Update README.md
Browse files
README.md
CHANGED
@@ -121,7 +121,7 @@ Please refer to the [remote-sensing-VQA-benchmark](https://huggingface.co/datase
|
|
121 |
|
122 |
## 3. To Reproduce this Domain-Adapted MLLM
|
123 |
|
124 |
-
Using our training data, [
|
125 |
|
126 |
For reference, we train from Qwen2.5-VL-3B-Instruct for 1 epoch with a learning rate of 1e-5, and a global batch size of 128.
|
127 |
|
|
|
121 |
|
122 |
## 3. To Reproduce this Domain-Adapted MLLM
|
123 |
|
124 |
+
Using our training data, [remote-sensing-visual-instructions](https://huggingface.co/datasets/AdaptLLM/remote-sensing-visual-instructions), you can easily reproduce our models based on the [LlamaFactory](https://github.com/hiyouga/LLaMA-Factory) repository.
|
125 |
|
126 |
For reference, we train from Qwen2.5-VL-3B-Instruct for 1 epoch with a learning rate of 1e-5, and a global batch size of 128.
|
127 |
|