Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow 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
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,324 @@
+                 Yi Series Models Community License Agreement
+                                 Version: 2.1
+                       Date of Release: November 23, 2023
+ 
+1. Definition
+
+“Agreement” refers to the terms and conditions defined in this Yi Series Models 
+Community License Agreement for the use, reproduction and distribution of Yi 
+Series Models.
+ 
+“Model” refers to associated components (including checkpoints) developed based
+on machine learning, including learned weights and parameters (including the
+status of optimizer).
+ 
+“Yi Series Models” refers to opensource models with different specifications and
+capabilities named “Yi” provided by the Licensor, including Yi-6B, Yi-34B etc.
+ 
+“Derivatives” refers to all modifications to Yi Series Models, work based on Yi
+Series Models, or any other models created or initialized by transferring the
+weights, parameters, activations, or output patterns of Yi Series Models to
+other models to achieve similar performance, including but not limited to
+methods that require using intermediate data representations or generating
+synthetic data based on Yi Series Models to train other models.
+ 
+“Licensor” refers to Beijing Lingyiwanwu Information Technology Co., Ltd.
+ 
+“you” refers to an individual or legal entity that exercises the license granted
+by this Agreement and/or uses the Yi Series Models for any purpose and in any
+field of use.
+ 
+“Third Party” refers to any individuals, legal entities or non-legal 
+organizations other than you.
+ 
+“Distribute” refers to transmitting, copying, publishing, or otherwise sharing 
+the Yi Series Models with third parties, including providing the Yi Series
+Models through electronic or other remote means (such as any SaaS software or
+PaaS software accessed via API or web access).
+ 
+“Commercial Purposes” refers to the use of the Yi Series Models, directly or
+indirectly, for the operation, promotion, revenue generation, or any other
+profit-making purposes for entities or individuals.
+ 
+“Laws and Regulations” refers to the laws and administrative regulations of the
+mainland of the People's Republic of China (for the purposes of this Agreement
+only, excluding Hong Kong, Macau, and Taiwan).
+ 
+“Personal Information” refers to various information related to identified or
+identifiable natural persons recorded electronically or by other means,
+excluding information that has been anonymized.
+ 
+“Logo” refers to any trademark, service mark, trade name, domain name, website
+name, or other distinctive branding marks.
+ 
+2. License and License Restrictions
+The Licensor hereby grants you a non-exclusive, global, non-transferable,
+non-sub-licensable, revocable, and royalty-free copyright license. You must
+adhere to the following license restrictions:
+ 
+1) Your use of the Yi Series Models must comply with the Laws and Regulations as
+well as applicable legal requirements of other countries/regions, and respect
+social ethics and moral standards, including but not limited to, not using the
+Yi Series Models for purposes prohibited by Laws and Regulations as well as
