Update base_model formatting

2025-01-19 15:53:47 +08:00
parent 1cad7af032
commit 96599ff289
15 changed files with 94038 additions and 58 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,47 +1,36 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.npy filter=lfs diff=lfs merge=lfs -text
 *.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *.tfevents* filter=lfs diff=lfs merge=lfs -text
 *.db* filter=lfs diff=lfs merge=lfs -text
 *.ark* filter=lfs diff=lfs merge=lfs -text
 **/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
 **/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
 **/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.gguf* filter=lfs diff=lfs merge=lfs -text
 *.ggml filter=lfs diff=lfs merge=lfs -text
 *.llamafile* filter=lfs diff=lfs merge=lfs -text
 *.pt2 filter=lfs diff=lfs merge=lfs -text
 *.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.npy filter=lfs diff=lfs merge=lfs -text
 *.npz filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
--- a/LICENSE.txt
+++ b/LICENSE.txt
@@ -0,0 +1,126 @@
 LLAMA 2 COMMUNITY LICENSE AGREEMENT	
 Llama 2 Version Release Date: July 18, 2023
 "Agreement" means the terms and conditions for use, reproduction, distribution and 
 modification of the Llama Materials set forth herein.
 "Documentation" means the specifications, manuals and documentation 
 accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
 libraries/llama-downloads/.
 "Licensee" or "you" means you, or your employer or any other person or entity (if 
 you are entering into this Agreement on such person or entity's behalf), of the age 
 required under applicable laws, rules or regulations to provide legal consent and that 
 has legal authority to bind your employer or such other person or entity if you are 
 entering in this Agreement on their behalf.
 "Llama 2" means the foundational large language models and software and 
 algorithms, including machine-learning model code, trained model weights, 
 inference-enabling code, training-enabling code, fine-tuning enabling code and other 
 elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
 libraries/llama-downloads/.
 "Llama Materials" means, collectively, Meta's proprietary Llama 2 and 
 Documentation (and any portion thereof) made available under this Agreement.
 "Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you 
 are an entity, your principal place of business is in the EEA or Switzerland) and Meta 
 Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
 By clicking "I Accept" below or by using or distributing any portion or element of the 
 Llama Materials, you agree to be bound by this Agreement.
 1. License Rights and Redistribution. 
      a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
 transferable and royalty-free limited license under Meta's intellectual property or 
 other rights owned by Meta embodied in the Llama Materials to use, reproduce, 
 distribute, copy, create derivative works of, and make modifications to the Llama 
 Materials.  
      b. Redistribution and Use.  
            i. If you distribute or make the Llama Materials, or any derivative works 
 thereof, available to a third party, you shall provide a copy of this Agreement to such 
 third party. 
            ii.  If you receive Llama Materials, or any derivative works thereof, from 
 a Licensee as part of an integrated end user product, then Section 2 of this 
 Agreement will not apply to you. 
            iii. You must retain in all copies of the Llama Materials that you 
 distribute the following attribution notice within a "Notice" text file distributed as a 
 part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License, 
 Copyright (c) Meta Platforms, Inc. All Rights Reserved."
            iv. Your use of the Llama Materials must comply with applicable laws 
 and regulations (including trade compliance laws and regulations) and adhere to the 
 Acceptable Use Policy for the Llama Materials (available at 
 https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into 
 this Agreement.
            v. You will not use the Llama Materials or any output or results of the 
 Llama Materials to improve any other large language model (excluding Llama 2 or 
 derivative works thereof).  
 2. Additional Commercial Terms. If, on the Llama 2 version release date, the 
 monthly active users of the products or services made available by or for Licensee, 
 or Licensee's affiliates, is greater than 700 million monthly active users in the 
 preceding calendar month, you must request a license from Meta, which Meta may 
 grant to you in its sole discretion, and you are not authorized to exercise any of the 
 rights under this Agreement unless or until Meta otherwise expressly grants you 
 such rights.
 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE 
 LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE 
 PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, 
 EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY 
 WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR 
 FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE 
 FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING 
 THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR 
 USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE 
 LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, 
 NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS 
 AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, 
 CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN 
 IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF 
 ANY OF THE FOREGOING.
