metadata

license: other
language:
  - en
tags:
  - causal-lm
  - llama
inference: false

Wizard-Vicuna-13B-GPTQ

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

It is the result of quantising to 4bit using GPTQ-for-LLaMa.

Repositories available

How to easily download and use this model in text-generation-webui

Open the text-generation-webui UI as normal.

Click the Model tab.
Under Download custom model or LoRA, enter TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ.
Click Download.
Wait until it says it's finished downloading.
Click the Refresh icon next to Model in the top left.
In the Model drop-down: choose the model you just downloaded, Wizard-Vicuna-13B-Uncensored-GPTQ.
If you see an error in the bottom right, ignore it - it's temporary.
Fill out the GPTQ parameters on the right: Bits = 4, Groupsize = 128, model_type = Llama
Click Save settings for this model in the top right.
Click Reload the Model in the top right.
Once it says it's loaded, click the Text Generation tab and enter a prompt!

Provided files

Compatible file - Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors

In the main branch - the default one - you will find Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors

This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility

It was created without the --act-order parameter. It may have slightly lower inference quality compared to the other file, but is guaranteed to work on all versions of GPTQ-for-LLaMa and text-generation-webui.

Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors
- Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
- Works with AutoGPTQ.
- Works with text-generation-webui one-click-installers
- Parameters: Groupsize = 128g. No act-order.
- Command used to create the GPTQ:
```
python llama.py ehartford_Wizard-Vicuna-13B-Uncensored c4 --wbits 4 --groupsize 128 --true-sequential --save_safetensors Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors
```

Latest file with act-order - Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.latest.act-order.safetensors

In the latest branch you will find Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.latest.act-order.safetensors

This requires recent GPTQ-for-LLaMa code. It will not work with ooba's fork.

It was created with the --act-order parameter to maximise inference quality.

To download this branch in text-generation-webui, enter TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ:latest in the Download Model box.

Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.latest.act-order.safetensors
- Works only with recent GPTQ-for-LLaMa.
- Works with AutoGPTQ.
- Will not work with text-generation-webui one-click-installers
- Parameters: Groupsize = 128g. Act order.
- Command used to create the GPTQ:
```
python llama.py ehartford_Wizard-Vicuna-13B-Uncensored c4 --wbits 4 --groupsize 128 --true-sequential --act-order --save_safetensors Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.latest.act-order.safetensors
```

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.