fofr / star-trek-gpt-j-6b

gpt-j-6b trained on the Memory Alpha Star Trek Wiki

  • Public
  • 434 runs
  • A100 (80GB)
  • GitHub
  • License

Input

*string
Shift + Return to add a new line

Input Prompt.

integer
(minimum: 1)

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 500

string

Choose a decoding method

Default: "top_p"

integer

Valid if you choose top_k decoding. The number of highest probability vocabulary tokens to keep for top-k-filtering

Default: 50

number
(minimum: 0.01, maximum: 1)

Valid if you choose top_p decoding. When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 1

number
(minimum: 0.01, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.75

number
(minimum: 0.01, maximum: 5)

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Default: 1.2

Output

The most popular holodecks were those at Starfleet Academy, and holographic programs created by Starfleet Command. The Academy featured a 'Star Trek'-themed program in its gymnasium, while other holosuites included a small zoo with various animals including Klingons, Cardassians, Ferengis, Bajorans, Yridians, Tellarites, Xindi-Reptilians, Vulcans, Romulans, Federation members, and several others from different Star Fleet organizations.
Generated in

Run time and cost

This model costs approximately $0.0041 to run on Replicate, or 243 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 3 seconds. The predict time for this model varies significantly based on the inputs.

Readme

A GPT-J-6B large language model fine tuned on the Star Trek Wiki ‘Memory Alpha’.

This model is an experiment to see how the Wiki information translates after fine tuning.

Content from Memory Alpha is licensed under a creative commons non-commercial license: https://memory-alpha.fandom.com/wiki/Memory_Alpha:Creative_Commons_License

Intended use

An experiment in fine tuning.

Ethical considerations

This model is not suitable for commercial purposes.

Caveats and recommendations

The model has deep knowledge of the Star Trek universe, but sometimes it acts like the facts have been shuffled.