Update for Transformers AWQ support

2025-01-26 19:00:16 +08:00
parent d03c2d995e
commit edfed77a30
15 changed files with 94148 additions and 60 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 +1,449 @@
 ---
-license: Apache License 2.0
+base_model: Xwin-LM/Xwin-LM-13B-V0.2
+inference: false
+license: llama2
+model_creator: Xwin-LM
+model_name: Xwin LM 13B v0.2
+model_type: llama
+prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
+  The assistant gives helpful, detailed, and polite answers to the user''s questions.
+  USER: {prompt} ASSISTANT:

-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##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
-#- 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
+  '
+quantized_by: TheBloke
 ---
-### 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
-```bash
-#安装ModelScope
-pip install modelscope
+<!-- 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 -->
+
+# Xwin LM 13B v0.2 - AWQ
+- Model creator: [Xwin-LM](https://huggingface.co/Xwin-LM)
+- Original model: [Xwin LM 13B v0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2)
+
+<!-- description start -->
+## Description
+
+This repo contains AWQ model files for [Xwin-LM's Xwin LM 13B v0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2).
+
+
+### 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.
+
+It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.
+
+As of September 25th 2023, preliminary Llama-only AWQ support has also been added to [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference).
+
+Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
+<!-- description end -->
+<!-- repositories-available start -->
+## Repositories available
+
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GGUF)
+* [Xwin-LM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2)
+<!-- repositories-available end -->
+
+<!-- prompt-template start -->
+## Prompt template: Vicuna
+
 ```
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+
+```
+
+<!-- prompt-template 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/Xwin-LM-13B-v0.2-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.25 GB
+
+<!-- README_AWQ.md-provided-files end -->
+
+<!-- README_AWQ.md-use-from-vllm start -->
+## Serving this model from vLLM
+
+Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
+
+Note: at the time of writing, vLLM has not yet done a new release with AWQ support.
+
+If you try the vLLM examples below and get an error about `quantization` being unrecognised, or other AWQ-related issues, please install vLLM from Github source.
+
+- When using vLLM as a server, pass the `--quantization awq` parameter, for example:
+
+```shell
+python3 python -m vllm.entrypoints.api_server --model TheBloke/Xwin-LM-13B-v0.2-AWQ --quantization awq --dtype half
+```
+
+When using vLLM from Python code, pass the `quantization=awq` parameter, for example:
+
 ```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('TheBloke/Xwin-LM-13B-v0.2-AWQ')
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+llm = LLM(model="TheBloke/Xwin-LM-13B-v0.2-AWQ", quantization="awq", dtype="half")
+
+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
-```
-#Git模型下载
-git clone https://www.modelscope.cn/TheBloke/Xwin-LM-13B-v0.2-AWQ.git
+<!-- README_AWQ.md-use-from-vllm start -->
+
+<!-- README_AWQ.md-use-from-tgi start -->
+## Serving this model from 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/Xwin-LM-13B-v0.2-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 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'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {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 -->
+## How to use this AWQ model from Python code
+
+### Install the necessary packages
+
+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 .
+```
+
+### You can then try the following example code
+
+```python
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer
+
+model_name_or_path = "TheBloke/Xwin-LM-13B-v0.2-AWQ"
+
+# Load model
+model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
+                                          trust_remote_code=False, safetensors=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
+
+prompt = "Tell me about AI"
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+
+'''
+
+print("\n\n*** Generate:")
+
+tokens = tokenizer(
+    prompt_template,
+    return_tensors='pt'
+).input_ids.cuda()
+
+# Generate output
+generation_output = model.generate(
+    tokens,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    max_new_tokens=512
+)
+
+print("Output: ", tokenizer.decode(generation_output[0]))
+
+"""
+# 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:
+
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
+- [vLLM](https://github.com/vllm-project/vllm)
+- [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
+
+TGI merged AWQ support on September 25th, 2023: [TGI PR #1054](https://github.com/huggingface/text-generation-inference/pull/1054).  Use the `:latest` Docker container until the next TGI release is made.
+
+<!-- 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: Xwin-LM's Xwin LM 13B v0.2
+
+
+<h3 align="center">
+Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
+</h3>
+
+<p align="center">
+  <a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
+</p>
+
+
+
+
+**Step up your LLM alignment with Xwin-LM!**
+
+Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
+
+## News
+
+- 💥 [Oct 12, 2023] [Xwin-LM-7B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2) and [Xwin-LM-13B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2) have been released, with improved comparison data and RL training (i.e., PPO). Their winrates v.s. GPT-4 have increased significantly, reaching **59.83%** (7B model) and **70.36%** (13B model) respectively. The 70B model will be released soon.
+- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
+- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
+- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
+- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
+
+
+## Model Card
+| Model        | Checkpoint | Report | License  |
+|------------|------------|-------------|------------------|
+|Xwin-LM-7B-V0.2| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-13B-V0.2| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2" target="_blank">HF Link</a> |  |  <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> |  | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> |  |  <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> |  |  <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+## Benchmarks
+
+### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
+
+The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
+
+| **Model**                         | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)**  |**AlpacaEval (winrate %)** |
+|----------------------------------|------------|----------|-------------|
+|    | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
+| **Xwin-LM-70B-V0.1**                   | **95.57**      | **87.50**          | **60.61**            |
+| GPT-4                          | 95.28  | 84.66     |  50.00      |
+| **Xwin-LM-13B-V0.2**          | **93.22**  | **87.14**  |  **70.36**    |
+| WizardLM-70B-V1.0           | 92.91  | 80.19     |  46.70      |
+| Llama-2-70B-Chat         | 92.66  | 81.97     |  51.19      |
+| **Xwin-LM-13B-V0.1**          | **91.76**  | **81.79**  |  **55.30**    |
+| ChatGPT                    | 89.37  | 50.00     |  16.60      |
+| **Xwin-LM-7B-V0.2**      | **89.31** | **79.60**    |  **59.83**     |
+| WizardLM-13B-V1.2         | 89.17  | 75.75     |  41.91      |
+| **Xwin-LM-7B-V0.1**      | **87.35** | **76.40**    |  **47.57**     |
+| Llama-2-13B-Chat     | 81.09  | 64.22     |  30.92      |
+
+
+### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
+
+|   Prompts  |  GPT4 response   |  Xwin-LM response |
+|----------------|------------|--------|
+|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
+| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
+
+
+### Xwin-LM performance on NLP foundation tasks.
+
+The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). 
+
+| Model            | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average    |
+|------------------|-------------|-------------|-------------------|-------------------|------------|
+| Text-davinci-003 | 56.9 | **85.2**    | 59.3         | 82.2       | 70.9  |
+|Vicuna-13b 1.1   | 51.3        | 53.0        | 51.8              | 80.1              | 59.1       |
+|Guanaco 30B   | 57.6        | 63.7        | 50.7              | 85.1              | 64.3       |   
+| WizardLM-7B 1.0      | 42.7        | 51.6        | 44.7              | 77.7              | 54.2       |
+| WizardLM-13B 1.0     | 52.3        | 57.2        | 50.5              | 81.0              | 60.2       |
+| WizardLM-30B 1.0    | 58.8    | 62.5 | 52.4       | 83.3          | 64.2|
+| Llama-2-7B-Chat      | 48.3        | 52.9        | 45.6     | 78.6    | 56.4       |
+| Llama-2-13B-Chat      | 54.6        | 59.0        | 44.1     | 81.9    | 59.9       |
+| Llama-2-70B-Chat      | 63.9        | 64.6        | 52.8       | 85.9   | 66.8       |
+| **Xwin-LM-7B-V0.1**      | 49.7        | 56.2        | 48.1     | 79.5    | 58.4       |
+| **Xwin-LM-13B-V0.1**      | 56.6        | 62.4        | 45.5     | 83.0    | 61.9       |
+| **Xwin-LM-70B-V0.1**      | **69.6**        | 70.5        | **60.1**       | **87.1**   | **71.8**       |
+| **Xwin-LM-7B-V0.2**      | 50.0  | 56.4    |  49.5   |  78.9   |     58.7       |
+| **Xwin-LM-13B-V0.2**      | 56.6 |    61.5   |  43.8   | 82.9  |         61.2      |
+
+
+## Inference
+
+### Conversation Template
+To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
+```
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
+```
+
+### HuggingFace Example
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
+tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
+(
+    prompt := "A chat between a curious user and an artificial intelligence assistant. "
+            "The assistant gives helpful, detailed, and polite answers to the user's questions. "
+            "USER: Hello, can you help me? "
+            "ASSISTANT:"
+)
+inputs = tokenizer(prompt, return_tensors="pt")
+samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
+output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+print(output) 
+# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
+```
+
+
+### vLLM Example
+Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vLLM](https://github.com/vllm-project/vllm). Please refer to [vLLM](https://github.com/vllm-project/vllm) for detailed installation instructions.
+```python
+from vllm import LLM, SamplingParams
+(
+    prompt := "A chat between a curious user and an artificial intelligence assistant. "
+            "The assistant gives helpful, detailed, and polite answers to the user's questions. "
+            "USER: Hello, can you help me? "
+            "ASSISTANT:"
+)
+sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
+llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
+outputs = llm.generate([prompt,], sampling_params)
+
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(generated_text)
+```
+
+## TODO
+
+- [ ] Release the source code
+- [ ] Release more capabilities, such as math, reasoning, and etc.
+
+## Citation
+Please consider citing our work if you use the data or code in this repo.
+```
+@software{xwin-lm,
+  title = {Xwin-LM},
+  author = {Xwin-LM Team},
+  url = {https://github.com/Xwin-LM/Xwin-LM},
+  version = {pre-release},
+  year = {2023},
+  month = {9},
+}
+```
+
+## Acknowledgements
+
+Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vLLM](https://github.com/vllm-project/vllm).
--- 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 +1,35 @@
+{
+  "_name_or_path": "/workspace/process/xwin-lm_xwin-lm-13b-v0.2/source",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "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": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32001,
+  "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": "4.28.1"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84253a39c4a7e2578ed825a5ea85f72bfc8f7cb59201dc6af9b06cad5bdaf27
+size 7248007792
--- 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 +1,24 @@
+{
+  "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": "[PAD]",
+  "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 +1,35 @@
+{
+  "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
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": 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}`