     "optimizer_grad_clip_norm": 1.0,
     "scheduler_warmup_steps": 0,
-    "scheduler_decay_steps": 700000,
+    "scheduler_decay_steps": 25000000,
     "scheduler_decay_lr": 5e-05,
     "tokenizer_max_length": 48,
     "freeze_vision_encoder": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c4dfbc04b9783c9e27e492c1df3379292e75884eb9b019b66a73872daa6afdb
+oid sha256:41b0fc1e6772257ab5c47f46338e8438cb8c05ef0a6f2c83123b1a614c397f59
 size 6721209208