TheBloke/Kimiko-v2-13B-fp16

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

---

Kimiko v2 13B - FP16

• Model creator: nRuaif
• Original model: Kimiko v2 13B

Description

This repo contains pytorch format fp16 model files for nRuaif's Kimiko v2 13B.

It is the result of merging and/or converting the source repository to float16.

Repositories available

• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)
• Unquantised fp16 model in pytorch format, for GPU inference and for further conversions
• nRuaif's original LoRA adapter, which can be merged on to the base model.

Prompt template: Vicuna

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the chirper.ai team!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Kacper Wikieł, knownsqashed, Leonard Tan, Asp the Wyvern, Daniel P. Andersen, Luke Pendergrass, Stanislav Ovsiannikov, RoA, Dave, Ai Maven, Kalila, Will Dee, Imad Khwaja, Nitin Borwankar, Joseph William Delisle, Tony Hughes, Cory Kujawski, Rishabh Srivastava, Russ Johnson, Stephen Murray, Lone Striker, Johann-Peter Hartmann, Elle, J, Deep Realms, SuperWojo, Raven Klaugh, Sebastain Graf, ReadyPlayerEmma, Alps Aficionado, Mano Prime, Derek Yates, Gabriel Puliatti, Mesiah Bishop, Magnesian, Sean Connelly, biorpg, Iucharbius, Olakabola, Fen Risland, Space Cruiser, theTransient, Illia Dulskyi, Thomas Belote, Spencer Kim, Pieter, John Detwiler, Fred von Graf, Michael Davis, Swaroop Kallakuri, subjectnull, Clay Pascal, Subspace Studios, Chris Smitley, Enrico Ros, usrbinkat, Steven Wood, alfie_i, David Ziegler, Willem Michiel, Matthew Berman, Andrey, Pyrater, Jeffrey Morgan, vamX, LangChain4j, Luke @flexchar, Trenton Dambrowitz, Pierre Kircher, Alex, Sam, James Bentley, Edmond Seymore, Eugene Pentland, Pedro Madruga, Rainer Wilmers, Dan Guido, Nathan LeClaire, Spiking Neurons AB, Talal Aujan, zynix, Artur Olbinski, Michael Levine, 阿明, K, John Villwock, Nikolai Manek, Femi Adebogun, senxiiz, Deo Leter, NimbleBox.ai, Viktor Bowallius, Geoffrey Montalvo, Mandus, Ajan Kanaga, ya boyyy, Jonathan Leane, webtim, Brandon Frisco, danny, Alexandros Triantafyllidis, Gabriel Tamborski, Randy H, terasurfer, Vadim, Junyu Yang, Vitor Caleffi, Chadd, transmissions 11

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: nRuaif's Kimiko v2 13B

Model Details

Model Description

• Developed by: nRuaif
• Model type: large language model
• License:
• Finetuned from model [optional]: Llama-13B

Model Sources [optional]

Uses

The model uses Fastchat/ShareGPT format.

Direct Use

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

Do anything you want. I don't care

Bias, Risks, and Limitations

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

Training Details

Training Data

3000 convos with 4090 cut off len.

Training Procedure

Training Hyperparameters

• Training regime: BF16, QLoRA, constant LR 5e-5

Compute Infrastructure

The model is trained on 1 A100 for 2 hours on runpod.