Update README.md

README.md

@@ -1,36 +1,23 @@
 ---
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
 library_name: transformers
-model_name: Q7B_mc0_sr_mc0_full_bs2_gs4_lr1e-5_VF_0826_2309
-tags:
-- generated_from_trainer
-- sft
-- trl
-licence: license
+model_name: ob11/Qwen-VL-PRM-7B
+licence: apache-2.0
+datasets:
+- ob11/VL-PRM300K-V1-train
 ---
 
-# Model Card for Q7B_mc0_sr_mc0_full_bs2_gs4_lr1e-5_VF_0826_2309
+# Model Summary
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+> Qwen-VL-PRM-3B is a process reward model finetuned from Qwen2.5-7B-Instruct on approximately 300,000 examples. It shows strong test-time scaling performance improvements on various advanced multimodal reasoning benchmarks despite being trained mainly on abstract reasoning datasets and elementary reasoning datasets.
 
-## Quick start
+- **Logs:** https://wandb.ai/aisg-arf/multimodal-reasoning/runs/pj4oc0qh
+- **Repository:** [ob11/vlprm](https://github.com/theogbrand/vlprm/)
+- **Paper:** https://arxiv.org/abs/
 
-```python
-from transformers import pipeline
+# Use
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-
-## Training procedure
-
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/aisg-arf/multimodal-reasoning/runs/pj4oc0qh) 
-
-
-This model was trained with SFT.
+The model usage is documented [here](https://github.com/theogbrand/vlprm/blob/main/eval/tts_eval/reward_guided_search/VisualPRMv2.py).
 
 ### Framework versions
 
@@ -41,18 +28,15 @@ This model was trained with SFT.
 - Tokenizers: 0.21.4
 
 ## Citations
-
-
-
-Cite TRL as:
     
 ```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
+@misc{ong2025vlprms,
+      title={VL-PRMs: Vision-Language Process Reward Models}, 
+      author={Brandon Ong, Tej Deep Pala, Vernon Toh, William Chandra Tjhi and Soujanya Poria},
+      year={2025},
+      eprint={},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={}, 
 }
 ```