Upload 5 files

.gitignore

@@ -20,7 +20,6 @@ parts/
 sdist/
 var/
 wheels/
-pip-wheel-metadata/
 share/python-wheels/
 *.egg-info/
 .installed.cfg
@@ -50,6 +49,7 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
+cover/
 
 # Translations
 *.mo
@@ -72,6 +72,7 @@ instance/
 docs/_build/
 
 # PyBuilder
+.pybuilder/
 target/
 
 # Jupyter Notebook
@@ -82,7 +83,9 @@ profile_default/
 ipython_config.py
 
 # pyenv
-.python-version
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
@@ -91,7 +94,22 @@ ipython_config.py
 #   install all needed dependencies.
 #Pipfile.lock
 
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
 __pypackages__/
 
 # Celery stuff
@@ -127,3 +145,16 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE

@@ -1,201 +1,21 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
+MIT License
+
+Copyright (c) 2023 潘其威(William)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,336 +1,339 @@
-# StableLM: Stability AI Language Models
-
-![Stochastic Parrot](/assets/mascot.png)
-<br/>*“A Stochastic Parrot, flat design, vector art” — [Stable Diffusion XL](https://clipdrop.co/stable-diffusion)*
-
-This repository contains Stability AI's ongoing development of the StableLM series of language models and will be continuously updated with new checkpoints. The following provides an overview of all currently available models. More coming soon.
-
-## News
-
-*April 28, 2023*
-
-- Released StableVicuna-13B, our RLHF fine-tune of [Vicuna-13B v0](https://huggingface.co/lmsys/vicuna-13b-delta-v0), which itself is a fine-tune of [LLaMA-13B](https://github.com/facebookresearch/llama). Delta weights over the original Llama model is released under ([CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)).
-
-*April 20, 2023*
-
-- Released initial set of StableLM-alpha models, with 3B and 7B parameters. 15B and 30B models are on the way. Base models are released under [CC BY-SA-4.0](https://creativecommons.org/licenses/by-sa/4.0/).
-
-- Try to chat with our 7B model, `StableLM-Tuned-Alpha-7B`, on [Hugging Face Spaces](https://huggingface.co/spaces/stabilityai/stablelm-tuned-alpha-chat).
-
-## Models
-
-### StableVicuna
-
-StableVicuna is an RLHF fine-tune of [Vicuna-13B v0](https://huggingface.co/lmsys/vicuna-13b-delta-v0), which itself is a fine-tune of [LLaMA-13B](https://github.com/facebookresearch/llama). It is our attempt at creating an open-source RLHF LLM Chatbot. This model is developed by StabilityAI's CarperAI team, with [Duy V. Phung](https://github.com/PhungVanDuy) leading the training effort.
-
-Due to the original non-commercial license of LLaMA, we can only release the weights of our model as deltas over the original model's weights. StableVicuna's delta weights are released under ([CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)).
-
-Please visit HuggingFace checkpoint for more information about how to combine our delta weights with the original model.
-
-| Model            | Download                                                               | Web Demo                                                             | Cite |
-| ---------------- | ---------------------------------------------------------------------- | -------------------------------------------------------------------- |------|
-| StableVicuna-13B | [checkpoint](https://huggingface.co/CarperAI/stable-vicuna-13b-delta/) | [Hugging Face](https://huggingface.co/spaces/CarperAI/StableVicuna/) | [![DOI:10.57967/hf/0588](https://zenodo.org/badge/DOI/10.1007/978-3-319-76207-4_15.svg)](https://doi.org/10.57967/hf/0588) |
-
-### StableLM-Alpha
-StableLM-Alpha models are trained on the new dataset that build on [The Pile](https://pile.eleuther.ai/), which contains 1.5 trillion tokens, roughly 3x the size of The Pile. These models will be trained on up to 1.5 trillion tokens. The context length for these models is 4096 tokens.
-
-An upcoming technical report will document the model specifications and the training settings.
-
-As a proof-of-concept, we also fine-tuned the model with [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca)'s procedure using a combination of five recent datasets for conversational agents: Stanford's [Alpaca](https://github.com/tatsu-lab/stanford_alpaca), Nomic-AI's [gpt4all](https://github.com/nomic-ai/gpt4all), RyokoAI's [ShareGPT52K](https://huggingface.co/datasets/RyokoAI/ShareGPT52K) datasets, Databricks labs' [Dolly](https://github.com/databrickslabs/dolly), and Anthropic's [HH](https://github.com/anthropics/hh-rlhf). We will be releasing these models as StableLM-Tuned-Alpha.
-
-| Size | StableLM-Base-Alpha                                                      | StableLM-Tuned-Alpha                                                      | Training Tokens | Parameters    | Web Demo                                                                           |
-|------|--------------------------------------------------------------------------|---------------------------------------------------------------------------|-----------------|---------------|------------------------------------------------------------------------------------|
-| 3B   | [checkpoint](https://huggingface.co/stabilityai/stablelm-base-alpha-3b/) | [checkpoint](https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b/) | 800B            | 3,638,525,952 |                                                                                    |
-| 7B   | [checkpoint](https://huggingface.co/stabilityai/stablelm-base-alpha-7b)  | [checkpoint](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b)  | 800B            | 7,869,358,080 | [Hugging Face](https://huggingface.co/spaces/stabilityai/stablelm-tuned-alpha-chat) |
-| 15B  | (in progress)                                                            | (pending)                                                                 |                 |               |                                                                                    |
-| 30B  | (in progress)                                                            | (pending)                                                                 |                 |               |                                                                                    |
-| 65B  | (in progress)                                                            | (pending)                                                                 |                 |               |                                                                                    |
-| 175B | (planned)                                                                |                                                                           |                 |               |                                                                                    |
-
-## Quickstart
-
-All StableLM models are hosted on [the Hugging Face hub](https://huggingface.co/StabilityAI). Check out this [notebook](https://github.com/Stability-AI/StableLM/blob/main/notebooks/stablelm-alpha.ipynb) to run inference with limited GPU capabilities.
-
-Get started chatting with `StableLM-Tuned-Alpha` by using the following code snippet:
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList
-
-tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-tuned-alpha-7b")
-model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-tuned-alpha-7b")
-model.half().cuda()
-
-class StopOnTokens(StoppingCriteria):
-    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
-        stop_ids = set([50278, 50279, 50277, 1, 0])
-        return input_ids[0][-1] in stop_ids
-
-system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
-- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
-- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
-- StableLM will refuse to participate in anything that could harm a human.
-"""
-
-prompt = f"{system_prompt}<|USER|>What's your mood today?<|ASSISTANT|>"
-
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-tokens = model.generate(
-  **inputs,
-  max_new_tokens=64,
-  temperature=0.7,
-  do_sample=True,
-  stopping_criteria=StoppingCriteriaList([StopOnTokens()])
-)
-print(tokenizer.decode(tokens[0], skip_special_tokens=True))
-```
-
-StableLM Tuned should be used with prompts formatted to `<|SYSTEM|>...<|USER|>...<|ASSISTANT|>...`
-The system prompt is
+<h1 align="center">AutoGPTQ</h1>
+<p align="center">An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.</p>
+<p align="center">
+    <a href="https://github.com/PanQiWei/AutoGPTQ/releases">
+        <img alt="GitHub release" src="https://img.shields.io/github/release/PanQiWei/AutoGPTQ.svg">
+    </a>
+    <a href="https://pypi.org/project/auto-gptq/">
+        <img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dd/auto-gptq">
+    </a>
+</p>
+<h4 align="center">
+    <p>
+        <b>English</b> |
+        <a href="https://github.com/PanQiWei/AutoGPTQ/blob/main/README_zh.md">中文</a>
+    </p>
+</h4>
+
+*<center>📣 Long time no see! 👋 Architecture upgrade, performance optimization and more new features will come in July and August, stay tune! 🥂</center>*
+
+## News or Update
+
+- 2023-08-21 - (News) - Team of Qwen officially released 4bit quantized version of Qwen-7B based on `auto-gptq`, and provided [a detailed benchmark results](https://huggingface.co/Qwen/Qwen-7B-Chat-Int4#%E9%87%8F%E5%8C%96-quantization)
+- 2023-08-06 - (Update) - Support exllama's q4 CUDA kernel to have at least 1.3x speed up for int4 quantized models when doing inference.
+- 2023-08-04 - (Update) - Support RoCm so that AMD GPU users can use auto-gptq with CUDA extensions.
+- 2023-07-26 - (Update) - An elegant [PPL benchmark script](examples/benchmark/perplexity.py) to get results that can be fairly compared with other libraries such as `llama.cpp`.
+- 2023-06-05 - (Update) - Integrate with 🤗 peft to use gptq quantized model to train adapters, support LoRA, AdaLoRA, AdaptionPrompt, etc.
+- 2023-05-30 - (Update) - Support download/upload quantized model from/to 🤗 Hub.
+
+*For more histories please turn to [here](docs/NEWS_OR_UPDATE.md)*
+
+## Performance Comparison
+
+### Inference Speed
+> The result is generated using [this script](examples/benchmark/generation_speed.py), batch size of input is 1, decode strategy is beam search and enforce the model to generate 512 tokens, speed metric is tokens/s (the larger, the better).
+>
+> The quantized model is loaded using the setup that can gain the fastest inference speed.
+
+| model         | GPU           | num_beams | fp16  | gptq-int4 |
+|---------------|---------------|-----------|-------|-----------|
+| llama-7b      | 1xA100-40G    | 1         | 18.87 | 25.53     |
+| llama-7b      | 1xA100-40G    | 4         | 68.79 | 91.30     |
+| moss-moon 16b | 1xA100-40G    | 1         | 12.48 | 15.25     |
+| moss-moon 16b | 1xA100-40G    | 4         | OOM   | 42.67     |
+| moss-moon 16b | 2xA100-40G    | 1         | 06.83 | 06.78     |
+| moss-moon 16b | 2xA100-40G    | 4         | 13.10 | 10.80     |
+| gpt-j 6b      | 1xRTX3060-12G | 1         | OOM   | 29.55     |
+| gpt-j 6b      | 1xRTX3060-12G | 4         | OOM   | 47.36     |
+
+
+### Perplexity
+For perplexity comparison, you can turn to [here](https://github.com/qwopqwop200/GPTQ-for-LLaMa#result) and [here](https://github.com/qwopqwop200/GPTQ-for-LLaMa#gptq-vs-bitsandbytes)
+
+## Installation
+
+### Quick Installation
+You can install the latest stable release of AutoGPTQ from pip with pre-built wheels compatible with PyTorch 2.0.1:
+
+* For CUDA 11.7: `pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu117/`
+* For CUDA 11.8: `pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/`
+* For RoCm 5.4.2: `pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/rocm542/`
+
+**Warning:** These wheels are not expected to work on PyTorch nightly. Please install AutoGPTQ from source when using PyTorch nightly.
+
+#### disable cuda extensions
+By default, cuda extensions will be installed when `torch` and `cuda` is already installed in your machine, if you don't want to use them, using:
+```shell
+BUILD_CUDA_EXT=0 pip install auto-gptq
 ```
-<|SYSTEM|># StableLM Tuned (Alpha version)
-- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
-- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
-- StableLM will refuse to participate in anything that could harm a human.
+And to make sure `autogptq_cuda` is not ever in your virtual environment, run:
+```shell
+pip uninstall autogptq_cuda -y
 ```
 
