Duxiaoman-DI
/

XuanYuan-6B-Chat-4bit

Text Generation

Inference Endpoints

Model card Files Files and versions Community

homeyang commited on Mar 8

Commit

302c102

•

1 Parent(s): a39977a

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -57,4 +57,5 @@ print(f"输入: {content}")
 inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.95)
 outputs = tokenizer.decode(outputs.cpu()[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
-print(f"输出: {outputs}")

 inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.95)
 outputs = tokenizer.decode(outputs.cpu()[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
+print(f"输出: {outputs}")
+```