初始化项目，由ModelHub XC社区提供模型
Model: Hcompany/Holo1.5-3B Source: Original Platform
This commit is contained in:
ModelHub XC
242
.eval_results/screenspot_pro.yaml
Normal file
242
.eval_results/screenspot_pro.yaml
Normal file
@@ -0,0 +1,242 @@
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: overall
|
||||
value: 51.5
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: android_studio_macos
|
||||
value: 50.0
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: autocad_windows
|
||||
value: 14.7
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: blender_windows
|
||||
value: 47.9
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: davinci_macos
|
||||
value: 54.5
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: eviews_windows
|
||||
value: 94.0
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: excel_macos
|
||||
value: 40.6
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: fruitloops_windows
|
||||
value: 42.1
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: illustrator_windows
|
||||
value: 19.4
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: inventor_windows
|
||||
value: 48.6
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: linux_common_linux
|
||||
value: 48.0
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: macos_common_macos
|
||||
value: 41.5
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: matlab_macos
|
||||
value: 66.7
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: origin_windows
|
||||
value: 27.4
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: photoshop_windows
|
||||
value: 51.0
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: powerpoint_windows
|
||||
value: 70.7
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: premiere_windows
|
||||
value: 42.3
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: pycharm_macos
|
||||
value: 55.1
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: quartus_windows
|
||||
value: 35.6
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: solidworks_windows
|
||||
value: 32.5
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: stata_windows
|
||||
value: 46.9
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: unreal_engine_windows
|
||||
value: 60.0
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: vivado_windows
|
||||
value: 71.2
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: vmware_macos
|
||||
value: 58.5
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: vscode_macos
|
||||
value: 56.4
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: windows_common_windows
|
||||
value: 32.1
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
|
||||
- dataset:
|
||||
id: likaixin/ScreenSpot-Pro
|
||||
task_id: word_macos
|
||||
value: 85.7
|
||||
source:
|
||||
url: https://gui-agent.github.io/grounding-leaderboard/
|
||||
name: ScreenSpot-Pro Leaderboard
|
||||
user: merve
|
||||
53
.gitattributes
vendored
Normal file
53
.gitattributes
vendored
Normal file
@@ -0,0 +1,53 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
129
LICENSE
Normal file
129
LICENSE
Normal file
@@ -0,0 +1,129 @@
|
||||
H Product RESEARCH LICENSE AGREEMENT Release Date: [June 3rd, 2025]
|
||||
|
||||
By clicking to agree or by using or distributing any portion or element of the H Product Materials and/or Alibaba Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
|
||||
|
||||
The H Product was “Built with Qwen”. Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved. The Qwen Research License Agreement is available here: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE (the “Qwen Research License Agreement”).
|
||||
|
||||
Your use, reproduction, distribution, copy and/or modification of Alibaba Cloud Materials is subject to the Qwen Research License Agreement. In case of contradiction between the Qwen Research License Agreement and this Agreement, the Qwen Research License Agreement shall prevail with respect to Alibaba Cloud Materials.
|
||||
|
||||
|
||||
1. Definitions
|
||||
|
||||
|
||||
a. This H Product RESEARCH LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
|
||||
|
||||
|
||||
b. "We" (or "Us") shall mean H.AI.
|
||||
|
||||
|
||||
c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
|
||||
|
||||
|
||||
d. "Third Parties" shall mean individuals or legal entities that are not under common control with us or you.
|
||||
e. "H Product" shall mean the large language models, and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Us, and which are “Built with Qwen”.
|
||||
|
||||
|
||||
f. "Qwen" shall mean the large language models, and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Alibaba Cloud.
|
||||
|
||||
|
||||
g. "Materials" shall mean, collectively, H.AI's proprietary H Product and Documentation (and any portion thereof) made available under this Agreement, to the exclusion of Alibaba Cloud’s Materials.
|
||||
"Alibaba Cloud Materials" shall mean, collectively, Alibaba Cloud's proprietary Qwen and Documentation (and any portion thereof) made available under Qwen Research License Agreement.
|
||||
|
||||
|
||||
h. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
|
||||
|
||||
|
||||
i. "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.
|
||||
|
||||
|
||||
j. "Non-Commercial" shall mean for research or evaluation purposes only.