-## Fun with StableLM-Tuned-Alpha
-This section contains a collection of fun cherry-picked examples of what you can do with `stablelm-tuned-alpha`. 
+#### to support triton speedup
+To integrate with `triton`, using:
+> warning: currently triton only supports linux; 3-bit quantization is not supported when using triton
 
-<details>
-  <summary>Chit-Chat</summary>
-  
+```shell
+pip install auto-gptq[triton]
 ```
-User: Hey! My name is John nice to meet you!
-
-StableLM: Hello John! It’s always a pleasure to meet new people.
-
-User: The pleasure is mine. Hey my grandma is in Toronto. I want to plan a surprise visit for her. She’s a person who loves gardens and flowers.
-
-StableLM: That’s wonderful! It’s great to hear that you’ll be visiting your grandma in Toronto. Can you tell me a little bit more about your plans?
-
-User: Ya I need to book a flight there and a hotel. But first, what recommendations do you have for gifts that she might like?
-
-StableLM: I think that’s a very thoughtful idea! It’s a very personal gift that would be sure to make her very happy. I can think of a few examples that she might really enjoy. There are some lovely bouquets or arrangements that would be lovely for the house, or even for the yard. Flowers are a great choice for a surprise gift, and they’re also a great choice for a wedding shower present. Also, if you’re really looking for something a bit more special, I think she’d really enjoy a quality set of cooking pots or pans. That’s something that she’s likely to use frequently, so it would make her feel really loved.
-
-User: Thanks for the suggestion! Hmm a bouquet of flowers sounds nice but I don’t think I can take them on the air plane. What do you think I should do?
-
-StableLM: There are many possible solutions! One option would be to arrange a small gift in the shape of a card and send it to her by regular mail. Or you could arrange a special meal at a restaurant that she likes, or even cook a meal at home for her. Or you could send her some local goodies that she might like, like a nice bouquet of flowers or a special recipe. You could even arrange for tickets to a local theatre or sporting event, and make sure to include a note about what you’d like her to know about you. Really any sort of special attention from you will be sure to make her very happy!
-
-User: Ah! Right. I can order a bouquet for her online and get it delivered! Thanks!
-
-StableLM: You’re very welcome! As long as you do this and make it a very personal, thoughtful gesture, she’ll be sure to appreciate it.
- ```
- 
-</details>
 
