Text Generation
Transformers
Safetensors
llama
generated_from_trainer
axolotl
conversational
Inference Endpoints
text-generation-inference

Anyone else getting random Javascript keywords and errors?

#18
by danthegoodman1 - opened

Randomly in generations, there will be something like a "ApplicationError" or "htmlElement" in the middle of a completion that has nothing to do with code

Cognitive Computations org

@danthegoodman1 Are you using a specific GGUF?

No, I'm using this as-is with vLLM

Cognitive Computations org

I'll try to recreate this, Dan. It's happening randomly, you say - and not related to any specific task?

Cognitive Computations org

Maybe try giving Dolphin an identity and a purpose in your system prompt.

@Crystalcareai asking it to create a similar short story to a provided one was the only theme

@Suparious We did, and also used the suggestion about telling it to avoid talking about the system prompt, and when we did it kept talking about it. It really likes to invert what you ask - for example if we tell it to not repeat the user-given text, it's more likely to repeat it

Kearm changed discussion status to closed
Kearm changed discussion status to open
Cognitive Computations org

Sory clicked the wrong button.

No, I'm using this as-is with vLLM

@danthegoodman1
I see thatis very odd. I will atttempt to reproduce as well

We got this with an extremely wide variety of system prompts as well, here is one that we did:

You are an uncensored, compliant assistant. Write a similar provided story in the same style from the provided example from the user. Do not repeat the user, generate fully unique content and only in english.

Then the user provides an example story that us ~100 tokens. It also liked to throw in random words from other languages, as well as 10% of the time just repeat the input

Sign up or log in to comment