TheBloke's picture
Update README.md
86d0b72
|
raw
history blame
4.11 kB
metadata
license: other
datasets:
  - ehartford/wizard_vicuna_70k_unfiltered
language:
  - en
tags:
  - uncensored
inference: false

Wizard-Vicuna-13B-Uncensored GGML

This is GGML format quantised 4bit and 5bit models of Eric Hartford's 'uncensored' training of Wizard-Vicuna 13B.

This repo is the result of quantising to 4bit and 5bit GGML for CPU inference using llama.cpp.

Repositories available

THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!

llama.cpp recently made a breaking change to its quantisation methods.

I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 12th or later (commit b9fd7ee or later) to use them.

If you are currently unable to update llama.cpp, eg because you use a UI which hasn't updated yet, you can find GGMLs compatible with the older llama.cpp code in branch previous_llama

Imgur

Provided files

Name Quant method Bits Size RAM required Use case
Wizard-Vicuna-13B-Uncensored.ggml.q4_0.bin q4_0 4bit 8.14GB 10.5GB 4-bit.
Wizard-Vicuna-13B-Uncensored.ggml.q5_0.bin q5_0 5bit 8.95GB 11.0GB 5-bit. Higher accuracy, higher resource usage and slower inference.
Wizard-Vicuna-13B-Uncensored.ggml.q5_1.bin q5_1 5bit 9.76GB 12.25GB 5-bit. Even higher accuracy, and higher resource usage and slower inference.
Wizard-Vicuna-13B-Uncensored.ggml.q8_0.bin q8_0 8bit 14.6GB 17GB 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use.

How to run in llama.cpp

I use the following command line; adjust for your tastes and needs:

./main -t 8 -m Wizard-Vicuna-13B-Uncensored.ggml.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: write a story about llamas ### Response:"

Change -t 8 to the number of physical CPU cores you have.

How to run in text-generation-webui

GGML models can be loaded into text-generation-webui by installing the llama.cpp module, then placing the ggml model file in a model folder as usual.

Further instructions here: text-generation-webui/docs/llama.cpp-models.md.

Note: at this time text-generation-webui may not support the new May 12th llama.cpp quantisation methods.

Thireus has written a great guide on how to update it to the latest llama.cpp code which may be useful to get text-gen-ui working with the new llama.cpp quant methods sooner.

Original model card

This is wizard-vicuna-13b trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.

Shout out to the open source AI/ML community, and everyone who helped me out.

Note:

An uncensored model has no guardrails.

You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.

Publishing anything this model generates is the same as publishing it yourself.

You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.