Update README.md

README.md

@@ -77,8 +77,43 @@ Near‑linear scaling thanks to sharded ZeRO‑3 + RCCL optimisations.
 
 # Inference
 
+
 ### Offline
 
+```python
+model_name = "seedboxai/KafkaLM-15B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "Why did Kafka hit different?"
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+response = tokenizer.decode(output_ids, skip_special_tokens=True)
+
+print(response)
+```
 
 ## vLLM