Update README.md
Browse files
README.md
CHANGED
|
@@ -72,7 +72,7 @@ prompts = tokenizer.apply_chat_template(messages, tokenize=False)
|
|
| 72 |
|
| 73 |
llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
|
| 74 |
|
| 75 |
-
outputs = llm.generate(
|
| 76 |
|
| 77 |
generated_text = outputs[0].outputs[0].text
|
| 78 |
print(generated_text)
|
|
|
|
| 72 |
|
| 73 |
llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
|
| 74 |
|
| 75 |
+
outputs = llm.generate(prompts, sampling_params)
|
| 76 |
|
| 77 |
generated_text = outputs[0].outputs[0].text
|
| 78 |
print(generated_text)
|