Create README.md

README.md

@@ -0,0 +1,18 @@
+---
+datasets:
+- ShuaiYang03/VLA_Instruction_Tuning
+base_model:
+- nvidia/Eagle2-2B
+---
+
+# Model Card for InstructVLA-Generalist (with state)
+
+**Weights**
+
+* `checkpoints/step-006000-epoch-01-loss=0.1724.pt`: Complete model checkpoint for direct evaluation.
+
+**Evaluation Results**
+
+* `results_step-006000-epoch-01-loss=0.1724_instruct_cot_2-3`: Results on **SimplerEnv-Instruct** with multimodal reasoning.
+* `results_step-006000-epoch-01-loss=0.1724_simpler_1-3`: Results on **SimplerEnv**.
+