holoduke

I am really an AI noob. But lets say i tried the 7b model for translations purposes with below acceptable results. Can i train the model with 1 million of translated sentences to improve the quality of the translation output?

Method-X
Can you give an example on how you prompted the model? Your issue is probably related to that, but I would need an example to be sure. I've found the 7b Alpaca model [1] to work surprisingly well! Here's how you're supposed to prompt it:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction: {instruction}

### Response:

or

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction: {instruction}

### Input: {input}

### Response:

[1] https://github.com/cocktailpeanut/dalai