Update README.md

README.md

@@ -39,11 +39,11 @@ Built on **Phi-3.5 Vision-Instruct (7 B)**, it introduces **Direct Preference Op
 ```python
 from transformers import AutoModelForVision2Seq, AutoProcessor
 
-model_id  = "remove4anonymous/CheX-Phi-3.5-vision-instruct-DPO"
+model_id  = "CheX-Phi-3.5-vision-instruct-DPO"
 model     = AutoModelForVision2Seq.from_pretrained(model_id)
 processor = AutoProcessor.from_pretrained(model_id)
 
-inputs = processor(
+inputs = processor(remove4a
     images="example_frontal.jpg",
     text="Question: What abnormalities are present?\nAnswer:",
     return_tensors="pt"
@@ -54,17 +54,17 @@ print(processor.decode(generated[0], skip_special_tokens=True))
 ````
 
 > **Dependencies**  `pip install transformers>=4.41.0 timm accelerate`
-> For batch inference or a Streamlit demo, see the scripts in the [GitHub repo](https://github.com/remove4anonymous/CheX-Phi35V).
+> For batch inference or a Streamlit demo, see the scripts in the [GitHub repo](https://huggingface.co/HaiZhiYan/CheX-Phi35V).
 
 ---
 
 ## Available Checkpoints
 
-| HF Repo                                                                                                       | Stage         | Recommended Use           |
-| ------------------------------------------------------------------------------------------------------------- | ------------- | ------------------------- |
-| [`CheX-Phi3.5-vision-instruct-DPO`](https://huggingface.co/remove4anonymous/CheX-Phi-3.5-vision-instruct-DPO) | **DPO**       | Production / evaluation   |
-| [`CheX-Phi3.5-vision-instruct-SFT`](https://huggingface.co/remove4anonymous/CheX-Phi-3.5-vision-instruct-SFT) | SFT (phase 2) | Further preference tuning |
-| [`Phi-3.5-vision-instruct`](https://huggingface.co/remove4anonymous/Phi-3.5-vision-instruct)                  | Base          | Custom fine-tuning        |
+| HF Repo                                                      | Stage         | Recommended Use           |
+| ------------------------------------------------------------ | ------------- | ------------------------- |
+| [`CheX-Phi3.5-vision-instruct-DPO`](https://huggingface.co/HaiZhiYan/CheX-Phi35V/tree/main/CheX-Phi-3.5-vision-instruct-DPO) | **DPO**       | Production / evaluation   |
+| [`CheX-Phi3.5-vision-instruct-SFT`](https://huggingface.co/HaiZhiYan/CheX-Phi35V/tree/main/CheX-Phi-3.5-vision-instruct-SFT) | SFT (phase 2) | Further preference tuning |
+| [`Phi-3.5-vision-instruct`](https://huggingface.co/HaiZhiYan/CheX-Phi35V/tree/main/Phi-3.5-vision-instruct) | Base          | Custom fine-tuning        |
 
 ---
 
@@ -112,7 +112,7 @@ Evaluation scripts are provided in `stage3_evaluate_mimic_ext_vqa.sh`.
 
 ## Resources
 
-* **Code & training scripts** — [https://github.com/remove4anonymous/CheX-Phi35V](https://github.com/remove4anonymous/CheX-Phi35V)
+* **Code & training scripts** — [https://huggingface.co/HaiZhiYan/CheX-Phi35V](https://huggingface.co/HaiZhiYan/CheX-Phi35V)
 * **Data utilities** — `tools/generate_visual_prompt.py`
 * **Demo notebook** — `demo.py`
 
@@ -125,7 +125,7 @@ Evaluation scripts are provided in `stage3_evaluate_mimic_ext_vqa.sh`.
   title        = {CheX-Phi3.5V: Preference-Optimised Vision-Language Model for Chest X-ray Interpretation},
   author       = {Liu, Xiao and Others},
   year         = {2025},
-  howpublished = {\url{https://huggingface.co/remove4anonymous/CheX-Phi-3.5-vision-instruct-DPO}}
+  howpublished = {\url{https://huggingface.co/HaiZhiYan/CheX-Phi35V/tree/main/CheX-Phi-3.5-vision-instruct-DPO}}
 }
 ```
 
@@ -133,4 +133,3 @@ Evaluation scripts are provided in `stage3_evaluate_mimic_ext_vqa.sh`.
 
 
 
-