Hudhayfah/TestRepo

1---2language:3- en4license: apache-2.05library_name: transformers6datasets:7- Fredithefish/openassistant-guanaco-unfiltered8model_name: Guanaco 3B Uncensored v29inference: true10model_creator: Fredithefish11model_link: https://huggingface.co/Fredithefish/Guanaco-3B-Uncensored-v212model_type: gptneox13pipeline_tag: conversational14quantized_by: TheBloke15base_model: Fredithefish/Guanaco-3B-Uncensored-v216---17 18<!-- header start -->19<!-- 200823 -->20<div style="width: auto; margin-left: auto; margin-right: auto">21<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">22</div>23<div style="display: flex; justify-content: space-between; width: 100%;">24    <div style="display: flex; flex-direction: column; align-items: flex-start;">25        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>26    </div>27    <div style="display: flex; flex-direction: column; align-items: flex-end;">28        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>29    </div>30</div>31<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>32<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">33<!-- header end -->34 35# Guanaco 3B Uncensored v2 - GPTQ36- Model creator: [Fredithefish](https://huggingface.co/Fredithefish)37- Original model: [Guanaco 3B Uncensored v2](https://huggingface.co/Fredithefish/Guanaco-3B-Uncensored-v2)38 39<!-- description start -->40## Description41 42This repo contains GPTQ model files for [Fredithefish's Guanaco 3B Uncensored v2](https://huggingface.co/Fredithefish/Guanaco-3B-Uncensored-v2).43 44Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.45 46<!-- description end -->47<!-- repositories-available start -->48## Repositories available49 50* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ)51* [Fredithefish's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Fredithefish/Guanaco-3B-Uncensored-v2)52<!-- repositories-available end -->53 54<!-- prompt-template start -->55## Prompt template: Guanaco56 57```58### Human: {prompt}59### Assistant:60 61```62 63<!-- prompt-template end -->64 65<!-- README_GPTQ.md-provided-files start -->66## Provided files and GPTQ parameters67 68Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.69 70Each separate quant is in a different branch.  See below for instructions on fetching from different branches.71 72All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.73 74<details>75  <summary>Explanation of GPTQ parameters</summary>76 77- Bits: The bit size of the quantised model.78- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.79- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.80- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.81- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).82- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used.  Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.83- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.84 85</details>86 87| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |88| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |89| [main](https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.83 GB | No | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. | 90| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.98 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. | 91| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.88 GB | No | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. | 92| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.83 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. | 93| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.04 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. | 94| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.10 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |95 96<!-- README_GPTQ.md-provided-files end -->97 98<!-- README_GPTQ.md-download-from-branches start -->99## How to download from branches100 101- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Guanaco-3B-Uncensored-v2-GPTQ:gptq-4bit-32g-actorder_True`102- With Git, you can clone a branch with:103```104git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Guanaco-3B-Uncensored-v2-GPTQ105```106- In Python Transformers code, the branch is the `revision` parameter; see below.107<!-- README_GPTQ.md-download-from-branches end -->108<!-- README_GPTQ.md-text-generation-webui start -->109## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).110 111Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).112 113It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.114 1151. Click the **Model tab**.1162. Under **Download custom model or LoRA**, enter `TheBloke/Guanaco-3B-Uncensored-v2-GPTQ`.117  - To download from a specific branch, enter for example `TheBloke/Guanaco-3B-Uncensored-v2-GPTQ:gptq-4bit-32g-actorder_True`118  - see Provided Files above for the list of branches for each option.1193. Click **Download**.1204. The model will start downloading. Once it's finished it will say "Done".1215. In the top left, click the refresh icon next to **Model**.1226. In the **Model** dropdown, choose the model you just downloaded: `Guanaco-3B-Uncensored-v2-GPTQ`1237. The model will automatically load, and is now ready for use!1248. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.125  * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.1269. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!127<!-- README_GPTQ.md-text-generation-webui end -->128 129<!-- README_GPTQ.md-use-from-python start -->130## How to use this GPTQ model from Python code131 132### Install the necessary packages133 134Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.135 136```shell137pip3 install transformers>=4.32.0 optimum>=1.12.0138pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7139```140 141If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:142 143```shell144pip3 uninstall -y auto-gptq145git clone https://github.com/PanQiWei/AutoGPTQ146cd AutoGPTQ147pip3 install .148```149 150### For CodeLlama models only: you must use Transformers 4.33.0 or later.151 152If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:153```shell154pip3 uninstall -y transformers155pip3 install git+https://github.com/huggingface/transformers.git156```157 158### You can then use the following code159 160```python161from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline162 163model_name_or_path = "TheBloke/Guanaco-3B-Uncensored-v2-GPTQ"164# To use a different branch, change revision165# For example: revision="gptq-4bit-32g-actorder_True"166model = AutoModelForCausalLM.from_pretrained(model_name_or_path,167                                             device_map="auto",168                                             trust_remote_code=False,169                                             revision="main")170 171tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)172 173prompt = "Tell me about AI"174prompt_template=f'''### Human: {prompt}175### Assistant:176 177'''178 179print("\n\n*** Generate:")180 181input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()182output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)183print(tokenizer.decode(output[0]))184 185# Inference can also be done using transformers' pipeline186 187print("*** Pipeline:")188pipe = pipeline(189    "text-generation",190    model=model,191    tokenizer=tokenizer,192    max_new_tokens=512,193    do_sample=True,194    temperature=0.7,195    top_p=0.95,196    top_k=40,197    repetition_penalty=1.1198)199 200print(pipe(prompt_template)[0]['generated_text'])201```202<!-- README_GPTQ.md-use-from-python end -->203 204<!-- README_GPTQ.md-compatibility start -->205## Compatibility206 207The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).208 209[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.210 211[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.212<!-- README_GPTQ.md-compatibility end -->213 214<!-- footer start -->215<!-- 200823 -->216## Discord217 218For further support, and discussions on these models and AI in general, join us at:219 220[TheBloke AI's Discord server](https://discord.gg/theblokeai)221 222## Thanks, and how to contribute223 224Thanks to the [chirper.ai](https://chirper.ai) team!225 226Thanks to Clay from [gpus.llm-utils.org](llm-utils)!227 228I'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.229 230If 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.231 232Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.233 234* Patreon: https://patreon.com/TheBlokeAI235* Ko-Fi: https://ko-fi.com/TheBlokeAI236 237**Special thanks to**: Aemon Algiz.238 239**Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser240 241 242Thank you to all my generous patrons and donaters!243 244And thank you again to a16z for their generous grant.245 246<!-- footer end -->247 248# Original model card: Fredithefish's Guanaco 3B Uncensored v2249 250 251<img src="https://huggingface.co/Fredithefish/Guanaco-3B-Uncensored/resolve/main/Guanaco-Uncensored.jpg" alt="Alt Text" width="295"/>252 253# ✨ Guanaco - 3B - Uncensored ✨254 255 256Guanaco-3B-Uncensored has been fine-tuned for 6 epochs on the [Unfiltered Guanaco Dataset.](https://huggingface.co/datasets/Fredithefish/openassistant-guanaco-unfiltered) using [RedPajama-INCITE-Base-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1) as the base model.257<br>The model does not perform well with languages other than English.258<br>Please note: This model is designed to provide responses without content filtering or censorship. It generates answers without denials.259 260## Special thanks261I would like to thank AutoMeta for providing me with the computing power necessary to train this model.262 263 264### Prompt Template265```266### Human: {prompt} ### Assistant:267```268 269### Changes270This is the second version of the 3B parameter Guanaco uncensored model.271The model has been fine-tuned on the V2 of the Guanaco unfiltered dataset.272