Update README.md

README.md

@@ -11,6 +11,50 @@ tags: []
 
 ## Model Details
 
+### Code to generate
+
+```py
+import torch
+from transformers import LlamaForCausalLM, LlamaConfig, AutoTokenizer
+
+# Set seed for reproducibility
+torch.manual_seed(0)
+
+# Initializing the configuration
+configuration = LlamaConfig(
+  head_dim=16,
+  hidden_size=32,
+  intermediate_size=64,
+  max_position_embeddings=131072,
+  model_type="llama",
+  num_attention_heads=2,
+  num_hidden_layers=1,
+  num_key_value_heads=2,
+  rms_norm_eps=1e-05,
+  rope_scaling={
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  rope_theta=500000.0,
+  tie_word_embeddings=True,
+  vocab_size=128256,
+)
+
+# Initializing a model from the configuration
+model = LlamaForCausalLM(configuration)
+
+# Re-use tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Xenova/Llama-3.2-Tokenizer")
+
+# Upload to the HF Hub
+model_id = 'onnx-community/tiny-random-LlamaForCausalLM-ONNX'
+model.push_to_hub(model_id)
+tokenizer.push_to_hub(model_id)
+```
+
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->