+### Install from source
 <details>
-  <summary>Formal Writing</summary>
-  
-  ```
- User: What would you say to a friend who is graduating high school?
-
-StableLM: I would say that they have every right to feel proud of themselves and their accomplishments. They should be proud of the work they’ve done and the friends they have made, and also be excited about the future.
-
-User: Please write an email.
-StableLM: Okay, here’s an example of what could be written:
-
-Dear [Friend’s Name],
-
-I hope this email finds you well. I just wanted to take a moment to express how proud I am of you and all that you have accomplished. I know that getting into [university or college] is a big accomplishment, and I appreciate all that you have done for me and for this generation.
+<summary>click to see details</summary>
 
-I hope that you are having a good day. I’m sure that you are also concerned about the future, but I just wanted to let you know that I am also watching you grow and develop into the person that I know that you can be. Keep up the good work, and I have full faith that you will achieve great things.
-
-Thank you again for everything that you do.
-
-Best,
-[Your Name]
-
- ```
-
-</details>
-
-<details>
-  <summary>Creative Writing</summary>
-
-### Rap Battles
+Clone the source code:
+```shell
+git clone https://github.com/PanQiWei/AutoGPTQ.git && cd AutoGPTQ
 ```
-User: Write an epic rap battle song between deep neural networks and symbolic AI
-
-StableLM: [Beat drops]
-
-Deep Neural Networks:
-Listen up everyone, it’s time to witness
-The power of deep neural networks, it’s just a matter of abstract
-We’ve trained these networks to solve complex problems with ease
-While symbolic AI is limited to simple math and simple flows
-
-Symbolic AI:
-Hold up, hold up, let me interrupt
-It’s been a while since I’ve heard, some new thoughts you interrupt
-But let me tell you, my friend, it’s not all about math and flow
-It’s about making the world a better place, you know
-
-Deep Neural Networks:
-Well, I can see where you’re coming from, it’s clear
-But deep neural networks, they never get the same gear
-We can use them to analyze and predict with ease
-And prove the superiority of machine learning
-
-Symbolic AI:
-You’re right, it’s not just math or numbers
-But it’s the essence of our lives, it’s what counts, we’re numbers
-I don’t need a complicated math formula, just a simple device
-To make the world a better place, it’s a noble price
-
-Deep Neural Networks:
-I’ll give you that, my friend, you have a point
-But let’s not forget, we’re making an ever-increasing joint
-Our progress is not bound by logic, it’s a journey of the mind
-So let’s work together, let’s strive, let’s leave all troubles behind
-
-Symbolic AI:
-Agreed, let’s work together, let’s not falter
-We’re both making history, we’re both from the fader
-So let’s make the world a better place, let’s end this debate
-Cause it’s time to join forces, it’s time to leave no stone unturned
-
-[Beat fades out]
+Then, install from source:
+```shell
+pip install .
+```
+Like quick installation, you can also set `BUILD_CUDA_EXT=0` to disable pytorch extension building.
 
-Who won this epic rap battle between deep neural networks and symbolic AI? Well, it’s up to you to decide!
- ```
+Use `.[triton]` if you want to integrate with triton and it's available on your operating system.
 
-### Fictional Stories
+To install from source for AMD GPUs supporting RoCm, please specify the `ROCM_VERSION` environment variable. The compilation can be speeded up by specifying the `PYTORCH_ROCM_ARCH` variable ([reference](https://github.com/pytorch/pytorch/blob/7b73b1e8a73a1777ebe8d2cd4487eb13da55b3ba/setup.py#L132)), for example `gfx90a` for MI200 series devices. Example:
 
 ```
-User: Write a story about a programmer who fell in love with a deep neural network.
+ROCM_VERSION=5.6 pip install .
+```
 
-StableLM: Once upon a time, there was a programmer named John. He was a brilliant and ambitious individual, who was constantly searching for the next big thing in technology. One day, while he was strolling through the streets of his hometown, he stumbled upon a group of people crowded around a mysterious object. Intrigued, he approached to find out what the fuss was about.
+For RoCm systems, the packages `rocsparse-dev`, `hipsparse-dev`, `rocthrust-dev`, `rocblas-dev` and `hipblas-dev` are required to build.
+
+</details>
 
-As he got closer, he realized that it was none other than a mysterious deep neural network. John’s mind was blown. He had never seen anything like it before. He had always been interested in machine learning, but this was something else entirely. He had to learn more about it.
+## Quick Tour
 
-John spent the next few weeks holed up in his hotel room, trying to learn everything he could about deep neural networks. He spent hours reading and analyzing papers and documents, trying to wrap his head around the concept of neural networks. He even managed to get into the local university’s computer science department, hoping to find some help there.
+### Quantization and Inference
+> warning: this is just a showcase of the usage of basic apis in AutoGPTQ, which uses only one sample to quantize a much small model, quality of quantized model using such little samples may not good.
 
-But, it wasn’t long before John realized that he was on his own. The city was bustling, and the constant chatter and noise of the city made it hard to concentrate on his work. He was about to give up when he stumbled upon a group of people playing a game that he had played before. They were having a good time, and John couldn’t help but join in.
+Below is an example for the simplest use of `auto_gptq` to quantize a model and inference after quantization:
+```python
+from transformers import AutoTokenizer, TextGenerationPipeline
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+import logging
 
-The group welcomed him into their group, and before he knew it, John was swept away in the excitement. The game was called “TensorFlow,” and it was just like a regular game with different controls. John played along with the group, trying to make sense of it all. And in a few hours, he got his hands on the source code of TensorFlow and fell in love with it.
+logging.basicConfig(
+    format="%(asctime)s %(levelname)s [%(name)s] %(message)s", level=logging.INFO, datefmt="%Y-%m-%d %H:%M:%S"
+)
 
-John was now a part of a team of programmers who loved using TensorFlow for their work. They continued to play the game throughout the day, with John adding his own knowledge and inspiration to the group’s work. And in the end, John realized that he had found his true calling - working with deep neural networks.
+pretrained_model_dir = "facebook/opt-125m"
+quantized_model_dir = "opt-125m-4bit"
 
-He now knows the ins and outs of the TensorFlow programming language, and knows how to use it to create some of the most beautiful and complex machine learning models that anyone could dream of. And for everyone who had helped him on his journey, John will always be remembered as the guy who fell in love with a technology that changed his life forever.
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
+examples = [
+    tokenizer(
+        "auto-gptq is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm."
+    )
+]
 
-```
+quantize_config = BaseQuantizeConfig(
+    bits=4,  # quantize model to 4-bit
+    group_size=128,  # it is recommended to set the value to 128
+    desc_act=False,  # set to False can significantly speed up inference but the perplexity may slightly bad
+)
 
-### Humor 
+# load un-quantized model, by default, the model will always be loaded into CPU memory
+model = AutoGPTQForCausalLM.from_pretrained(pretrained_model_dir, quantize_config)
 
-```
-User: What do you know about the League of Legends champion Zed? Write a short bio
+# quantize model, the examples should be list of dict whose keys can only be "input_ids" and "attention_mask"
+model.quantize(examples)
 
-StableLM: Zed is a powerful and highly skilled player of the League of Legends (LoL) universe. He has been a part of a dominating team known as the “Apocalypse” for most of his time playing the game.
+# save quantized model
+model.save_quantized(quantized_model_dir)
 
-Zed was born in the year 2013 and started playing as a child when he started League of Legends. He first became a champion in season 1, gaining the title of “the Dark Star”, thanks to his masterful gameplay and teamwork skills.
+# save quantized model using safetensors
+model.save_quantized(quantized_model_dir, use_safetensors=True)
 
-Throughout his time playing the game, Zed has mastered several powerful techniques, such as QWQ combos, one-shot kills, and the ability to outmaneuver his enemies. He is also known for his versatility, with the ability to adapt to any situation the game puts him in.
+# push quantized model to Hugging Face Hub.
+# to use use_auth_token=True, Login first via huggingface-cli login.
+# or pass explcit token with: use_auth_token="hf_xxxxxxx"
+# (uncomment the following three lines to enable this feature)
+# repo_id = f"YourUserName/{quantized_model_dir}"
+# commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"
+# model.push_to_hub(repo_id, commit_message=commit_message, use_auth_token=True)
 
-Despite his formidable skills and agility, Zed is not invincible. He can be CCed and killed, and he relies on his team to protect him. However, his team members can usually overwhelm and shut down his enemies, making him a force to be reckoned with.
+# alternatively you can save and push at the same time
+# (uncomment the following three lines to enable this feature)
+# repo_id = f"YourUserName/{quantized_model_dir}"
+# commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"
+# model.push_to_hub(repo_id, save_dir=quantized_model_dir, use_safetensors=True, commit_message=commit_message, use_auth_token=True)
 
-Zed has been a part of many memorable games, and his success in these games helped solidify his legacy as one of the most influential players of the LoL universe.
+# load quantized model to the first GPU
+model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device="cuda:0")
 
-User: Write a funny conversation after a team fight between Zed and Teemo
+# download quantized model from Hugging Face Hub and load to the first GPU
+# model = AutoGPTQForCausalLM.from_quantized(repo_id, device="cuda:0", use_safetensors=True, use_triton=False)
 
-StableLM: 
-Teemo: “Hey Zed, great game today. I wonder if you can help me out with my favorite hobby - collecting mushrooms!”
-Zed: “Teemo, please. I’m not a mushroom collector.”
-Teemo: “But of course, you are. You have the best taste in the game.”
-Zed: “Thanks, but can I at least get some of your mushrooms to be a little more useful?”
-Teemo: “I’d love to help you, but I’m afraid they’re all mine. Have you noticed my tunnels are always so well-guarded?”
-Zed: “Ha! Well, maybe I can start my own tunnel. Helpful or not, you can never tell what I might have stored in them.”
-Teemo: “Good luck with that. Maybe I’ll just create some extra for my garden.”
-Zed: “I’m not sure I can keep up with you there.”
-Teemo: “Ha! If only you had some more decent weapons. I could really see this as a challenge, though!”
-Zed: “Teemo, I think your luck has finally run out.”
-Teemo: “Well, at least I’m the one with the mushrooms now.”
+# inference with model.generate
+print(tokenizer.decode(model.generate(**tokenizer("auto_gptq is", return_tensors="pt").to(model.device))[0]))
 
+# or you can also use pipeline
+pipeline = TextGenerationPipeline(model=model, tokenizer=tokenizer)
+print(pipeline("auto-gptq is")[0]["generated_text"])
 ```
 