+applicable legal requirements of other countries/regions, such as harming
+national security, promoting terrorism, extremism, inciting ethnic or racial
+hatred, discrimination, violence, or pornography, and spreading false harmful
+information.
+ 
+2) You shall not, for military or unlawful purposes or in ways not allowed by
+Laws and Regulations as well as applicable legal requirements of other
+countries/regions, a) use, copy or Distribute the Yi Series Models, or b) create
+complete or partial Derivatives of the Yi Series Models.
+ 
+3) Your use of the Yi Series Models (including using the output of the Yi Series
+Models) and the creation of Derivatives must not infringe upon the legitimate
+rights of any Third Party, including but not limited to the rights of personal
+rights such as the right to likeness, reputation, and privacy, as well as
+intellectual property rights such as copyrights, patents, trade secrets, and
+other property rights.
+ 
+4) You must clearly attribute the source of the Yi Series Models to the Licensor
+and provide a copy of this Agreement to any Third-Party users of the Yi Series
+Models and Derivatives.
+ 
+5) If you modify the Yi Series Models to create Derivatives, you must clearly
+indicate the substantial modifications made, and these modifications shall not
+violate the license restrictions of this Agreement. You shall not enable,
+assist, or in any way facilitate Third Parties to violate the license
+restrictions of this Agreement.
+ 
+If you plan to use the Yi Series Models and Derivatives for Commercial Purposes, 
+please refer to the Registration Form of Yi Series Models for Commercial Purposes 
+(“Registration Form”), as provided in Attachment 1 of the Yi Series Models 
+Commercial License Agreement (available at https://www.lingyiwanwu.com/yi-license) 
+and send completed Registration Form to the email: yi@01.ai to complete the 
+registration and obtain the license for Commercial Purposes. If you obtained the 
+license for Commercial Purposes and use the Yi Series Models and Derivatives for 
+Commercial Purposes, you must comply with the afore-mentioned license restrictions 
+and restrictions specified under the Yi Series Models Commercial License Agreement.
+ 
+ 
+3. Intellectual Property
+The ownership of the Yi Series Models and their related intellectual property
+rights is solely held by the Licensor.
+ 
+In any circumstance, without the prior written consent of the Licensor, you are
+not allowed to use any Logo associated with the Licensor. If your use of
+Licensor's Logo in violation of this Agreement causes any losses to the Licensor
+or others, you will bear full legal responsibility.
+ 
+ 
+4. Disclaimer and Limitation of Liability
+
+The Yi Series Models are provided "AS IS." The Licensor does not provide any
+express or implied warranties for the Yi Series Models, including but not
+limited to stability, ownership, merchantability, non-infringement, or fitness
+for a specific purpose of the Yi Series Models and their output results. You
+assume all responsibilities for the risks and consequences arising from the use,
+reproduction, distribution of the Yi Series Models, and the creation of
+Derivatives.
+ 
+The Licensor complies with Laws and Regulations at all stages of model training,
