Update README.md

README.md

@@ -1,42 +1,2 @@
----
-library_name: transformers
-license: other
-base_model: Qwen/Qwen2.5-VL-3B-Instruct
-tags:
-- llama-factory
-- full
-- generated_from_trainer
-model-index:
-- name: MMR1-3B-SFT
-  results: []
----
-
-
-## 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: 256
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 1024
-- total_eval_batch_size: 2048
-- 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: 5.0
-
-### Training results
-
-### Framework versions
-
-- Transformers 4.51.2
-- Pytorch 2.6.0+cu124
-- Datasets 3.6.0
-- Tokenizers 0.21.0
+[![arXiv](https://img.shields.io/badge/arXiv-2509.21268-b31b1b.svg)](https://arxiv.org/abs/2509.21268)
+[![Hugging Face](https://img.shields.io/badge/HuggingFace-MMR1-FFAE1A)](https://huggingface.co/papers/2509.21268)