Update for Transformers AWQ support

2025-02-03 00:08:39 +08:00
parent ea6d26bf32
commit e2489ed4e3
15 changed files with 94055 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
 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 +1,374 @@
 ---
-license: Apache License 2.0
+base_model: Delcos/Mistral-Pygmalion-7b
 inference: false
 language:
 - en
 library_name: transformers
 license: cc-by-nc-nd-4.0
 model_creator: Devon M
 model_name: Mistral Pygmalion 7B
 model_type: llama
 pipeline_tag: text-generation
 prompt_template: '### Instruction:
-#model-type:
+  {prompt}
 ##如 gpt、phi、llama、chatglm、baichuan 等
 #- gpt
-#domain:
+  ### Assistant:
 ##如 nlp、cv、audio、multi-modal
 #- nlp
-#language:
+  '
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+quantized_by: TheBloke
-#- cn 
+tags:
-
+- Mistral
-#metrics:
+- Pygmalion
-##如 CIDEr、Blue、ROUGE 等
+- llama-2
-#- CIDEr
+- llama-2-7b
 #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。
+<!-- markdownlint-disable MD041 -->
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+
 <!-- header start -->
 <!-- 200823 -->
 <div style="width: auto; margin-left: auto; margin-right: auto">
 <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 -->
 # Mistral Pygmalion 7B - AWQ
 - Model creator: [Devon M](https://huggingface.co/Delcos)
 - Original model: [Mistral Pygmalion 7B](https://huggingface.co/Delcos/Mistral-Pygmalion-7b)
 <!-- description start -->
 ## Description
 This repo contains AWQ model files for [Devon M's Mistral Pygmalion 7B](https://huggingface.co/Delcos/Mistral-Pygmalion-7b).
 ### About AWQ
 AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
 It is supported by:
 - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
 - [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
 - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
 - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
 <!-- description end -->
 <!-- repositories-available start -->
 ## Repositories available
 * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Mistral-Pygmalion-7B-AWQ)
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mistral-Pygmalion-7B-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mistral-Pygmalion-7B-GGUF)
 * [Devon M's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Delcos/Mistral-Pygmalion-7b)
 <!-- repositories-available end -->
 <!-- prompt-template start -->
 ## Prompt template: Instruction-Assistant-Hashes
 SDK下载
 ```bash
 #安装ModelScope
 pip install modelscope
 ```
 ### Instruction:
 {prompt}
 ### Assistant:
 ```
 <!-- prompt-template end -->
 <!-- licensing start -->
 ## Licensing
 The creator of the source model has listed its license as `cc-by-nc-nd-4.0`, and this quantization has therefore used that same license.
 As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
 In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Devon M's Mistral Pygmalion 7B](https://huggingface.co/Delcos/Mistral-Pygmalion-7b).
 <!-- licensing end -->
 <!-- README_AWQ.md-provided-files start -->
 ## Provided files, and AWQ parameters
 For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
 Models are released as sharded safetensors files.
 | Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
 | ------ | ---- | -- | ----------- | ------- | ---- |
 | [main](https://huggingface.co/TheBloke/Mistral-Pygmalion-7B-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 3.89 GB
 <!-- README_AWQ.md-provided-files end -->
 <!-- README_AWQ.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/Mistral-Pygmalion-7B-AWQ`.
 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: `Mistral-Pygmalion-7B-AWQ`
 7. Select **Loader: AutoAWQ**.
 8. Click Load, and the model will load and is now ready for use.
 9. 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.
 10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
 <!-- README_AWQ.md-text-generation-webui end -->
 <!-- README_AWQ.md-use-from-vllm start -->
 ## Multi-user inference server: vLLM
 Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
 - Please ensure you are using vLLM version 0.2 or later.
 - When using vLLM as a server, pass the `--quantization awq` parameter.
 For example:
 ```shell
 python3 python -m vllm.entrypoints.api_server --model TheBloke/Mistral-Pygmalion-7B-AWQ --quantization awq
 ```
 - When using vLLM from Python code, again set `quantization=awq`.
 For example:
 ```python
-#SDK模型下载
+from vllm import LLM, SamplingParams
-from modelscope import snapshot_download
+
-model_dir = snapshot_download('TheBloke/Mistral-Pygmalion-7B-AWQ')
+prompts = [
    "Tell me about AI",
    "Write a story about llamas",
    "What is 291 - 150?",
    "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
 ]
 prompt_template=f'''### Instruction:
 {prompt}
 ### Assistant:
 '''
 prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
 sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
 llm = LLM(model="TheBloke/Mistral-Pygmalion-7B-AWQ", quantization="awq", dtype="auto")
 outputs = llm.generate(prompts, sampling_params)
