Update README.md

README.md

@@ -20,9 +20,13 @@ Our key contributions are as follows:
 
 
 ## Model Details
-* Developed by: Alan Dao, Dinh Bach Vu, Tuan Le Duc Anh, Bui Quang Huy (Menlo Research)
-* Model type: Qwen 2.5 3B Instruct, fine-tuned for hand pose estimation
+* Model architecture: Qwen 2.5 3B Instruct, fine-tuned for hand pose estimation
+* Dataset:
+  * Training: [homebrewltd/robot-hand-poses-train](https://huggingface.co/datasets/homebrewltd/robot-hand-poses-train)
+  * Eval: [homebrewltd/robotic-hand-poses-eval](https://huggingface.co/datasets/homebrewltd/robotic-hand-poses-eval)
 * License: Apache-2.0 license
+* Developed by: Alan Dao, Dinh Bach Vu, Tuan Le Duc Anh, Bui Quang Huy (Menlo Research)
+
 
 ## How to Get Started 
 
@@ -34,7 +38,7 @@ from qwen_vl_utils import process_vision_info
 
 # 1. Load model and processor
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_path = "path/to/qwen2.5_vl/checkpoint-1500/"
+model_path = "homebrewltd/Poseless-3B"
 
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     model_path,
@@ -53,8 +57,13 @@ processor = AutoProcessor.from_pretrained(
 image = Image.open("your_hand_image.png").convert("RGB")
 
 # 3. Create messages
+SYSTEM_PROMPT = """You are a specialized Vision Language Model designed to accurately estimate joint angles from hand pose images. Your task is to analyze images of a human or robotic hand and output precise angle measurements for each joint. Output joint angles in radians.
+Output Format:
+<lh_WRJ2>angle</lh_WRJ2><lh_WRJ1>angle</lh_WRJ1><lh_FFJ4>angle</lh_FFJ4><lh_FFJ3>angle</lh_FFJ3><lh_FFJ2>angle</lh_FFJ2><lh_FFJ1>angle</lh_FFJ1><lh_MFJ4>angle</lh_MFJ4><lh_MFJ3>angle</lh_MFJ3><lh_MFJ2>angle</lh_MFJ2><lh_MFJ1>angle</lh_MFJ1><lh_RFJ4>angle</lh_RFJ4><lh_RFJ3>angle</lh_RFJ3><lh_RFJ2>angle</lh_RFJ2><lh_RFJ1>angle</lh_RFJ1><lh_LFJ5>angle</lh_LFJ5><lh_LFJ4>angle</lh_LFJ4><lh_LFJ3>angle</lh_LFJ3><lh_LFJ2>angle</lh_LFJ2><lh_LFJ1>angle</lh_LFJ1><lh_THJ5>angle</lh_THJ5><lh_THJ4>angle</lh_THJ4><lh_THJ3>angle</lh_THJ3><lh_THJ2>angle</lh_THJ2><lh_THJ1>angle</lh_THJ1>
+"""
+
 messages = [
-    {"role": "system", "content": "You are a specialized Vision Language Model designed to accurately estimate joint angles from hand pose images..."},
+    {"role": "system", "content": f"{SYSTEM_PROMPT}"},
     {
         "role": "user",
         "content": [