4n3mone
/

glm-4-ko-9b-chat

Feature Extraction

Model card Files Files and versions Community

4n3mone commited on Jul 1

Commit

c71df51

•

1 Parent(s): b4a15e0

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

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

 # GLM-4-9B-Chat
 # If you encounter OOM (Out of Memory) issues, it is recommended to reduce max_model_len or increase tp_size.
 max_model_len, tp_size = 131072, 1
+model_name = "4n3mone/glm-4-ko-9b-chat"
 prompt = [{"role": "user", "content": "피카츄랑 아구몬 중에서 누가 더 귀여워?"}]
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)