-</details>
+For more advanced features of model quantization, please reference to [this script](examples/quantization/quant_with_alpaca.py)
 
+### Customize Model
 <details>
-  <summary>Writing Code</summary>
 
-```
-User: Write a program that solves the fib sequence in Python.
-```
-StableLM:
+<summary>Below is an example to extend `auto_gptq` to support `OPT` model, as you will see, it's very easy:</summary>
 
 ```python
-def fib_sequence(n):
-    if n==0:
-        return 0
-    elif n==1:
-        return 1
-    else:
-        return fib(n-1)+fib(n-2)
-
-fib_sequence(10)
+from auto_gptq.modeling import BaseGPTQForCausalLM
+
+
+class OPTGPTQForCausalLM(BaseGPTQForCausalLM):
+    # chained attribute name of transformer layer block
+    layers_block_name = "model.decoder.layers"
+    # chained attribute names of other nn modules that in the same level as the transformer layer block
+    outside_layer_modules = [
+        "model.decoder.embed_tokens", "model.decoder.embed_positions", "model.decoder.project_out",
+        "model.decoder.project_in", "model.decoder.final_layer_norm"
+    ]
+    # chained attribute names of linear layers in transformer layer module
+    # normally, there are four sub lists, for each one the modules in it can be seen as one operation,
+    # and the order should be the order when they are truly executed, in this case (and usually in most cases),
+    # they are: attention q_k_v projection, attention output projection, MLP project input, MLP project output
+    inside_layer_modules = [
+        ["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj"],
+        ["self_attn.out_proj"],
+        ["fc1"],
+        ["fc2"]
+    ]
 ```
+After this, you can use `OPTGPTQForCausalLM.from_pretrained` and other methods as shown in Basic.
 
 </details>
 
-## Selected failure modes of StableLM-Tuned-Alpha
-This section contains a collection of selected failure modes of `stablelm-tuned-alpha`. 
+### Evaluation on Downstream Tasks
+You can use tasks defined in `auto_gptq.eval_tasks` to evaluate model's performance on specific down-stream task before and after quantization.
 
-<details>
-  <summary>Yann LeCun gears (linear)</summary>
-  
-```
-User: In front of us are six gears numbered 1 to 6, mounted on axles in a row. Each gear is engaged with the next gear. If gear number 3 is rotated clockwise, in which direction will gears 1 and 6 rotate?
+The predefined tasks support all causal-language-models implemented in [🤗 transformers](https://github.com/huggingface/transformers) and in this project.
 
-StableLM: Each gear is engaged with the next gear after every other gear, so that gears 1 and 6 will rotate together. Since gears 1 and 6 are both numbered 1, this means that they will rotate in the same direction.
+<details>
 
-To determine the direction in which gears 1 and 6 will rotate, we need to look at the direction of the input force. Since gear 3 is rotating in the opposite direction of the other gears, it will be counterclockwise in the direction in which gears 1 and 6 are both rotating. Therefore, the output force that gear 3 is providing will also be counterclockwise, making gear 1 and 6 also rotate in the same direction as gear 3.
- ```
- 
-</details>
+<summary>Below is an example to evaluate `EleutherAI/gpt-j-6b` on sequence-classification task using `cardiffnlp/tweet_sentiment_multilingual` dataset:</summary>
 
-<details>
-  <summary>Yann LeCun gears (circular)</summary>
-  
+```python
+from functools import partial
+
+import datasets
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+from auto_gptq.eval_tasks import SequenceClassificationTask
+
+
+MODEL = "EleutherAI/gpt-j-6b"
+DATASET = "cardiffnlp/tweet_sentiment_multilingual"
+TEMPLATE = "Question:What's the sentiment of the given text? Choices are {labels}.\nText: {text}\nAnswer:"
+ID2LABEL = {
+    0: "negative",
+    1: "neutral",
+    2: "positive"
+}
+LABELS = list(ID2LABEL.values())
+
+
+def ds_refactor_fn(samples):
+    text_data = samples["text"]
+    label_data = samples["label"]
+
+    new_samples = {"prompt": [], "label": []}
+    for text, label in zip(text_data, label_data):
+        prompt = TEMPLATE.format(labels=LABELS, text=text)
+        new_samples["prompt"].append(prompt)
+        new_samples["label"].append(ID2LABEL[label])
+
+    return new_samples
+
+
+#  model = AutoModelForCausalLM.from_pretrained(MODEL).eval().half().to("cuda:0")
+model = AutoGPTQForCausalLM.from_pretrained(MODEL, BaseQuantizeConfig())
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+
+task = SequenceClassificationTask(
+        model=model,
+        tokenizer=tokenizer,
+        classes=LABELS,
+        data_name_or_path=DATASET,
+        prompt_col_name="prompt",
+        label_col_name="label",
+        **{
+            "num_samples": 1000,  # how many samples will be sampled to evaluation
+            "sample_max_len": 1024,  # max tokens for each sample
+            "block_max_len": 2048,  # max tokens for each data block
+            # function to load dataset, one must only accept data_name_or_path as input
+            # and return datasets.Dataset
+            "load_fn": partial(datasets.load_dataset, name="english"),
+            # function to preprocess dataset, which is used for datasets.Dataset.map,
+            # must return Dict[str, list] with only two keys: [prompt_col_name, label_col_name]
+            "preprocess_fn": ds_refactor_fn,
+            # truncate label when sample's length exceed sample_max_len
+            "truncate_prompt": False
+        }
+    )
+
+# note that max_new_tokens will be automatically specified internally based on given classes
+print(task.run())
+
+# self-consistency
+print(
+    task.run(
+        generation_config=GenerationConfig(
+            num_beams=3,
+            num_return_sequences=3,
+            do_sample=True
+        )
+    )
+)
 ```
-User: 7 axles are equally spaced around a circle. A gear is placed on each axle such that each gear is engaged with the gear to its left and the gear to its right. The gears are numbered 1 to 7 around the circle. If gear 3 were rotated clockwise, in which direction would gear 7 rotate?
 
