Added requirement file for transformers

README.md

@@ -175,6 +175,29 @@ We provide an example code to run `InternVL3-78B` using `transformers`.
 
 > Please use transformers>=4.37.2 to ensure the model works normally.
 
+- Use this requirements.txt file:
+```
+# Note: PyTorch and FlashAttention must be installed separately.
+# See installation instructions.
+
+# Core ML/DL Libraries
+transformers>=4.37.2
+accelerate
+einops
+timm
+
+# Utilities
+pyyaml
+Pillow
+tqdm
+ninja
+wheel
+packaging
+
+# pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu126
+# pip install flash-attn --no-build-isolation
+```
+
 ### Model Loading
 
 #### 16-bit (bf16 / fp16)