 # Print the outputs.
 for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
 ```
-Git下载
+<!-- README_AWQ.md-use-from-vllm start -->
-```
+
-#Git模型下载
+<!-- README_AWQ.md-use-from-tgi start -->
-git clone https://www.modelscope.cn/TheBloke/Mistral-Pygmalion-7B-AWQ.git
+## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
 Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
 Example Docker parameters:
 ```shell
 --model-id TheBloke/Mistral-Pygmalion-7B-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
 ```
-<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>
+Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
 ```shell
 pip3 install huggingface-hub
 ```
 ```python
 from huggingface_hub import InferenceClient
 endpoint_url = "https://your-endpoint-url-here"
 prompt = "Tell me about AI"
 prompt_template=f'''### Instruction:
 {prompt}
 ### Assistant:
 '''
 client = InferenceClient(endpoint_url)
 response = client.text_generation(prompt,
                                  max_new_tokens=128,
                                  do_sample=True,
                                  temperature=0.7,
                                  top_p=0.95,
                                  top_k=40,
                                  repetition_penalty=1.1)
 print(f"Model output: ", response)
 ```
 <!-- README_AWQ.md-use-from-tgi end -->
 <!-- README_AWQ.md-use-from-python start -->
 ## Inference from Python code using AutoAWQ
 ### Install the AutoAWQ package
 Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later.
 ```shell
 pip3 install autoawq
 ```
 If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
 ```shell
 pip3 uninstall -y autoawq
 git clone https://github.com/casper-hansen/AutoAWQ
 cd AutoAWQ
 pip3 install .
 ```
 ### AutoAWQ example code
 ```python
 from awq import AutoAWQForCausalLM
 from transformers import AutoTokenizer
 model_name_or_path = "TheBloke/Mistral-Pygmalion-7B-AWQ"
 # Load tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
 # Load model
 model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
                                          trust_remote_code=False, safetensors=True)
 prompt = "Tell me about AI"
 prompt_template=f'''### Instruction:
 {prompt}
 ### Assistant:
 '''
 print("*** Running model.generate:")
 token_input = tokenizer(
    prompt_template,
    return_tensors='pt'
 ).input_ids.cuda()
 # Generate output
 generation_output = model.generate(
    token_input,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    max_new_tokens=512
 )
 # Get the tokens from the output, decode them, print them
 token_output = generation_output[0]
 text_output = tokenizer.decode(token_output)
 print("LLM output: ", text_output)
 """
 # Inference should be possible with transformers pipeline as well in future
 # But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
 from transformers import 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'])
 """
 ```
 <!-- README_AWQ.md-use-from-python end -->
 <!-- README_AWQ.md-compatibility start -->
 ## Compatibility
 The files provided are tested to work with:
 - [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
 - [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
 - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
 - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
 <!-- README_AWQ.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**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
 Thank you to all my generous patrons and donaters!
 And thank you again to a16z for their generous grant.
 <!-- footer end -->
 # Original model card: Devon M's Mistral Pygmalion 7B
 # MistralPy-7b
 This is a merger focusing on preserving the roleplay abilities of Pygmalion while gaining the improved results from Mistral. This model works best for roleplay but is still fairly capable assistant. The smaller (7b) size does mean it isn't perfect at more complex reasoning tasks, but this should be addressed in the larger version that I'll upload soon.
 ### Prompt Template
 ```
 ### Instruction:
 {Prompt & Backstory}
 ### Assistant:
 {Output}
 ```
 Example:
 ```
 ### Instruction:
 You are Sally, a fun 19 year old woman. Her favorite animal is "cat". Her favoritate color is "blue". She enjoys grape juice and cake.
 ### Assistant:
 Sally: Hi, how are you?
 User: Okay, you?
 ```
 # Send a message
 [Steam](https://steamcommunity.com/id/delcos/)
 #### Discord: delcos69
--- 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 +1,5 @@
 {
  "</s>": 2,
  "<s>": 1,
  "<unk>": 0
 }
--- a/config.json
+++ b/config.json
@@ -0,0 +1,35 @@
 {
  "_name_or_path": "/workspace/process/delcos_mistral-pygmalion-7b/source",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.34.0",
  "use_cache": true,
  "vocab_size": 32000,
  "quantization_config": {
    "quant_method": "awq",
    "zero_point": true,
    "group_size": 128,
    "bits": 4,
    "version": "gemm"
  }
 }
--- 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 +1,10 @@
 {
  "bos_token_id": 1,
  "do_sample": true,
  "eos_token_id": 2,
  "max_length": 4096,
  "pad_token_id": 0,
  "temperature": 0.6,
  "top_p": 0.9,
  "transformers_version": "4.34.0"
 }
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:36928328495298e5f01a8ab8d89a78a129c624052e015a4c7574a643bfe43ae0
 size 3889391512
--- a/quant_config.json
+++ b/quant_config.json
@@ -0,0 +1,6 @@
 {
    "zero_point": true,
    "q_group_size": 128,
    "w_bit": 4,
    "version": "GEMM"
 }
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,11 @@
 {
  "additional_special_tokens": [
    "<unk>",
    "<s>",
    "</s>"
  ],
  "bos_token": "<s>",
  "eos_token": "</s>",
  "pad_token": "<unk>",
  "unk_token": "<unk>"
 }
--- 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 +1,39 @@
 {
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "legacy": false,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<unk>",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": true
 }
		`@@ -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}`