flyingfishinwater
/

tinystories_zh

Text Generation

text-generation-inference

Model card Files Files and versions

Qi Wang commited on Sep 21, 2023

Commit

7d55cd5

·

1 Parent(s): 70fb6e9

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -84,7 +84,7 @@ config = AutoConfig.from_pretrained(model_path)
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForCausalLM.from_pretrained(model_path, config=config)
 inputs = tokenizer("从前", return_tensors="pt", add_special_tokens=True)
-outputs = model.generate(**inputs, max_length=768)
 text = tokenizer.batch_decode(outputs)[0]
 print(text)
 ```

 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForCausalLM.from_pretrained(model_path, config=config)
 inputs = tokenizer("从前", return_tensors="pt", add_special_tokens=True)
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.9)
 text = tokenizer.batch_decode(outputs)[0]
 print(text)
 ```