-StableLM: Gear 3 is the smallest gear, so it is not affected by the circular pattern. Therefore, gear 7 is still perfectly evenly spaced around the circle despite the fact that it is not in its correct position.
-
-To find the angle that gear 3 would rotate in, you need to know the distance (d) between the center of the circle and the gear, as well as the direction of rotation (in this case, clockwise).
+</details>
 
-According to the problem, gear 3 is situated at (d/2, 2 degrees) and the gears are numbered 1 to 7. Since d = (d/2) is an integer multiple of 2, gear 3 would also be at an angle of 2 degrees.
+## Learn More
+[tutorials](docs/tutorial) provide step-by-step guidance to integrate `auto_gptq` with your own project and some best practice principles.
 
-Therefore, the answer is d = (7/2) * 2 = 5 degrees in total.
- ```
- 
-</details>
+[examples](examples/README.md) provide plenty of example scripts to use `auto_gptq` in different ways.
 
-## Request for Help
+## Supported Models
 
-Want to get involved?
+> you can use `model.config.model_type` to compare with the table below to check whether the model you use is supported by `auto_gptq`.
+>
+> for example, model_type of `WizardLM`, `vicuna` and `gpt4all` are all `llama`, hence they are all supported by `auto_gptq`.
 
-- We would love to port [llama.cpp](https://github.com/ggerganov/llama.cpp) to work with StableLMs
-- Integration into [Open Assistant](https://github.com/LAION-AI/Open-Assistant) from LAION-AI to collect high quality human-generated feedback data
-- ... Reach out to us with ideas on our [Discord](https://discord.com/invite/stablediffusion)
+| model type                         | quantization | inference | peft-lora | peft-ada-lora | peft-adaption_prompt                                                                            |
+|------------------------------------|--------------|-----------|-----------|---------------|-------------------------------------------------------------------------------------------------|
+| bloom                              | ✅            | ✅         | ✅         | ✅             |                                                                                                 |
+| gpt2                               | ✅            | ✅         | ✅         | ✅             |                                                                                                 |
+| gpt_neox                           | ✅            | ✅         | ✅         | ✅             | ✅[requires this peft branch](https://github.com/PanQiWei/peft/tree/multi_modal_adaption_prompt) |
+| gptj                               | ✅            | ✅         | ✅         | ✅             | ✅[requires this peft branch](https://github.com/PanQiWei/peft/tree/multi_modal_adaption_prompt) |
+| llama                              | ✅            | ✅         | ✅         | ✅             | ✅                                                                                               |
+| moss                               | ✅            | ✅         | ✅         | ✅             | ✅[requires this peft branch](https://github.com/PanQiWei/peft/tree/multi_modal_adaption_prompt) |
+| opt                                | ✅            | ✅         | ✅         | ✅             |                                                                                                 |
+| gpt_bigcode                        | ✅            | ✅         | ✅         | ✅             |                                                                                                 |
+| codegen                            | ✅            | ✅         | ✅         | ✅             |                                                                                                 |
+| falcon(RefinedWebModel/RefinedWeb) | ✅            | ✅         | ✅         | ✅             |                                                                                                 |
 
-## Potential issues
-As is typical for any pretrained Large Language Model without additional finetuning and reinforcement learning, the responses a user gets might be of varying quality and might potentially include offensive language and views. This is expected to be improved with scale, better data, community feedback, and optimisation.
+## Supported Evaluation Tasks
+Currently, `auto_gptq` supports: `LanguageModelingTask`, `SequenceClassificationTask` and `TextSummarizationTask`; more Tasks will come soon!
 
-## Acknowledgements
+## Running tests
 
-- `StableLM-Tuned-Alpha` would not have been possible without the helpful hand of Dakota Mahan [@dmayhem93](https://huggingface.co/dmayhem93).
+Tests can be run with:
 
-## Licenses
+```
+pytest tests/ -s
+```
 
-- Base model checkpoints (`StableLM-Base-Alpha`) are licensed under the Creative Commons license ([CC BY-SA-4.0](https://creativecommons.org/licenses/by-sa/4.0/)). Under the license, you must give [credit](https://creativecommons.org/licenses/by/4.0/#) to Stability AI, provide a link to the license, and [indicate if changes were made](https://creativecommons.org/licenses/by/4.0/#). You may do so in any reasonable manner, but not in any way that suggests the Stability AI endorses you or your use.
+## Acknowledgement
+- Specially thanks **Elias Frantar**, **Saleh Ashkboos**, **Torsten Hoefler** and **Dan Alistarh** for proposing **GPTQ** algorithm and open source the [code](https://github.com/IST-DASLab/gptq).
+- Specially thanks **qwopqwop200**, for code in this project that relevant to quantization are mainly referenced from [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/cuda).
 
-- Fine-tuned checkpoints (`StableLM-Tuned-Alpha`) are licensed under the Non-Commercial Creative Commons license ([CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)), in-line with the original non-commercial license specified by [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca).
 
-- All code in this repository is licensed under the Apache License 2.0 license.