+maintaining the legality, authenticity, accuracy, objectivity, and diversity of
+data and algorithms. The Licensor is not liable for any direct, indirect,
+incidental consequences, and other losses or damages related to your use,
+reproduction, and distribution of the Yi Series Models, and the creation of
+Derivatives under this Agreement. This includes but is not limited to:
+ 
+1) The Licensor is not responsible for data security risks resulting from your
+use of the Yi Series Models.
+ 
+2) The Yi Series Models may contain Personal Information. When you use Yi Series
+Models, you acknowledge that you are the data processing entity as defined under
+the Laws and Regulations responsible for determining the processing methods and
+purposes of Personal Information. You must comply with legal requirements for
+processing any Personal Information that may be contained in the Yi Series
+Models and assume the associated legal responsibilities, as well as the risks
+and consequences of processing Personal Information.
+ 
+3) The Licensor is not liable for reputation risks arising from your use of the
+Yi Series Models or the output results of the Yi Series Models.
+ 
+4) The Licensor is not liable for intellectual property risks associated with
+your use of the Yi Series Models’ output results.
+ 
+If your use, reproduction, distribution of the Yi Series Models, or the creation
+of Derivatives result in losses to the Licensor, the Licensor has the right to
+seek compensation from you. For any claims made by Third Parties against the
+Licensor related to your use, reproduction, and distribution of the Yi Series
+Models, or the creation of Derivatives, the Licensor has the right to demand
+that you defend, compensate, and indemnify the Licensor and protect the Licensor
+from harm.
+ 
+ 
+5. Dispute Resolution
+
+The stipulation, effectiveness, interpretation, performance, modification, and
+termination of the Agreement, the use, copy and Distribute of the Yi Series
+Models, and dispute resolution associated with your use, copy and distribution
+shall be governed by the laws of the mainland of the People's Republic of China
+(for the purposes of this agreement only, excluding Hong Kong, Macau, and
+Taiwan), and the application of conflict of laws is excluded.
+ 
+Any disputes arising from the use, copy or distribution of the Yi Series Models
+should first be resolved through amicable negotiations. If negotiations fail,
+legal proceedings should be initiated in the People's Court at the location of
+the Licensor.
+ 
+ 
+6. Effectiveness and Termination of the Agreement
+
+Your use of the Yi Series Models signifies that you have read and agreed to be
+bound by the terms of the Agreement. The Agreement becomes effective from the
+date of your use of the Yi Series Models and will terminate from the date you
+cease using the Yi Series Models. If you violate any terms or restrictions in
+the Agreement, the Licensor reserves the right to terminate the Agreement.
+ 
+Upon termination of the Agreement, you must immediately cease using the Yi
+Series Models. Section 4, "Disclaimer and Limitation of Liability," and Section
+5, "Dispute Resolution," of this Agreement remain in effect after the
+termination of this Agreement.
+ 
+ 
