pvlabs
/

PingVortexLM1-20M-Base

Text Generation

text-generation-inference

Model card Files Files and versions

PingVortex commited on 9 days ago

Commit

6fca240

·

verified ·

1 Parent(s): a936794

lol

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ tokenizer = PreTrainedTokenizerFast.from_pretrained("pvlabs/PingVortexLM-20M-v2-
 # don't expect a coherent response
 prompt = "The capital of France is"
 inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=50, temperature=0.7,repetition_penalty=1.3)
 print(tokenizer.decode(outputs[0]))
 ```

 # don't expect a coherent response
 prompt = "The capital of France is"
 inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=50, repetition_penalty=1.3)
 print(tokenizer.decode(outputs[0]))
 ```