| ▲ | resiros 6 days ago |
| I look forward for the day someone trains a model that can do good writing, without emdashes, it's not but and all of the AI slop. |
|
| ▲ | astrange 6 days ago | parent | next [-] |
| You want a base model like text-davinci-001. Instruct models have most of their creativity destroyed. |
| |
| ▲ | Gracana 5 days ago | parent [-] | | How do you use the base model? | | |
| ▲ | astrange 4 days ago | parent [-] | | OpenAI Playground still has it. Otherwise go out and find one. | | |
| ▲ | Gracana 3 days ago | parent [-] | | I mean in terms of prompting. What methods do you employ to get useful results out of a model that is not tuned for particular form of response? | | |
| ▲ | Gracana 2 days ago | parent [-] | | Seems simple enough, all the base models do is continuation, but you can do few-shot prompting to establish a pattern if you want. I will have to give it a try. |
|
|
|
|
|
| ▲ | 1gn15 5 days ago | parent | prev [-] |
| Try one of the fine-tunes from https://allura.moe/. Or use an autocomplete model. Mistral and Qwen have them. |