19 lines
689 B
Markdown
19 lines
689 B
Markdown
|
# izzilis gpt-2 bot
|
||
|
|
|
||
|
|
Meant to be used with a finetuned GPT-2 model
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
just run it, it'll make a `bot_config.json` file in the running path
|
||
|
|
|
||
|
|
fill it out
|
||
|
|
|
||
|
|
run again
|
||
|
|
|
||
|
|
## Docker Usage
|
||
|
|
|
||
|
|
The dockerfile makes a few assumptions which you must fulfill:
|
||
|
|
|
||
|
|
* the gpt python files & model are in the gpt/ directory (this directory doesn't exist, please make it (it must contain both `generate_unconditional_samples.py` and the `models` directory containing your finetuned model))
|
||
|
|
* you have ran the bot already. Once to generate a `bot_config.json` and a second time, once the aforementioned file is generated and filled out by the user, `fediverse.toml` from authenticating with the instance.
|