+7. Updates to the Agreement and Contact Information
+
+The Licensor reserves the right to update the Agreement from time to time. The
+latest version of the Agreement will be posted by the Licensor through
+https://01.ai.
+ 
+For any questions related to licensing and copyright, please contact the
+Licensor at yi@01.ai.
+
+
+
+                     Yi系列模型社区许可协议
+                          版本: 2.1
+                    发布日期: 2023年11月23日
+ 
+1. 定义
+
+“协议”是指本协议中定义Yi系列模型使用、复制和分发的条款和条件。
+
+“模型”是指任何附带的基于机器学习的组件(包括检查点)，包括学习的权重、参数（包括优
+化器状态）。
+
+“Yi系列模型”是指许可方开源的以Yi命名的不同规格、不同能力的模型，包括
+Yi-6B、Yi-34B等。
+
+“模型衍生品”是指对Yi系列模型的所有修改、基于Yi系列模型的工作，或通过将Yi系列模型
+的权重、参数、激活或输出模式转移到其他模型而创建或初始化的任何其他模型，以使其他
+模型的性能与Yi系列模型类似，包括但不限于需要使用中间数据表示的提取方法或基于Yi系
+列模型生成合成数据来训练其他模型的方法。
+
+“许可方”是指北京零一万物信息技术有限公司。
+
+“您”是指行使本协议授予的权限和/或出于任何目的和在任何使用领域使用Yi系列模型的个
+人或法人实体。
+ 
+“第三方”是指您之外的任何个人、法人实体或非法人组织。
+ 
+“分发”是指向第三方传输、复制、发布或以其他方式共享Yi系列模型，包括将Yi系列模型作
+为通过电子或其他远程方式（例如基于 API 或 Web 访问的任何 SaaS 软件或 PaaS 软
+件）提供。
+ 
+“商业用途”是指使用Yi系列模型，直接或间接为实体或个人进行运营、推广或产生收入，或
+用于任何其他盈利目的。
+ 
+“法律法规”是指中华人民共和国大陆地区（仅为本协议之目的，不包括香港、澳门和台湾）
+的法律及行政法规。
+ 
+“个人信息”是指以电子或者其他方式记录的与已识别或者可识别的自然人有关的各种信息，
+不包括匿名化处理后的信息。
+ 
+“标识” 是指任何商标、服务标记、商号、域名、网站名称或其他带有显著品牌特征的标记。
+ 
+ 
+2. 许可及许可限制
+
+许可方特此授予您非排他性、全球性、不可转让、不可再许可、可撤销、免版税的版权许可。
+您必须满足如下许可限制条件：
+ 
+1) 您对Yi系列模型的使用应遵守法律法规以及其他国家/地区适用的法律要求、尊重社会公
+德和伦理道德。包括但不限于您不得将Yi系列模型用作危害国家安全、宣扬恐怖主义、极端
+主义，宣扬民族及种族仇恨、歧视，暴力、色情，以及虚假有害信息等法律法规以及其他国
+家/地区适用的法律要求禁止的目的。
+ 
+2) 您不得出于军事或非法目的，或以法律法规以及其他国家/地区适用的法律要求所不允许
+的方式 a) 使用、复制、或分发Yi系列模型; 或 b) 创建Yi系列模型的全部或部分衍生品。
+ 
+3) 您对Yi系列模型的使用（包括使用Yi系列模型的输出）以及模型衍生品的创建不得侵犯
+任何第三方的合法权益，包括但不限于他人肖像权、名誉权、隐私权等人格权，著作权、专
+利权、商业秘密等知识产权，或其他财产权益。
+ 
+4) 您必须向Yi系列模型及Yi系列模型衍生品的任何第三方使用者明确Yi系列模型的来源为
+许可方并向其提供本协议的副本。
+ 
+5) 若您修改Yi系列模型得到模型衍生品，您必须以显著的方式说明修改的内容，且上述修
+改不得违反本协议的许可限制条件，也不能允许、协助或以其他方式使得第三方违反本协议
+中的许可限制条件。
+ 
+如果您计划将Yi系列模型及模型衍生品用作商业用途，请参见《Yi系列模型商用许可协议》
+（参见：https://www.lingyiwanwu.com/yi-license）附件一《Yi系列模型商用登
+记表》（“登记表”）并将填写完毕的登记表发送至 yi@01.ai 邮箱完成登记即可获得商用
+许可。若您获得商用许可并将Yi系列模型及模型衍生品用作商业用途，您应满足许可方上述
+许可限制条件及《Yi系列模型商用许可协议》中的商业许可限制。
+ 
+3. 知识产权
+
+Yi系列模型的所有权及其相关知识产权，由许可方单独所有。
+ 
+在任何情况下，未经许可方事先书面同意，您不得以任何方式使用许可方的任何标识。由于
+您违反本协议使用许可方的标识给许可方或他人造成损失的，由您承担全部法律责任。
+ 
+ 
+4. 免责声明及责任限制
+
+Yi系列模型按“原样”提供。许可方不对Yi系列模型提供任何明示或暗示的保证，包括但不限
+于：模型及输出结果的稳定性、所有权、适销性、非侵权性、或特定用途适用性。您将对适
+用、复制及分发Yi系列模型以及创建模型衍生品所产生的风险与后果承担所有责任。
+ 
+许可方在模型训练的所有阶段都遵守法律法规，坚持维护数据和算法的合法、真实、准确、
+客观和多样性。许可方不对您根据本协议使用、复制及分发Yi系列模型，以及创建模��衍生
+品而产生或与之相关的任何直接、间接、附带的后果、以及其他损失或损害承担责任。包括
+但不限于：
+ 
+1) 许可方不承担您因使用Yi系列模型而导致的数据安全风险。
+ 
+2) Yi系列模型中可能包含个人信息。在您使用Yi系列模型的过程中，您承认您为法律法规
+定义下决定个人信息处理方式和目的的个人信息处理者。您应遵守法律法规要求处理Yi系列
+模型中可能包含的个人信息，并承担相应的法律责任，以及处理个人信息的风险和后果。
+ 
+3) 许可方不承担您使用Yi系列模型或模型输出结果而产生的声誉风险。
+ 
+4) 许可方不承担您使用Yi系列模型的输出结果涉及的知识产权风险。
+ 
+若由于您对Yi系列模型的使用、复制或分发，或者创建模型衍生品而导致许可方遭受损失，
+许可方有权要求您对许可方的损失进行赔偿。对于任何第三方向许可方提出的因您使用、复
+制或分发Yi系列模型或创建模型衍生品行为的相关索赔，许可方有权要求您为许可方进行辩
+护、赔偿并使许可方免受损害。
+ 
+ 
+5. 争议解决
+
+协议的订立、效力、解释、履行、修改和终止，使用、复制和分发Yi系列模型以及争议解决
+均适用中华人民共和国大陆地区（仅为本协议之目的，不包括香港、澳门和台湾）法律，并
+排除冲突法的适用。
+ 
+因使用、复制和分发Yi系列模型而发生的任何争议，各方应首先通过友好协商的方式加以解
+决。协商不成时，应向许可方所在地人民法院提起诉讼。
+ 
+ 
+6. 协议的生效及终止
+
+您使用Yi系列模型即表示您已阅读并同意接受协议的约束。协议自您使用Yi系列模型之日起
+生效并将在您停止使用Yi系列模型之日起终止。若您违反协议中的任何条款或限制，许可方
+有权终止协议。
+ 
+若协议终止，您需立即停止使用Yi系列模型。本协议第4条“免责声明及责任限制”及第5条
+“争议解决”在协议终止后仍有效。
+ 
+ 
+7. 协议更新及联系方式
+
+许可方有权对协议进行不时更新。许可方将通过 https://01.ai 公布协议最新版本。有关
+许可和版权的任何问题，请通过 yi@01.ai 与许可方联系。

