thanhkt
/

Qwen2.5-1.5B-Vi-Alpaca-GGUF

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

thanhkt commited on 27 days ago

Commit

d48820d

•

1 Parent(s): 72cfabb

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -35,7 +35,7 @@ load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "thanhkt/Qwen2.5-1.5B-MathInstruct",
     max_seq_length = max_seq_length,
     dtype = dtype,
     load_in_4bit = load_in_4bit,

 model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "thanhkt/Qwen2.5-1.5B-Vi-Alpaca-GGUF",
     max_seq_length = max_seq_length,
     dtype = dtype,
     load_in_4bit = load_in_4bit,