 5. Intellectual Property.
      a. No trademark licenses are granted under this Agreement, and in 
 connection with the Llama Materials, neither Meta nor Licensee may use any name 
 or mark owned by or associated with the other or any of its affiliates, except as 
 required for reasonable and customary use in describing and redistributing the 
 Llama Materials.
      b. Subject to Meta's ownership of Llama Materials and derivatives made by or 
 for Meta, with respect to any derivative works and modifications of the Llama 
 Materials that are made by you, as between you and Meta, you are and will be the 
 owner of such derivative works and modifications.
      c. If you institute litigation or other proceedings against Meta or any entity 
 (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama 
 Materials or Llama 2 outputs or results, or any portion of any of the foregoing, 
 constitutes infringement of intellectual property or other rights owned or licensable 
 by you, then any licenses granted to you under this Agreement shall terminate as of 
 the date such litigation or claim is filed or instituted. You will indemnify and hold 
 harmless Meta from and against any claim by any third party arising out of or related 
 to your use or distribution of the Llama Materials.
 6. Term and Termination. The term of this Agreement will commence upon your 
 acceptance of this Agreement or access to the Llama Materials and will continue in 
 full force and effect until terminated in accordance with the terms and conditions 
 herein. Meta may terminate this Agreement if you are in breach of any term or 
 condition of this Agreement. Upon termination of this Agreement, you shall delete 
 and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the 
 termination of this Agreement. 
 7. Governing Law and Jurisdiction. This Agreement will be governed and 
 construed under the laws of the State of California without regard to choice of law 
 principles, and the UN Convention on Contracts for the International Sale of Goods 
 does not apply to this Agreement. The courts of California shall have exclusive 
 jurisdiction of any dispute arising out of this Agreement. 
--- a/1
+++ b/1
@@ -0,0 +1 @@
 Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
--- a/README.md
+++ b/README.md
@@ -1,47 +1,333 @@
 ---
-license: Apache License 2.0
+license: llama2
 datasets:
 - totally-not-an-llm/EverythingLM-data-V3
 model_name: EverythingLM 13B V3 16K
 base_model: totally-not-an-llm/EverythingLM-13b-V3-16k
 inference: false
 model_creator: Kai Howard
 model_type: llama
 prompt_template: 'USER: {prompt}
-#model-type:
+  ASSISTANT:
 ##如 gpt、phi、llama、chatglm、baichuan 等
 #- gpt
-#domain:
+  '
-##如 nlp、cv、audio、multi-modal
+quantized_by: TheBloke
 #- nlp
 #language:
 ##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
 #- cn 
 #metrics:
 ##如 CIDEr、Blue、ROUGE 等
 #- CIDEr
 #tags:
 ##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
 #- pretrained
 #tools:
 ##如 vllm、fastchat、llamacpp、AdaSeq 等
 #- vllm
 ---
 ### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
 #### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
-SDK下载
+<!-- header start -->
-```bash
+<!-- 200823 -->
-#安装ModelScope
+<div style="width: auto; margin-left: auto; margin-right: auto">
-pip install modelscope
+<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 </div>
 <div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
        <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>
    </div>
 </div>
 <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>
 <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
 <!-- header end -->
 # EverythingLM 13B V3 16K - GPTQ
 - Model creator: [Kai Howard](https://huggingface.co/totally-not-an-llm)
 - Original model: [EverythingLM 13B V3 16K](https://huggingface.co/totally-not-an-llm/EverythingLM-13b-V3-16k)
 <!-- description start -->
 ## Description
 This repo contains GPTQ model files for [Kai Howard's EverythingLM 13B V3 16K](https://huggingface.co/totally-not-an-llm/EverythingLM-13b-V3-16k).
 Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
 <!-- description end -->
 <!-- repositories-available start -->
 ## Repositories available
 * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-AWQ)
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GGUF)
 * [Kai Howard's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/totally-not-an-llm/EverythingLM-13b-V3-16k)
 <!-- repositories-available end -->
 <!-- prompt-template start -->
 ## Prompt template: User-Assistant
 ```
 USER: {prompt}
 ASSISTANT:
 ```
 <!-- prompt-template end -->
 <!-- README_GPTQ.md-provided-files start -->
 ## Provided files, and GPTQ parameters
 Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
 Each separate quant is in a different branch.  See below for instructions on fetching from different branches.
 All 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.
 <details>
  <summary>Explanation of GPTQ parameters</summary>
 - Bits: The bit size of the quantised model.
 - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
 - 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.
 - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
 - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration 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).
 - 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.
 - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
 </details>
 | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
 | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
 | [main](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 8192 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | 
 | [gptq-4-32g-actorder_True](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ/tree/gptq-4-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 8192 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | 
 | [gptq-8--1g-actorder_True](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ/tree/gptq-8--1g-actorder_True) | 8 | None | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 8192 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. | 
 | [gptq-8-128g-actorder_True](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ/tree/gptq-8-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 8192 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. | 
 | [gptq-8-32g-actorder_True](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ/tree/gptq-8-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 8192 | 14.54 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. | 
 | [gptq-4-64g-actorder_True](https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ/tree/gptq-4-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [c4](https://huggingface.co/datasets/allenai/c4) | 8192 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
 <!-- README_GPTQ.md-provided-files end -->
 <!-- README_GPTQ.md-download-from-branches start -->
 ## How to download, including from branches
 ### In text-generation-webui
 To download from the `main` branch, enter `TheBloke/EverythingLM-13B-V3-16K-GPTQ` in the "Download model" box.
