Update README.md

README.md

@@ -17,4 +17,46 @@ tags:
 **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**.
+* `results_step-006000-epoch-01-loss=0.1724_simpler_1-3`: Results on **SimplerEnv**.
+* `vlmeval`: Multimodal performance
+
+This checkpoint supports dialogue, please check our [Code](https://github.com/InternRobotics/InstructVLA#evaluation)
+
+```python
+
+import torch
+from vla.instructvla_eagle_dual_sys_v2_meta_query_v2 import load, load_vla
+from PIL import Image
+import numpy as np
+
+model_path = 'outputs/release_ckpts/instructvla_finetune_v2_xlora_freeze_head_instruction--image_aug/checkpoints/step-013500-epoch-01-loss=0.1093.pt'
+
+# Load Stage-2 (Generalist) model
+model = load_vla(model_path, stage="stage2").eval().to(torch.bfloat16).cuda()
+
+messages = [
+    {"content": "You are a helpful assistant."},  # system
+    {
+        "role": "user",
+        "content": "Can you describe the main idea of this image?",
+        "image": [{'np_array': np.asarray(Image.open("./asset/teaser.png"))}]
+    }
+]
+
+# Preprocess input
+inputs = model.processor.prepare_input(dict(prompt=messages))
+autocast_dtype = torch.bfloat16
+
+with torch.autocast("cuda", dtype=autocast_dtype, enabled=True):
+    output = model.vlm.generate(
+        input_ids=inputs['input_ids'].cuda(),
+        attention_mask=inputs['attention_mask'].cuda(),
+        pixel_values=inputs['pixel_values'].cuda(),
+        max_new_tokens=200,
+        output_hidden_states=False,
+    )
+
+response = model.processor.tokenizer.decode(output[0])
+print(response)
+
+```