README.md

@@ -0,0 +1,239 @@
+---
+license: other
+license_name: yi-license
+license_link: LICENSE
+library_name: pytorch
+---
+
+<div align="center">
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_dark.svg" width="200px">
+  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="200px"> 
+  <img alt="specify theme context for images" src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="200px">
+</picture>
+
+</div>
+
+<div align="center">
+  <h1 align="center">Yi Vision Language Model</h1>
+</div>
+
+
+<div align="center">
+  <h3 align="center">Better Bilingual Multimodal Model</h3>
+</div>
+
+<p align="center">
+🤗 <a href="https://huggingface.co/01-ai" target="_blank">Hugging Face</a> • 🤖 <a href="https://www.modelscope.cn/organization/01ai/" target="_blank">ModelScope</a> • ✡️ <a href="https://wisemodel.cn/organization/01.AI" target="_blank">WiseModel</a>
+</p> 
+
+<p align="center">
+    👩‍🚀 Ask questions or discuss ideas on <a href="https://github.com/01-ai/Yi/discussions" target="_blank"> GitHub </a>!
+</p> 
+
+<p align="center">
+    👋 Join us 💬 <a href="https://github.com/01-ai/Yi/issues/43#issuecomment-1827285245" target="_blank"> WeChat (Chinese) </a>!
+</p> 
+
+<p align="center">
+    📚 Grow at <a href="https://github.com/01-ai/Yi/blob/main/docs/learning_hub.md"> Yi Learning Hub </a>!
+</p> 
+
+<hr>
+
+<!-- DO NOT REMOVE ME -->
+
+<details open>
+<summary></b>📕 Table of Contents</b></summary>
+
+- [What is Yi-VL?](#what-is-yi-vl)
+  - [Overview](#overview)
+  - [Models](#models)
+  - [Features](#features)
+  - [Architecture](#architecture)
+  - [Training](#training)
+  - [Limitations](#limitations)
+- [Why Yi-VL?](#why-yi-vl)
+  - [Benchmarks](#benchmarks)
+  - [Showcases](#showcases)
+- [How to use Yi-VL?](#how-to-use-yi-vl)
+  - [Quick start](#quick-start)
+  - [Hardware requirements](#hardware-requirements)
+- [Misc.](#misc)
+  - [Acknowledgements and attributions](#acknowledgements-and-attributions)
+    - [List of used open-source projects](#list-of-used-open-source-projects)
+  - [License](#license)
+
+</details>
+
+<hr>
+
+# What is Yi-VL?
+
+## Overview
+
+- **Yi Vision Language (Yi-VL)** model is the open-source, multimodal version of the Yi **Large Language Model (LLM)** series, enabling content comprehension, recognition, and multi-round conversations about images.
+  
+- Yi-VL demonstrates exceptional performance, **ranking first** among all existing open-source models in the latest benchmarks including [MMMU](https://mmmu-benchmark.github.io/#leaderboard) in English and [CMMMU](https://mmmu-benchmark.github.io/#leaderboard) in Chinese (based on data available up to January 2024).
+  
+- Yi-VL-34B is the **first** open-source 34B vision language model worldwide.
+
+## Models
+
+Yi-VL has released the following versions.
+
+Model |       Download
+|---|---
+Yi-VL-34B |• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-VL-34B)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-VL-34B/summary)
+Yi-VL-6B | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-VL-6B)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-VL-6B/summary)
+
+## Features
+
+Yi-VL offers the following features:
+
+- Multi-round text-image conversations: Yi-VL can take both text and images as inputs and produce text outputs. Currently, it supports multi-round visual question answering with one image.
+  
+- Bilingual text support: Yi-VL supports conversations in both English and Chinese, including text recognition in images.  
+  
+- Strong image comprehension: Yi-VL is adept at analyzing visuals, making it an efficient tool for tasks like extracting, organizing, and summarizing information from images.
+  
+- Fine-grained image resolution: Yi-VL supports image understanding at a higher resolution of 448&times;448.
+
+## Architecture
+
+Yi-VL adopts the [LLaVA](https://github.com/haotian-liu/LLaVA) architecture, which is composed of three primary components:
+
+- Vision Transformer (ViT): it's initialized with [CLIP ViT-H/14 model](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) and used for image encoding.
+
+- Projection Module: it's designed to align image features with text feature space, consisting of a two-layer Multilayer Perceptron (MLP) with layer normalizations.
+  
+- Large Language Model (LLM): it's initialized with [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat) or [Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat), demonstrating exceptional proficiency in understanding and generating both English and Chinese. 
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/EGVHSWG4kAcX01xDaoeXS.png)
+
+## Training 
+
+### Training process
+
+Yi-VL is trained to align visual information well to the semantic space of Yi LLM, which undergoes a comprehensive three-stage training process:
+
+- Stage 1: The parameters of ViT and the projection module are trained using an image resolution of 224&times;224. The LLM weights are frozen. The training leverages an image caption dataset comprising 100 million image-text pairs from [LAION-400M](https://laion.ai/blog/laion-400-open-dataset/). The primary objective is to enhance the ViT's knowledge acquisition within our specified architecture and to achieve better alignment between the ViT and the LLM. 
+     
+- Stage 2: The image resolution of ViT is scaled up to 448&times;448, and the parameters of ViT and the projection module are trained. It aims to further boost the model's capability for discerning intricate visual details. The dataset used in this stage includes about 25 million image-text pairs, such as [LAION-400M](https://laion.ai/blog/laion-400-open-dataset/), [CLLaVA](https://huggingface.co/datasets/LinkSoul/Chinese-LLaVA-Vision-Instructions), [LLaVAR](https://llavar.github.io/), [Flickr](https://www.kaggle.com/datasets/hsankesara/flickr-image-dataset), [VQAv2](https://paperswithcode.com/dataset/visual-question-answering-v2-0), [RefCOCO](https://github.com/lichengunc/refer/tree/master), [Visual7w](http://ai.stanford.edu/~yukez/visual7w/) and so on.
