Update README.md

README.md

@@ -4,14 +4,30 @@ tags:
   - custom_generate
 ---
 
+## Description
+Test repo to experiment with calling `generate` from the hub. It is a simplified implementation of greedy decoding.
+
 ## Base model:
 `Qwen/Qwen2.5-0.5B-Instruct`
 
-## Description
-Test repo to experiment with calling `generate` from the hub. It is a simplified implementation of greedy decoding.
+## Model compatibility
+Most models. More specifically, any `transformer` LLM/VLM trained for causal language modeling.
 
 ## Additional Arguments
 `left_padding` (`int`, *optional*): number of padding tokens to add before the provided input
 
 ## Output Type changes
 (none)
+
+## Example usage
+
+```py
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", device_map="auto")
+
+inputs = tokenizer(["The quick brown"], return_tensors="pt").to(model.device)
+gen_out = model.generate(**inputs, left_padding=5, custom_generate="transformers-community/custom_generate_example", trust_remote_code=True)
+print(tokenizer.batch_decode(gen_out, skip_special_tokens=True))
+```