Model Card for Kimiko_J

This is my new Kimiko models, trained with GPT-J for...purpose

Model Details

Model Description

• Developed by: nRuaif
• Model type: Decoder only
• License: CC BY-NC-SA
• Finetuned from model [optional]: GPT-J

Model Sources [optional]

• Repository: https://github.com/OpenAccess-AI-Collective/axolotl

Uses

Direct Use

This model is trained on 3k examples of instructions dataset, high quality roleplay, for best result follow this format

<<HUMAN>>
How to do abc

<<AIBOT>>
Here is how

Or with system prompting for roleplay

<<SYSTEM>>
A's Persona:
B's Persona:
Scenario:
Add some instruction here on how you want your RP to go.

Bias, Risks, and Limitations

All bias of this model come from GPT-J with an exception of NSFW bias.....

Training Details

Training Data

3000 examples from LIMAERP, LIMA and I sample 1000 good instruction from Airboro

Training Procedure

Model is trained with 1 L4 from GCP costing a whooping 1USD

Training Hyperparameters

• Training regime: [More Information Needed]

3 epochs with 0.0002 lr, full 4096 ctx token, LoRA

Speeds, Sizes, Times [optional]

It takes 5 hours to train this model with xformers enable

[More Information Needed]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: L4 with 12CPUs 48gb ram
• Hours used: 5
• Cloud Provider: GCP
• Compute Region: US
• Carbon Emitted: 0.2KG