Update README.md
Browse files
README.md
CHANGED
@@ -45,7 +45,7 @@ from vllm import LLM, SamplingParams
|
|
45 |
# GLM-4-9B-Chat
|
46 |
# If you encounter OOM (Out of Memory) issues, it is recommended to reduce max_model_len or increase tp_size.
|
47 |
max_model_len, tp_size = 131072, 1
|
48 |
-
model_name = "4n3mone/glm-4-ko-9b-chat
|
49 |
prompt = [{"role": "user", "content": "피카츄랑 아구몬 중에서 누가 더 귀여워?"}]
|
50 |
|
51 |
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
|
|
|
45 |
# GLM-4-9B-Chat
|
46 |
# If you encounter OOM (Out of Memory) issues, it is recommended to reduce max_model_len or increase tp_size.
|
47 |
max_model_len, tp_size = 131072, 1
|
48 |
+
model_name = "4n3mone/glm-4-ko-9b-chat"
|
49 |
prompt = [{"role": "user", "content": "피카츄랑 아구몬 중에서 누가 더 귀여워?"}]
|
50 |
|
51 |
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
|