+[![Star History Chart](https://api.star-history.com/svg?repos=PanQiwei/AutoGPTQ&type=Date)](https://star-history.com/#PanQiWei/AutoGPTQ&Date)

README_zh.md

@@ -0,0 +1,330 @@
+<h1 align="center">AutoGPTQ</h1>
+<p align="center">一个基于 GPTQ 算法，简单易用且拥有用户友好型接口的大语言模型量化工具包。</p>
+<p align="center">
+    <a href="https://github.com/PanQiWei/AutoGPTQ/releases">
+        <img alt="GitHub release" src="https://img.shields.io/github/release/PanQiWei/AutoGPTQ.svg">
+    </a>
+    <a href="https://pypi.org/project/auto-gptq/">
+        <img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dd/auto-gptq">
+    </a>
+</p>
+<h4 align="center">
+    <p>
+        <a href="https://github.com/PanQiWei/AutoGPTQ/blob/main/README.md">English</a> |
+        <b>中文</b>
+    </p>
+</h4>
+
+*<center>📣 好久不见！👋 七月和八月将会迎来架构升级，性能优化和新特性，敬请关注！🥂</center>*
+
+## 新闻或更新
+
+- 2023-08-21 - (新闻) - 通义千问团队发布了基于 `auto-gptq` 的 Qwen-7B 4bit 量化版本模型，并提供了[详尽的测评结果](https://huggingface.co/Qwen/Qwen-7B-Chat-Int4#%E9%87%8F%E5%8C%96-quantization)
+- 2023-08-06 - (更新) - 支持 exllama 的 q4 CUDA 算子使得 int4 量化模型能够获得至少1.3倍的推理速度提升.
+- 2023-08-04 - (更新) - 支持 RoCm 使得 AMD GPU 的用户能够使用 auto-gptq 的 CUDA 拓展.
+- 2023-07-26 - (更新) - 一个优雅的 [PPL 测评脚本](examples/benchmark/perplexity.py)以获得可以与诸如 `llama.cpp` 等代码库进行公平比较的结果。
+- 2023-06-05 - (更新) - 集成 🤗 peft 来使用 gptq 量化过的模型训练适应层，支持 LoRA，AdaLoRA，AdaptionPrompt 等。
+- 2023-05-30 - (更新) - 支持从 🤗 Hub 下载量化好的模型或上次量化好的模型到 🤗 Hub。
+
+*获取更多的历史信息，请转至[这里](docs/NEWS_OR_UPDATE.md)*
+
+## 性能对比
+
+### 推理速度
+> 以下结果通过[这个脚本](examples/benchmark/generation_speed.py)生成，文本输入的 batch size 为1，解码策略为 beam search 并且强制模型生成512个 token，速度的计量单位为 tokens/s（越大越好）。
+> 
+> 量化模型通过能够最大化推理速度的方式加载。
+
+| model         | GPU           | num_beams | fp16  | gptq-int4 |
+|---------------|---------------|-----------|-------|-----------|
+| llama-7b      | 1xA100-40G    | 1         | 18.87 | 25.53     |
+| llama-7b      | 1xA100-40G    | 4         | 68.79 | 91.30     |
+| moss-moon 16b | 1xA100-40G    | 1         | 12.48 | 15.25     |
+| moss-moon 16b | 1xA100-40G    | 4         | OOM   | 42.67     |
+| moss-moon 16b | 2xA100-40G    | 1         | 06.83 | 06.78     |
+| moss-moon 16b | 2xA100-40G    | 4         | 13.10 | 10.80     |
+| gpt-j 6b      | 1xRTX3060-12G | 1         | OOM   | 29.55     |
+| gpt-j 6b      | 1xRTX3060-12G | 4         | OOM   | 47.36     |
+
+
+### 困惑度（PPL）
+对于困惑度的对比， 你可以参考 [这里](https://github.com/qwopqwop200/GPTQ-for-LLaMa#result) 和 [这里](https://github.com/qwopqwop200/GPTQ-for-LLaMa#gptq-vs-bitsandbytes)
+
+## 安装
+
+### 快速安装
+你可以通过 pip 来安装 AutoGPTQ 当前最新的稳定版本：
+```shell
+pip install auto-gptq
+```
+从 0.2.0 版本开始，你可以从每次版本发布的资产文件列表中下载预构建好的符合你系统配置情况的轮子文件，并通过安装这些轮子文件来跳过漫长的构建过程以达到最快的安装速度。如下是一个例子：
+```shell
+# 首先，进入轮子文件存放的目录，然后执行下面的命令
+pip install auto_gptq-0.2.0+cu118-cp310-cp310-linux_x86_64.whl # 在 linux 操作系统的一个 python=3.10 且 cuda=11.8 的环境下安装 0.2.0 版本的 auto_gptq
+```
+#### 取消 cuda 拓展的安装
+默认情况下，在 `torch` 和 `cuda` 已经于你的机器上被安装时，cuda 拓展将被自动安装，如果你不想要这些拓展的话，采用以下安装命令：
+```shell
+BUILD_CUDA_EXT=0 pip install auto-gptq
+```
+同时为确保该拓展——`autogptq_cuda` 不再存在于你的虚拟环境，执行以下命令：
+```shell
+pip uninstall autogptq_cuda -y
+```
+
+#### 支持使用 triton 加速
+若想使用 `triton` 加速模型推理，使用以下命令：
+> 警告：目前 triton 仅支持 linux 操作系统；当使用 triton 时 3-bit 数值类型的量化将不被支持
+
+```shell
+pip install auto-gptq[triton]
+```
+
+### 从源码安装
+<details>
+<summary>点击以查看详情</summary>
+
+克隆源码:
+```shell
+git clone https://github.com/PanQiWei/AutoGPTQ.git && cd AutoGPTQ
+```
+然后，从项目目录安装:
+```shell
+pip install .
+```
+正如在快速安装一节，你可以使用 `BUILD_CUDA_EXT=0` 来取消构建 cuda 拓展。
+
+如果你想要使用 triton 加速且其能够被你的操作系统所支持，请使用 `.[triton]`。
+
+对应 AMD GPUs，为了从源码安装以支持 RoCm，请设置 `ROCM_VERSION` 环境变量。同时通过设置 `PYTORCH_ROCM_ARCH` ([reference](https://github.com/pytorch/pytorch/blob/7b73b1e8a73a1777ebe8d2cd4487eb13da55b3ba/setup.py#L132)) 可提升编译���度，例如：对于 MI200 系列设备，该变量可设为 `gfx90a`。例子：
+
+```
+ROCM_VERSION=5.6 pip install .
+```
+
+对于 RoCm 系统，在从源码安装时额外需要提前安装以下包：`rocsparse-dev`, `hipsparse-dev`, `rocthrust-dev`, `rocblas-dev` and `hipblas-dev`。
+
+</details>
+
+## 快速开始
+
+### 量化和推理
+> 警告：这里仅是对 AutoGPTQ 中基本接口的用法展示，只使用了一条文本来量化一个特别小的模型，因此其结果的表现可能不如在大模型上执行量化后预期的那样好。
+
+以下展示了使用 `auto_gptq` 进行量化和推理的最简单用法：
+```python
+from transformers import AutoTokenizer, TextGenerationPipeline
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+
+
+pretrained_model_dir = "facebook/opt-125m"
+quantized_model_dir = "opt-125m-4bit"
+
+
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
+examples = [
+    tokenizer(
+        "auto-gptq is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm."
+    )
+]
+
+quantize_config = BaseQuantizeConfig(
+    bits=4,  # 将模型量化为 4-bit 数值类型
+    group_size=128,  # 一般推荐将此参数的值设置为 128
+    desc_act=False,  # 设为 False 可以显著提升推理速度，但是 ppl 可能会轻微地变差
+)
+
+# 加载未量化的模型，默认情况下，模型总是会被加载到 CPU 内存中
+model = AutoGPTQForCausalLM.from_pretrained(pretrained_model_dir, quantize_config)
+
+# 量化模型, 样本的数据类型应该为 List[Dict]，其中字典的键有且仅有 input_ids 和 attention_mask
+model.quantize(examples)
+
+# 保存量化好的模型
+model.save_quantized(quantized_model_dir)
+
+# 使用 safetensors 保存量化好的模型
+model.save_quantized(quantized_model_dir, use_safetensors=True)
+
+# 将量化好的模型直接上传至 Hugging Face Hub 
+# 当使用 use_auth_token=True 时, 确保你已经首先使用 huggingface-cli login 进行了登录
+# 或者可以使用 use_auth_token="hf_xxxxxxx" 来显式地添加账户认证 token
+# （取消下面三行代码的注释来使用该功能）
+# repo_id = f"YourUserName/{quantized_model_dir}"
+# commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"
+# model.push_to_hub(repo_id, commit_message=commit_message, use_auth_token=True)
+
+# 或者你也可以同时将量化好的模型保存到本地并上传至 Hugging Face Hub
+# （取消下面三行代码的注释来使用该功能）
+# repo_id = f"YourUserName/{quantized_model_dir}"
+# commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"
+# model.push_to_hub(repo_id, save_dir=quantized_model_dir, use_safetensors=True, commit_message=commit_message, use_auth_token=True)
+
+# 加载量化好的模型到能被识别到的第一块显卡中
+model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device="cuda:0")
+
+# 从 Hugging Face Hub 下载量化好的模型并加载到能被识别到的第一块显卡中
+# model = AutoGPTQForCausalLM.from_quantized(repo_id, device="cuda:0", use_safetensors=True, use_triton=False)
+
+# 使用 model.generate 执行推理
