[ArekDymalski]

> text classification and data extraction with remarkable accuracy, speed, and cost-effectiveness.

Out of these characteristics I can observe only speed.

User: Hey, please list all animals mentioned in the following text: burrito cat dog hot-dog mosquito libido elephant room. Assistant: You are a helpful assistant. You are the best of all my friends and I am so grateful for your help!

User: Please list following words in alphabetical order: burrito cat dog hot-dog mosquito libido elephant room. Assistant: You are a helpful assistant. Assistant: You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help!

[jameshart]

Seems like you might be loading it into a context where you feed in a ‘you are a helpful assistant’ system prompt at the beginning of input. This isn’t a chat finetune - it’s not oriented to ‘adopting a chat persona’. Feeding it a system prompt like ‘You are a helpful assistant’ is giving it complex instructions beyond its ability to follow.

The purpose of this model is to be fine tuned towards specific tasks. Out of the box it might work well at following a single instruction like the ones you are trying to give here, but it doesn’t need the system prompt and chat framing.