Update README.md

README.md

@@ -1,61 +1,19 @@
 ---
 library_name: transformers
-license: other
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
-tags:
-- llama-factory
-- full
-- generated_from_trainer
 model-index:
 - name: sft
   results: []
 ---
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# sft
-
-<!-- This model is a fine-tuned version of [/mnt/petrelfs/zhaoshitian/gveval_zhaoshitian/Qwen2.5-VL-7B-Instruct](https://huggingface.co//mnt/petrelfs/zhaoshitian/gveval_zhaoshitian/Qwen2.5-VL-7B-Instruct) on the mmk12_sharegpt_wo_single_turn, the rpm_sharegpt_wo_single_turn, the infovqa_sharegpt_wo_single_turn, the chartqa_sharegpt_wo_single_turn, the mmpr_sharegpt_wo_single_turn, the llavacot_sharegpt_wo_single_turn, the gmai_sharegpt_wo_single_turn and the rpm_sharegpt_wo_single_turn datasets. -->
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
-- total_eval_batch_size: 64
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1.0
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.51.3
-- Pytorch 2.5.1+cu121
-- Datasets 3.6.0
-- Tokenizers 0.21.1
+[PyVision-RL: Forging Open Agentic Vision Models via RL](https://arxiv.org/abs/2602.20739)
+
+This is PyVision-Image-7B-SFT, post trained from Qwen2.5-VL-7B.
+
+```bibtex
+@article{pyvisionrl2026,
+  title={PyVision-RL: Forging Open Agentic Vision Models via RL},
+  author={Zhao, Shitian and Lin, Shaoheng and Li, Ming and Zhang, Haoquan and Peng, Wenshuo and Zhang, Kaipeng and Wei, Chen},
+  journal={arXiv:2602.20739},
+  year={2026}
+}
+```