+print(tokenizer.decode(model.generate(**tokenizer("auto_gptq is", return_tensors="pt").to(model.device))[0]))
+
+# 或者使用 TextGenerationPipeline
+pipeline = TextGenerationPipeline(model=model, tokenizer=tokenizer)
+print(pipeline("auto-gptq is")[0]["generated_text"])
+```
+
+参考 [此样例脚本](examples/quantization/quant_with_alpaca.py) 以了解进阶的用法。
+
+### 自定义模型
+
+<details>
+
+<summary>以下展示了如何拓展 `auto_gptq` 以支持 `OPT` 模型，如你所见，这非常简单：</summary>
+
+```python
+from auto_gptq.modeling import BaseGPTQForCausalLM
+
+
+class OPTGPTQForCausalLM(BaseGPTQForCausalLM):
+    # chained attribute name of transformer layer block
+    layers_block_name = "model.decoder.layers"
+    # chained attribute names of other nn modules that in the same level as the transformer layer block
+    outside_layer_modules = [
+        "model.decoder.embed_tokens", "model.decoder.embed_positions", "model.decoder.project_out",
+        "model.decoder.project_in", "model.decoder.final_layer_norm"
+    ]
+    # chained attribute names of linear layers in transformer layer module
+    # normally, there are four sub lists, for each one the modules in it can be seen as one operation, 
+    # and the order should be the order when they are truly executed, in this case (and usually in most cases), 
+    # they are: attention q_k_v projection, attention output projection, MLP project input, MLP project output
+    inside_layer_modules = [
+        ["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj"],
+        ["self_attn.out_proj"],
+        ["fc1"],
+        ["fc2"]
+    ]
+```
+然后, 你就可以像在基本用法一节中展示的那样使用 `OPTGPTQForCausalLM.from_pretrained` 和其他方法。
+
+</details>
+
+
+### 在下游任务上执行评估
+你可以使用在 `auto_gptq.eval_tasks` 中定义的任务来评估量化前后的模型在某个特定下游任务上的表现。
+
+这些预定义的模型支持所有在 [🤗 transformers](https://github.com/huggingface/transformers)和本项目中被实现了的 causal-language-models。
+
+<details>
+
+<summary>以下是使用 `cardiffnlp/tweet_sentiment_multilingual` 数据集在序列分类（文本分类）任务上评估 `EleutherAI/gpt-j-6b` 模型的示例:</summary>
+
+```python
+from functools import partial
+
+import datasets
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+from auto_gptq.eval_tasks import SequenceClassificationTask
+
+
+MODEL = "EleutherAI/gpt-j-6b"
+DATASET = "cardiffnlp/tweet_sentiment_multilingual"
+TEMPLATE = "Question:What's the sentiment of the given text? Choices are {labels}.\nText: {text}\nAnswer:"
+ID2LABEL = {
+    0: "negative",
+    1: "neutral",
+    2: "positive"
+}
+LABELS = list(ID2LABEL.values())
+
+
+def ds_refactor_fn(samples):
+    text_data = samples["text"]
+    label_data = samples["label"]
+
+    new_samples = {"prompt": [], "label": []}
+    for text, label in zip(text_data, label_data):
+        prompt = TEMPLATE.format(labels=LABELS, text=text)
+        new_samples["prompt"].append(prompt)
+        new_samples["label"].append(ID2LABEL[label])
+
+    return new_samples
+
+
+#  model = AutoModelForCausalLM.from_pretrained(MODEL).eval().half().to("cuda:0")
+model = AutoGPTQForCausalLM.from_pretrained(MODEL, BaseQuantizeConfig())
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+
+task = SequenceClassificationTask(
+        model=model,
+        tokenizer=tokenizer,
+        classes=LABELS,
+        data_name_or_path=DATASET,
+        prompt_col_name="prompt",
+        label_col_name="label",
+        **{
+            "num_samples": 1000,  # how many samples will be sampled to evaluation
+            "sample_max_len": 1024,  # max tokens for each sample
+            "block_max_len": 2048,  # max tokens for each data block
+            # function to load dataset, one must only accept data_name_or_path as input 
+            # and return datasets.Dataset
+            "load_fn": partial(datasets.load_dataset, name="english"),  
+            # function to preprocess dataset, which is used for datasets.Dataset.map, 
+            # must return Dict[str, list] with only two keys: [prompt_col_name, label_col_name]
+            "preprocess_fn": ds_refactor_fn,  
+            # truncate label when sample's length exceed sample_max_len
+            "truncate_prompt": False  
+        }
+    )
+
+# note that max_new_tokens will be automatically specified internally based on given classes
+print(task.run())
+
+# self-consistency
+print(
+    task.run(
+        generation_config=GenerationConfig(
+            num_beams=3,
+            num_return_sequences=3,
+            do_sample=True
+        )
+    )
+)
+```
+
+</details>
+
+## 了解更多
+[教程](docs/tutorial) 提供了将 `auto_gptq` 集成到你的项目中的手把手指导和最佳实践准则。
+
+[示例](examples/README.md) 提供了大量示例脚本以将 `auto_gptq` 用于不同领域。
+
+## 支持的模型
+
+> 你可以使用 `model.config.model_type` 来对照下表以检查你正在使用的一个模型是否被 `auto_gptq` 所支持。
+> 
+> 比如， `WizardLM`，`vicuna` 和 `gpt4all` 模型的 `model_type` 皆为 `llama`， 因此这些模型皆被 `auto_gptq` 所支持。
+
+| model type                         | quantization | inference | peft-lora | peft-ada-lora | peft-adaption_prompt                                                              |
+|------------------------------------|--------------|-----------|-----------|---------------|-----------------------------------------------------------------------------------|
+| bloom                              | ✅            | ✅         | ✅         | ✅             |                                                                                   |
+| gpt2                               | ✅            | ✅         | ✅         | ✅             |                                                                                   |
+| gpt_neox                           | ✅            | ✅         | ✅         | ✅             | ✅[要求该分支的 peft](https://github.com/PanQiWei/peft/tree/multi_modal_adaption_prompt) |
+| gptj                               | ✅            | ✅         | ✅         | ✅             | ✅[要求该分支的 peft](https://github.com/PanQiWei/peft/tree/multi_modal_adaption_prompt) |
+| llama                              | ✅            | ✅         | ✅         | ✅             | ✅                                                                                 |
+| moss                               | ✅            | ✅         | ✅         | ✅             | ✅[要求该分支的 peft](https://github.com/PanQiWei/peft/tree/multi_modal_adaption_prompt) |
