Naseej
/

noon-7b

Text Generation

question-answering

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

isrouush commited on Jun 21, 2023

Commit

58f5281

•

1 Parent(s): 935473a

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -61,11 +61,13 @@ generation_pipeline = pipeline("text-generation", model=model, tokenizer=tokeniz
 # But encourage you to try different values
 response = generation_pipeline(prompt,
     pad_token_id=tokenizer.eos_token_id,
     num_beams=4,
     max_length=500,
     top_p=0.1,
     repetition_penalty = 3.0,
-    no_repeat_ngram_size = 3)[0]['generated_text']
 print(response)
 ```

 # But encourage you to try different values
 response = generation_pipeline(prompt,
     pad_token_id=tokenizer.eos_token_id,
+    do_sample=False,
     num_beams=4,
     max_length=500,
     top_p=0.1,
+    top_k=20,
     repetition_penalty = 3.0,
+    no_repeat_ngram_size=3)[0]['generated_text']
 print(response)
 ```