 To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/EverythingLM-13B-V3-16K-GPTQ:gptq-4-32g-actorder_True`
 ### From the command line
 I recommend using the `huggingface-hub` Python library:
 ```shell
 pip3 install huggingface-hub
 ```
 To download the `main` branch to a folder called `EverythingLM-13B-V3-16K-GPTQ`:
 ```shell
 mkdir EverythingLM-13B-V3-16K-GPTQ
 huggingface-cli download TheBloke/EverythingLM-13B-V3-16K-GPTQ --local-dir EverythingLM-13B-V3-16K-GPTQ --local-dir-use-symlinks False
 ```
 To download from a different branch, add the `--revision` parameter:
 ```shell
 mkdir EverythingLM-13B-V3-16K-GPTQ
 huggingface-cli download TheBloke/EverythingLM-13B-V3-16K-GPTQ --revision gptq-4-32g-actorder_True --local-dir EverythingLM-13B-V3-16K-GPTQ --local-dir-use-symlinks False
 ```
 <details>
  <summary>More advanced huggingface-cli download usage</summary>
 If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
 The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
 For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
 To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
 ```shell
 pip3 install hf_transfer
 ```
 And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
 ```shell
 mkdir EverythingLM-13B-V3-16K-GPTQ
 HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/EverythingLM-13B-V3-16K-GPTQ --local-dir EverythingLM-13B-V3-16K-GPTQ --local-dir-use-symlinks False
 ```
 Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
 </details>
 ### With `git` (**not** recommended)
 To clone a specific branch with `git`, use a command like this:
 ```shell
 git clone --single-branch --branch gptq-4-32g-actorder_True https://huggingface.co/TheBloke/EverythingLM-13B-V3-16K-GPTQ
 ```
 Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
 <!-- README_GPTQ.md-download-from-branches end -->
 <!-- README_GPTQ.md-text-generation-webui start -->
 ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
 Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
 It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
 1. Click the **Model tab**.
 2. Under **Download custom model or LoRA**, enter `TheBloke/EverythingLM-13B-V3-16K-GPTQ`.
  - To download from a specific branch, enter for example `TheBloke/EverythingLM-13B-V3-16K-GPTQ:gptq-4-32g-actorder_True`
  - see Provided Files above for the list of branches for each option.
 3. Click **Download**.
 4. The model will start downloading. Once it's finished it will say "Done".
 5. In the top left, click the refresh icon next to **Model**.
 6. In the **Model** dropdown, choose the model you just downloaded: `EverythingLM-13B-V3-16K-GPTQ`
 7. The model will automatically load, and is now ready for use!
 8. 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.
  * 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`.
 9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
 <!-- README_GPTQ.md-text-generation-webui end -->
 <!-- README_GPTQ.md-use-from-python start -->
 ## How to use this GPTQ model from Python code
 ### Install the necessary packages
 Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
 ```shell
 pip3 install transformers optimum
 pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7
 ```
 If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
 ```shell
 pip3 uninstall -y auto-gptq
 git clone https://github.com/PanQiWei/AutoGPTQ
 cd AutoGPTQ
 git checkout v0.4.2
 pip3 install .
 ```
 ### You can then use the following code
 ```python
-#SDK模型下载
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-from modelscope import snapshot_download
+
-model_dir = snapshot_download('TheBloke/EverythingLM-13B-V3-16K-GPTQ')
+model_name_or_path = "TheBloke/EverythingLM-13B-V3-16K-GPTQ"
 # To use a different branch, change revision
 # For example: revision="gptq-4-32g-actorder_True"
 model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             revision="main")
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 prompt = "Tell me about AI"
 prompt_template=f'''USER: {prompt}
 ASSISTANT:
 '''
 print("\n\n*** Generate:")
 input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
 output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
 print(tokenizer.decode(output[0]))
 # Inference can also be done using transformers' pipeline
 print("*** Pipeline:")
 pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
 )
 print(pipe(prompt_template)[0]['generated_text'])
 ```
-Git下载
+<!-- README_GPTQ.md-use-from-python end -->
 <!-- README_GPTQ.md-compatibility start -->
 ## Compatibility
 The 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).
 [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.
 [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
 <!-- README_GPTQ.md-compatibility end -->
 <!-- footer start -->
 <!-- 200823 -->
 ## Discord
 For further support, and discussions on these models and AI in general, join us at:
 [TheBloke AI's Discord server](https://discord.gg/theblokeai)
 ## Thanks, and how to contribute
 Thanks to the [chirper.ai](https://chirper.ai) team!
 Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
 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**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
 Thank you to all my generous patrons and donaters!
 And thank you again to a16z for their generous grant.
 <!-- footer end -->
 # Original model card: Kai Howard's EverythingLM 13B V3 16K
 # EverythingLM-13b-V3-16k
 Introducing EverythingLM, a llama-2 based, general-purpose 13b model with 16k context thanks to LlongMa.  The model is trained on the EverythingLM-V3 dataset, more info can be found on the dataset page.
 The model is completely uncensored.
 Despite being "uncensored", the base model might be resistant; you might have to prompt-engineer certain prompts.
 ### Notable features:
 - Automatically triggered CoT reasoning.
 - Verbose and detailed replies.
 - Creative stories.
 - Good prompt understanding.
 ### Differences from V2:
 - Much more uncensored.
 - Actual roleplaying ability now!
 - General all around improvements thanks to the new dataset.  Check out the dataset for more info.
 ### Prompt format (Alpaca-chat):
 ```
-#Git模型下载
+USER: <prompt>
-git clone https://www.modelscope.cn/TheBloke/EverythingLM-13B-V3-16K-GPTQ.git
+ASSISTANT:
 ```
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+### Future plans:
 - Highest priority right now is V3.1 with more optimized training and iterative dataset improvements based on testing.
 ### Note:
 Through testing V2, I realized some alignment data had leaked in, causing the model to be less cooperative then intended.  This model should do much better due to stricter filetering.
--- a/USE_POLICY.md
+++ b/USE_POLICY.md
@@ -0,0 +1,50 @@
 # Llama 2 Acceptable Use Policy
 Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).
 ## Prohibited Uses
 We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to: 
 1. Violate the law or others’ rights, including to:
    1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 
        1. Violence or terrorism 
        2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
        3. Human trafficking, exploitation, and sexual violence
        4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
        5. Sexual solicitation
        6. Any other criminal activity
    2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
    3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
    4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 
    5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
    6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials
    7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 
 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following:
    1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
    2. Guns and illegal weapons (including weapon development)
    3. Illegal drugs and regulated/controlled substances
    4. Operation of critical infrastructure, transportation technologies, or heavy machinery
    5. Self-harm or harm to others, including suicide, cutting, and eating disorders
    6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
 3. Intentionally deceive or mislead others, including use of Llama 2 related to the following:
    1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
    2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
    3. Generating, promoting, or further distributing spam
    4. Impersonating another individual without consent, authorization, or legal right
    5. Representing that the use of Llama 2 or outputs are human-generated
    6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
 4. Fail to appropriately disclose to end users any known dangers of your AI system 
 Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
 * Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
 * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
 * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
 * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com)
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
 {
  "<pad>": 32000
 }
--- a/config.json
+++ b/config.json
@@ -0,0 +1,41 @@
 {
    "_name_or_path": "LLongMA-2-13b-16k",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 13824,
    "max_position_embeddings": 16384,
    "model_type": "llama",
    "num_attention_heads": 40,
    "num_hidden_layers": 40,
    "num_key_value_heads": 40,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
        "factor": 4.0,
        "type": "linear"
    },
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.31.0",
    "use_cache": true,
    "use_flash_attention": false,
    "vocab_size": 32000,
    "quantization_config": {
        "bits": 4,
        "group_size": 128,
        "damp_percent": 0.1,
        "desc_act": true,
        "sym": true,
        "true_sequential": true,
        "model_name_or_path": null,
        "model_file_base_name": "model",
        "quant_method": "gptq"
    }
 }
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
 {"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
 {
  "_from_model_config": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "temperature": 0.9,
  "top_p": 0.6,
  "transformers_version": "4.31.0"
 }
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:f58346ce9cc3f380f22eb685ee6cd0b2c399abe1d39e8731fc80cea7623a1743
 size 7259435192
--- a/quantize_config.json
+++ b/quantize_config.json
@@ -0,0 +1,10 @@
 {
  "bits": 4,
  "group_size": 128,
  "damp_percent": 0.1,
  "desc_act": true,
  "sym": true,
  "true_sequential": true,
  "model_name_or_path": null,
  "model_file_base_name": "model"
 }
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
 {
  "bos_token": {
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "pad_token": "<unk>",
  "unk_token": {
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
 }
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
 size 499723
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,34 @@
 {
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "legacy": false,
  "model_max_length": 8192,
  "pad_token": null,
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
 }
		`@@ -0,0 +1 @@`
							`Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.`
		`@@ -0,0 +1 @@`
							`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`