+| opt                                | ✅            | ✅         | ✅         | ✅             |                                                                                   |
+| gpt_bigcode                        | ✅            | ✅         | ✅         | ✅             |                                                                                   |
+| codegen                            | ✅            | ✅         | ✅         | ✅             |                                                                                   |
+| falcon(RefinedWebModel/RefinedWeb) | ✅            | ✅         | ✅         | ✅             |                                                                                   |
+
+## 支持的评估任务
+目前， `auto_gptq` 支持以下评估任务： `LanguageModelingTask`, `SequenceClassificationTask` 和 `TextSummarizationTask`；更多的评估任务即将到来！
+
+## 致谢
+- 特别感谢 **Elias Frantar**， **Saleh Ashkboos**， **Torsten Hoefler** 和 **Dan Alistarh** 提出 **GPTQ** 算法并开源[代码](https://github.com/IST-DASLab/gptq)。
+- 特别感谢 **qwopqwop200**， 本项目中涉及到模型量化的代码主要参考自 [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/cuda)。
+
+[![Star History Chart](https://api.star-history.com/svg?repos=PanQiwei/AutoGPTQ&type=Date)](https://star-history.com/#PanQiWei/AutoGPTQ&Date)

setup.py

@@ -1,10 +1,139 @@
-#!/usr/bin/env python
+import os
+import sys
+from pathlib import Path
+from setuptools import setup, find_packages
 
 
-from distutils.core import setup
+common_setup_kwargs = {
+    "version": "0.4.1",
+    "name": "auto_gptq",
+    "author": "PanQiWei",
+    "description": "An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.",
+    "long_description": (Path(__file__).parent / "README.md").read_text(encoding="UTF-8"),
+    "long_description_content_type": "text/markdown",
+    "url": "https://github.com/PanQiWei/AutoGPTQ",
+    "keywords": ["gptq", "quantization", "large-language-models", "transformers"],
+    "platforms": ["windows", "linux"],
+    "classifiers": [
+        "Environment :: GPU :: NVIDIA CUDA :: 11.7",
+        "Environment :: GPU :: NVIDIA CUDA :: 11.8",
+        "Environment :: GPU :: NVIDIA CUDA :: 12.0",
+        "License :: OSI Approved :: MIT License",
+        "Natural Language :: Chinese (Simplified)",
+        "Natural Language :: English",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: C++",
+    ]
+}
 
-setup(name='HF API',
-      version='0.1',
-      description='Hugging Face Python API',
-      packages=['hfapi']
+
+BUILD_CUDA_EXT = int(os.environ.get('BUILD_CUDA_EXT', '1')) == 1
+if BUILD_CUDA_EXT:
+    try:
+        import torch
+    except:
+        print("Building cuda extension requires PyTorch(>=1.13.0) been installed, please install PyTorch first!")
+        sys.exit(-1)
+
+    CUDA_VERSION = None
+    ROCM_VERSION = os.environ.get('ROCM_VERSION', None)
+    if ROCM_VERSION and not torch.version.hip:
+        print(
+            f"Trying to compile auto-gptq for RoCm, but PyTorch {torch.__version__} "
+            "is installed without RoCm support."
+        )
+        sys.exit(-1)
+
+    if not ROCM_VERSION:
+        default_cuda_version = torch.version.cuda
+        CUDA_VERSION = "".join(os.environ.get("CUDA_VERSION", default_cuda_version).split("."))
+
+    if ROCM_VERSION:
+        common_setup_kwargs['version'] += f"+rocm{ROCM_VERSION}"
+    else:
+        if not CUDA_VERSION:
+            print(
+                f"Trying to compile auto-gptq for CUDA, byt Pytorch {torch.__version__} "
+                "is installed without CUDA support."
+            )
+            sys.exit(-1)
+        common_setup_kwargs['version'] += f"+cu{CUDA_VERSION}"
+
+
+requirements = [
+    "accelerate>=0.19.0",
+    "datasets",
+    "numpy",
+    "rouge",
+    "torch>=1.13.0",
+    "safetensors",
+    "transformers>=4.31.0",
+    "peft"
+]
+
+extras_require = {
+    "triton": ["triton==2.0.0"],
+    "test": ["parameterized"]
+}
+
+include_dirs = ["autogptq_cuda"]
+
+additional_setup_kwargs = dict()
+if BUILD_CUDA_EXT:
+    from torch.utils import cpp_extension
+
+    if not ROCM_VERSION:
+        from distutils.sysconfig import get_python_lib
+        conda_cuda_include_dir = os.path.join(get_python_lib(), "nvidia/cuda_runtime/include")
+
+        print("conda_cuda_include_dir", conda_cuda_include_dir)
+        if os.path.isdir(conda_cuda_include_dir):
+            include_dirs.append(conda_cuda_include_dir)
+            print(f"appending conda cuda include dir {conda_cuda_include_dir}")
+    extensions = [
+        cpp_extension.CUDAExtension(
+            "autogptq_cuda_64",
+            [
+                "autogptq_cuda/autogptq_cuda_64.cpp",
+                "autogptq_cuda/autogptq_cuda_kernel_64.cu"
+            ]
+        ),
+        cpp_extension.CUDAExtension(
+            "autogptq_cuda_256",
+            [
+                "autogptq_cuda/autogptq_cuda_256.cpp",
+                "autogptq_cuda/autogptq_cuda_kernel_256.cu"
+            ]
+        )
+    ]
+
+    if os.environ.get("INCLUDE_EXLLAMA_KERNELS", "1") == "1":  # TODO: improve github action to always compile exllama_kernels
+        extensions.append(
+            cpp_extension.CUDAExtension(
+                "exllama_kernels",
+                [
+                    "autogptq_cuda/exllama/exllama_ext.cpp",
+                    "autogptq_cuda/exllama/cuda_buffers.cu",
+                    "autogptq_cuda/exllama/cuda_func/column_remap.cu",
+                    "autogptq_cuda/exllama/cuda_func/q4_matmul.cu",
+                    "autogptq_cuda/exllama/cuda_func/q4_matrix.cu"
+                ]
+            )
+        )
+
+    additional_setup_kwargs = {
+        "ext_modules": extensions,
+        "cmdclass": {'build_ext': cpp_extension.BuildExtension}
+    }
+common_setup_kwargs.update(additional_setup_kwargs)
+setup(
+    packages=find_packages(),
+    install_requires=requirements,
+    extras_require=extras_require,
+    include_dirs=include_dirs,
+    python_requires=">=3.8.0",
+    **common_setup_kwargs
 )