Open maotoledo opened 1 year ago
me too
Same issue here, how to finish the sentence?
try to adjust the chunk_size=1000 and chunk_overlap=200, test with 1500 and 250 respectively and see if that makes any difference.
any update on this issue please? When I increased the chunk_size=1000 and chunk_overlap=200 then error comes from Inference API: "Input validation error: inputs
must have less than 1024 tokens. Given: 1208"
How to fix this response completion issue? Please assist @kkatrina28 @DjangoMaker @jasonzhouxf
try this :
llm = HuggingFaceHub(repo_id="tiiuae/falcon-7b-instruct", task='text-generation', model_kwargs={'max_new_tokens': 200})
I've processed a document of a book chapter. But It gives me always same limited length response.![image](https://github.com/alejandro-ao/ask-multiple-pdfs/assets/95873143/aaf19205-d473-4b1a-8486-2949b90f49d1)