Update README.md

README.md

@@ -11,6 +11,41 @@ tags: []
 
 ## Model Details
 
+Tiny `Gemma2ForCausalLM` with randomly-initialized weights for testing. Code to generate:
+```py
+import torch
+from transformers import Gemma2ForCausalLM, Gemma2Config, AutoTokenizer
+
+# Set seed for reproducibility
+torch.manual_seed(0)
+
+# Initializing a Gemma2 gemma2-9b style configuration
+configuration = Gemma2Config(
+  head_dim=16,
+  hidden_size=32,
+  initializer_range=0.02,
+  intermediate_size=64,
+  max_position_embeddings=8192,
+  model_type="gemma2",
+  num_attention_heads=2,
+  num_hidden_layers=1,
+  num_key_value_heads=2,
+  vocab_size=256000,
+  attn_implementation='eager',
+)
+
+# Initializing a model from the gemma2-9b style configuration
+model = Gemma2ForCausalLM(configuration)
+
+# Re-use gemma2 tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Xenova/gemma2-tokenizer")
+
+# Upload to the HF Hub
+model_id = 'hf-internal-testing/tiny-random-Gemma2ForCausalLM'
+model.push_to_hub(model_id)
+tokenizer.push_to_hub(model_id)
+```
+
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->