+     
+- Stage 3: The parameters of the entire model (that is, ViT, projection module, and LLM) are trained. The primary goal is to enhance the model's proficiency in multimodal chat interactions, thereby endowing it with the ability to seamlessly integrate and interpret visual and linguistic inputs. To this end, the training dataset encompasses a diverse range of sources, totalling approximately 1 million image-text pairs, including [GQA](https://cs.stanford.edu/people/dorarad/gqa/download.html), [VizWiz VQA](https://vizwiz.org/tasks-and-datasets/vqa/), [TextCaps](https://opendatalab.com/OpenDataLab/TextCaps), [OCR-VQA](https://ocr-vqa.github.io/), [Visual Genome](https://homes.cs.washington.edu/~ranjay/visualgenome/api.html), [LAION GPT4V](https://huggingface.co/datasets/laion/gpt4v-dataset) and so on. To ensure data balancing, we impose a cap on the maximum data contribution from any single source, restricting it to no more than 50,000 pairs. 
+
+Below are the parameters configured for each stage.
+
+Stage | Global batch size | Learning rate | Gradient clip | Epochs
+|---|---|---|---|---
+Stage 1, 2 |4096|1e-4|0.5|1
+Stage 3|256|2e-5|1.0|2
+
+### Training resource consumption
+
+- The training consumes 128 NVIDIA A800 (80G) GPUs. 
+
+- The total training time amounted to approximately 10 days for Yi-VL-34B and 3 days for Yi-VL-6B. 
+
+## Limitations
+
+This is the initial release of the Yi-VL, which comes with some known limitations. It is recommended to carefully evaluate potential risks before adopting any models. 
+
+- Feature limitation
+  
+    - Visual question answering is supported. Other features like text-to-3D and image-to-video are not yet supported.
+    
+    - A single image rather than several images can be accepted as an input. 
+ 
+- Hallucination problem
+  
+    - There is a certain possibility of generating content that does not exist in the image.
+    
+    - In scenes containing multiple objects, some objects might be incorrectly identified or described with insufficient detail.
+  
+- Resolution issue
+  
+    - Yi-VL is trained on images with a resolution of 448&times;448. During inference, inputs of any resolution are resized to 448&times;448. Low-resolution images may result in information loss, and more fine-grained images (above 448) do not bring in extra knowledge.
+    
+- Other limitations of the Yi LLM.
+
+# Why Yi-VL?
+  
+## Benchmarks
+
+Yi-VL outperforms all existing open-source models in [MMMU](https://mmmu-benchmark.github.io) and [CMMMU](https://cmmmu-benchmark.github.io), two advanced benchmarks that include massive multi-discipline multimodal questions (based on data available up to January 2024).
+
+- MMMU
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/kCmXuwLbLvequ93kjh3mg.png)
+
+- CMMMU
+  
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/6YuSakMCg3D2AozixdoZ0.png)
+
+## Showcases
+
+Below are some representative examples of detailed description and visual question answering, showcasing the capabilities of Yi-VL.
+
+- English
+  
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64cc65d786d8dc0caa6ab3cd/F_2bIVwMtVamygbVqtb8E.png)
+
+- Chinese
+  
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/l_tLzugFtHk1dkVsFJE7B.png)
+
+# How to use Yi-VL?
+
+## Quick start
+
+Please refer to [Yi GitHub Repo](https://github.com/01-ai/Yi/tree/main/VL) for details.
+
+## Hardware requirements
+
+For model inference, the recommended GPU examples are:
+
+- Yi-VL-6B: RTX 3090, RTX 4090, A10, A30
+
+- Yi-VL-34B: 4 &times; RTX 4090, A800 (80 GB)
+
+# Misc.
+
+## Acknowledgements and attributions
+
+This project makes use of open-source software/components. We acknowledge and are grateful to these developers for their contributions to the open-source community.
+
+### List of used open-source projects
+
+1. LLaVA
+  - Authors: Haotian Liu, Chunyuan Li, Qingyang Wu, Yuheng Li, and Yong Jae Lee
+  - Source: https://github.com/haotian-liu/LLaVA
+  - License: Apache-2.0 license
+  - Description: The codebase is based on LLaVA code.
+
+2. OpenClip
+  - Authors: Gabriel Ilharco, Mitchell Wortsman, Ross Wightman, Cade Gordon, Nicholas Carlini, Rohan Taori, Achal Dave, Vaishaal Shankar, Hongseok Namkoong, John Miller, Hannaneh Hajishirzi, Ali Farhadi, and Ludwig Schmidt
+  - Source: https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K
+  - License: MIT
+  - Description: The ViT is initialized using the weights of OpenClip.
+
+**Notes**
+
+- This attribution does not claim to cover all open-source components used. Please check individual components and their respective licenses for full details.
+  
+- The use of the open-source components is subject to the terms and conditions of the respective licenses.
+
+We appreciate the open-source community for their invaluable contributions to the technology world.
+
+## License
+
+Please refer to the [acknowledgments and attributions](#acknowledgments_and_attributions) as well as individual components, for the license of source code. 
+
+The Yi series models are fully open for academic research and free for commercial use, permissions of which are automatically granted upon application. 
+
+All usage must adhere to the [Yi Series Models Community License Agreement 2.1](https://huggingface.co/01-ai/Yi-VL-34B/blob/main/LICENSE). 
+
+For free commercial use, you only need to send an email to get official commercial permission.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<image_placeholder>": 64002,
+  "<|endoftext|>": 64001,
+  "<|startoftext|>": 64000
+}

