Update README.md

README.md

@@ -8,6 +8,58 @@ tags: []
 <!-- Provide a quick summary of what the model is/does. -->
 
 
+## Conversion code
+
+```py
+from transformers import (
+    AutoProcessor,
+    Llama4ForConditionalGeneration,
+    Llama4VisionConfig,
+    Llama4TextConfig,
+    Llama4Config,
+)
+import torch
+
+torch.manual_seed(0)
+
+model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
+torch_dtype = torch.bfloat16  # or torch.float32
+
+intermediate_size_mlp = 64
+config = Llama4Config.from_pretrained(
+    model_id,
+    text_config=Llama4TextConfig.from_pretrained(
+        model_id,
+        head_dim=8,
+        hidden_size=16,
+        intermediate_size=32,
+        intermediate_size_mlp=intermediate_size_mlp,
+        moe_layers=[0,1,2,3,4],
+        no_rope_layers=[1,1,1,0,1],
+        num_attention_heads=10,
+        num_experts_per_tok=1,
+        num_hidden_layers=5,
+        num_key_value_heads=2,
+        num_local_experts=4,
+    ),
+    vision_config=Llama4VisionConfig.from_pretrained(
+        model_id,
+        hidden_size=16,
+        intermediate_size=intermediate_size_mlp,
+        num_attention_heads=4,
+        num_hidden_layers=2,
+        projector_input_dim=128,
+        projector_output_dim=128,
+        vision_output_dim=128,
+    ),
+)
+
+model = Llama4ForConditionalGeneration(config).to(torch_dtype)
+print(model.num_parameters())  # 6571696
+
+processor = AutoProcessor.from_pretrained(model_id)
+```
+
 
 ## Model Details