barty
/

CodeLlama-13B-MORepair

Text Generation

Model card Files Files and versions Community

barty commited on 18 days ago

Commit

f2b7f5a

·

verified ·

1 Parent(s): 8c0f52b

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -54,7 +54,8 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     device_map="auto",
-    load_in_8bit=True  # Enable 8-bit quantization for efficiency
 )
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     device_map="auto",
+    load_in_8bit=True,
+    torch_dtype=torch.float16
 )
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)