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "/home/ec2-user/model_weights/Yi-VL-34B",
+  "architectures": [
+    "YiVLForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "ignore_index": -100,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "image_token_index": 64002,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1280,
+  "mm_projector_type": "mlp2x_gelu_Norm",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "./vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448",
+  "model_type": "llava",
+  "moe_layer": null,
+  "moe_mode": "easy",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "projector_hidden_act": "gelu",
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "text_config": {
+    "model_type": "llama"
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.1",
+  "tune_mm_mlp_adapter": false,
+  "tune_vision_tower": true,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 64000
+}

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": 0.8,
+  "transformers_version": "4.34.0"
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 448,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 448
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ecbabcc9a0cae173a99b6fd776e020c1b8e55a5cfc52633c760ae840c3780e
+size 9975358895

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ed55b7a8bcff41fd65a21c447c5458fc87a9e8278a7f782e6090d22e917a1d
+size 9909328019

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8d0b644b5ba6e2b95069a0a562a07184c08c0cb29653196523002d57c69ffb
+size 9747818583

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7fad804afb6c70473c4a513f6af83d23cc1a1efa4cbb8b8c82601567b274ca
+size 9747847907

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138249bb4af01081f07cbabed88fd1008d774580cd97b283983e92500b4bc484
+size 9747847967

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d8e611083ae49e13a93b49cf6c61bd37cb6af60a99a1224129b3619716b110
+size 9938688835

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa77e118e13cee579708af229fd970964e52e47f12aa6e7984cf1e40fc2aaa60
+size 9991723306

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71dae5d9dc918516037467510c6591881953dc26c5d584de8bd92c01f2940a8b
+size 1104304609

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<|startoftext|>",
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|im_sep|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,99 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|im_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64002": {
+      "content": "<image_placeholder>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<|startoftext|>",
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|im_sep|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/.gitattributes

@@ -0,0 +1,32 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+saved_model/**/* 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/README.md

