linagora
/

Labess-7b-chat

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Wajdi1976 commited on 24 days ago

Commit

63eb912

·

verified ·

1 Parent(s): 0bddeb4

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -35,7 +35,7 @@ max_seq_length = 128 # Choose any! We auto support RoPE Scaling internally!
 dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
 load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "linagora/Labess-7b-chat-v1",
     max_seq_length = max_seq_length,
     dtype = dtype,
     load_in_4bit = load_in_4bit,

 dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
 load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
 model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "linagora/Labess-7b-chat",
     max_seq_length = max_seq_length,
     dtype = dtype,
     load_in_4bit = load_in_4bit,