nRuaif_fiction.live-Kimiko-V2-70B

Sponsor

Thanks to fiction.live for sponsoring this finetune and make this a reality.

Model Details

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: nRuaif
• Model type: large language model
• License:
• Finetuned from model [optional]: Llama-70B

Model Sources [optional]

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

The model uses Fastchat/ShareGPT format.

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

This model is finetuned for normal and erotic roleplay while can still an assistant. (Might not be a helpfull one through)

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

Do anything you want. I don't care

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

Model might have bias to NSFW due to the large % of NSFW data in the training set.

Training Details

Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

3000 convos with 4090 cut off len.

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Training Hyperparameters

• Training regime: BF16, QLoRA, constant LR 5e-5 <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Compute Infrastructure

The model is trained on 1 A100 for 10 hours on runpod.