@@ -0,0 +1,165 @@
+---
+license: mit
+widget:
+- src: >-
+    https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
+  candidate_labels: playing music, playing sports
+  example_title: Cat & Dog
+library_name: open_clip
+pipeline_tag: zero-shot-image-classification
+---
+# Model Card for CLIP ViT-H/14 - LAION-2B
+
+#  Table of Contents
+
+1. [Model Details](#model-details)
+2. [Uses](#uses)
+3. [Training Details](#training-details)
+4. [Evaluation](#evaluation)
+5. [Acknowledgements](#acknowledgements)
+6. [Citation](#citation)
+7. [How To Get Started With the Model](#how-to-get-started-with-the-model)
+
+
+# Model Details
+
+## Model Description
+
+A CLIP ViT-H/14 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip).
+
+Model training done by Romain Beaumont on the [stability.ai](https://stability.ai/) cluster. 
+
+# Uses
+
+As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model. 
+
+The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the LAION-5B blog (https://laion.ai/blog/laion-5b/) and upcoming paper include additional discussion as it relates specifically to the training dataset. 
+
+## Direct Use
+
+Zero-shot image classification, image and text retrieval, among others.
+
+## Downstream Use
+
+Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others.
+
+## Out-of-Scope Use
+
+As per the OpenAI models,
+
+**Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful. 
+
+Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use.
+
+Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases.
+
+Further the above notice, the LAION-5B dataset used in training of these models has additional considerations, see below.
+
+# Training Details
+
+## Training Data
+
+This model was trained with the 2 Billion sample English subset of LAION-5B (https://laion.ai/blog/laion-5b/).
+
+**IMPORTANT NOTE:** The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the demo links with caution and at your own risk. It is possible to extract a “safe” subset by filtering out samples based on the safety tags (using a customized trained NSFW classifier that we built). While this strongly reduces the chance for encountering potentially harmful content when viewing, we cannot entirely exclude the possibility for harmful content being still present in safe mode, so that the warning holds also there. We think that providing the dataset openly to broad research and other interested communities will allow for transparent investigation of benefits that come along with training large-scale models as well as pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. Providing our dataset openly, we however do not recommend using it for creating ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress.
+
+## Training Procedure
+
+Please see [training notes](https://docs.google.com/document/d/1EFbMLRWSSV0LUf9Du1pWzWqgeiIRPwEWX2s1C6mAk5c) and [wandb logs](https://wandb.ai/rom1504/eval_openclip/reports/H-14--VmlldzoyNDAxODQ3).
+
+# Evaluation
+
+Evaluation done with code in the [LAION CLIP Benchmark suite](https://github.com/LAION-AI/CLIP_benchmark).
+
+## Testing Data, Factors & Metrics
+
+### Testing Data
+
+The testing is performed with VTAB+ (A combination of VTAB (https://arxiv.org/abs/1910.04867) w/ additional robustness datasets) for classification and COCO and Flickr for retrieval.
+
+**TODO** - more detail
+
+## Results
+
+The model achieves a 78.0 zero-shot top-1 accuracy on ImageNet-1k.
+
+An initial round of benchmarks have been performed on a wider range of datasets, currently viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
+
+**TODO** - create table for just this model's metrics.
+
+# Acknowledgements
+
+Acknowledging [stability.ai](https://stability.ai/) for the compute used to train this model.
+
+# Citation
+
+**BibTeX:**
+
+LAION-5B
+```bibtex
+@inproceedings{schuhmann2022laionb,
+  title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
+  author={Christoph Schuhmann and
+          Romain Beaumont and
+          Richard Vencu and
+          Cade W Gordon and
+          Ross Wightman and
+          Mehdi Cherti and
+          Theo Coombes and
+          Aarush Katta and
+          Clayton Mullis and
+          Mitchell Wortsman and
+          Patrick Schramowski and
+          Srivatsa R Kundurthy and
+          Katherine Crowson and
+          Ludwig Schmidt and
+          Robert Kaczmarczyk and
+          Jenia Jitsev},
+  booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
+  year={2022},
+  url={https://openreview.net/forum?id=M3Y74vmsMcY}
+}
+```
+
+OpenAI CLIP paper
+```
+@inproceedings{Radford2021LearningTV,
+  title={Learning Transferable Visual Models From Natural Language Supervision},
+  author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
+  booktitle={ICML},
+  year={2021}
+}
+```
+
+OpenCLIP software
+```
+@software{ilharco_gabriel_2021_5143773,
+  author       = {Ilharco, Gabriel and
+                  Wortsman, Mitchell and
+                  Wightman, Ross and
+                  Gordon, Cade and
+                  Carlini, Nicholas and
+                  Taori, Rohan and
+                  Dave, Achal and
+                  Shankar, Vaishaal and
+                  Namkoong, Hongseok and
+                  Miller, John and
+                  Hajishirzi, Hannaneh and
+                  Farhadi, Ali and
+                  Schmidt, Ludwig},
+  title        = {OpenCLIP},
+  month        = jul,
+  year         = 2021,
+  note         = {If you use this software, please cite it as below.},
+  publisher    = {Zenodo},
+  version      = {0.1},
+  doi          = {10.5281/zenodo.5143773},
+  url          = {https://doi.org/10.5281/zenodo.5143773}
+}
+```
+
+# How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+** TODO ** - Hugging Face transformers, OpenCLIP, and timm getting started snippets

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448",
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 448,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0"
+}

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/open_clip_config.json

@@ -0,0 +1,31 @@
+{
+    "model_cfg": {
+        "embed_dim": 1024,
+        "vision_cfg": {
+            "image_size": 224,
+            "layers": 32,
+            "width": 1280,
+            "head_width": 80,
+            "patch_size": 14
+        },
+        "text_cfg": {
+            "context_length": 77,
+            "vocab_size": 49408,
+            "width": 1024,
+            "heads": 16,
+            "layers": 24
+        }
+    },
+    "preprocess_cfg": {
+        "mean": [
+            0.48145466,
+            0.4578275,
+            0.40821073
+        ],
+        "std": [
+            0.26862954,
+            0.26130258,
+            0.27577711
+        ]
+    }
+}

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a78ef8e8c73fd0df621682e7a8e8eb36c6916cb3c16b291a082ecd52ab79cc4
+size 3944692325

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 448,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 448
+}

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0c1b4a16fa93bd8bb53e5190e8624dc6f5de5175b9c6ebf02cc5c545247e6a
+size 2527168934

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+    "unk_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "bos_token": {
+        "content": "<|startoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "eos_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "pad_token": "<|endoftext|>",
+    "add_prefix_space": false,
+    "errors": "replace",
+    "do_lower_case": true,
+    "name_or_path": "openai/clip-vit-base-patch32",
+    "model_max_length": 77,
+    "special_tokens_map_file": "./special_tokens_map.json",
+    "tokenizer_class": "CLIPTokenizer"
+}