[_just7_]

Give it few shot examples and the quality should improve a lot. If you want a bot able to do technical Q&A give it two questions as well as the answers in its prompt. The model will then infer it's role as an AI that answer questions truthfully, and will try it's best to continue along those lines

[Roritharr]

I gave it the prompt thats the example from here: https://huggingface.co/blog/few-shot-learning-gpt-neo-and-in...

Tweet: "I hate it when my phone battery dies." Sentiment: Negative ### Tweet: "My day has been " Sentiment: Positive ### Tweet: "This is the link to the article" Sentiment: Neutral ### Tweet: "This new music video was incredibile" Sentiment:

and it's output was:

Tweet: "I hate it when my phone battery dies." Sentiment: Negative ### Tweet: "My day has been 90% balls." Seentiment: Negative ### Twitter: "i don't have a favourite type of music i just hate country" Seentiment: Negative ### Twitter: "c'mon first sunshine of the year...why the rain already?!" Seentiment: Negative ### Twitter: "Dear twitter, are you getting tired of me yet? Seentiment: Negative ### Twitter: "I don't care about the race, I just care about the president being a psych

Doesn't feel like that did the trick, but at least you got me to setup the shell command in a way where I pipe long-form prompts in via a separate file.

[visarga]

I think the model only has pre-training on large text but not multi-task fine-tuning and RLHF. So it can be improved a lot.

[speedgoose]

Hopefully a RLHF fine tuned model will be released soon because that will make the technology much more useful and less disappointing to people trying to run an alternative of ChatGPT on their local machine.

[mkl]

It invented "Seentiment"?