ctransformers
ctransformers copied to clipboard
About streaming server in openai API like
Hello, I get a weired issue when serving using ctransformers.
code:
model = AutoModelForCausalLM.from_pretrained(
args.base_model, **config
)
iterator: Generator = model.generate(gen_kwargs["inputs"])
for chat_chunk in iterator:
new_text = model.detokenize(chat_chunk)
print(new_text, end="", flush=True)
the new_text
are right, but when I return it one by one, there seems not white space between.
And printed out also have not white space
Does anyone got some idea why?