|
||||
k. “Qwen Research License Agreement” shall mean the license agreement governing the use, reproduction, distribution, copy and/or modification of Alibaba Cloud Materials, and available here: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE.
|
||||
|
||||
|
||||
2. Grant of Rights
|
||||
|
||||
|
||||
a. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under H.AIs intellectual property or other rights owned by us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials FOR NON-COMMERCIAL PURPOSES ONLY.
|
||||
|
||||
|
||||
b. If you are commercially using the Materials, you shall request a license from us.
|
||||
|
||||
|
||||
3. Redistribution
|
||||
|
||||
|
||||
You may distribute copies or make the Materials, or derivative works thereof, available as part of a product or service that contains any of them, with or without modifications, and in Source or Object form, provided that you meet the following conditions:
|
||||
|
||||
|
||||
a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement and the Qwen Research License Agreement;
|
||||
|
||||
|
||||
b. You shall cause any modified files to carry prominent notices stating that you changed the files;
|
||||
|
||||
|
||||
c. You shall retain in all copies of the Materials that you distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
|
||||
|
||||
|
||||
d. 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 terms and conditions of this Agreement and the Qwen Research License Agreement.
|
||||
|
||||
|
||||
4. Rules of use
|
||||
|
||||
|
||||
a. The Materials and Alibaba Cloud Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials and Alibaba Cloud Materials.
|
||||
|
||||
|
||||
b. If you use the Materials, Alibaba Cloud Materials or any outputs or results therefrom to create, train, fine-tune, or improve an AI model that is distributed or made available, you shall prominently display “Built with Qwen” or “Improved using Qwen” in the related product documentation.
|
||||
|
||||
|
||||
5. Intellectual Property
|
||||
|
||||
|
||||
a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for us. Conditioned upon compliance with the terms and conditions of this Agreement and the Qwen Research License Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
|
||||
|
||||
|
||||
b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
|
||||
|
||||
|
||||
c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licenses granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
|
||||
|
||||
|
||||
6. Disclaimer of Warranty and Limitation of Liability
|
||||
|
||||
|
||||
a. We are not obligated to support, update, provide training for, or develop any further version of the Materials or to grant any license thereto.
|
||||
|
||||
|
||||
b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
|
||||
|
||||
|
||||
c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
|
||||
|
||||
|
||||
d. You will defend, indemnify and hold harmless us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
|
||||
|
||||
|
||||
7. Survival and Termination.
|
||||
|
||||
|
||||
a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
|
||||
|
||||
|
||||
b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials and Alibaba Cloud Materials. Sections 6 and 8 shall survive the termination of this Agreement.
|
||||
|
||||
|
||||
8. Governing Law and Jurisdiction.
|
||||
|
||||
a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of France, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
|
||||
|
||||
|
||||
b. The Courts of Paris shall have exclusive jurisdiction over any dispute arising out of this Agreement.
|
||||
|
||||
|
||||
9. Other Terms and Conditions.
|
||||
|
||||
|
||||
a. Any arrangements, understandings, or agreements regarding the Material not stated herein are separate from and independent of the terms and conditions of this Agreement. You shall request a separate license from us, if you use the Materials in ways not expressly agreed to in this Agreement.
|
||||
|
||||
|
||||
b. We shall not be bound by any additional or different terms or conditions communicated by you unless expressly agreed.
|
||||
140
README.md
Normal file
140
README.md
Normal file
@@ -0,0 +1,140 @@
|
||||
---
|
||||
license: other
|
||||
license_name: other
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-VL-3B-Instruct
|
||||
pipeline_tag: image-text-to-text
|
||||
library_name: transformers
|
||||
tags:
|
||||
- multimodal
|
||||
- action
|
||||
- agent
|
||||
- pytorch
|
||||
---
|
||||
# **Holo1.5: Foundational Models for Computer Use Agents**
|
||||
[](https://github.com/hcompai/hai-cookbook/blob/main/holo1_5/holo_1_5_quickstart.ipynb)
|
||||
[](https://huggingface.co/spaces/Hcompany/Holo1.5-Navigation)
|
||||
## **Model Description**
|
||||
|
||||
Computer Use (CU) agents are AI systems that can interact with real applications—web, desktop, and mobile—on behalf of a user. They can navigate interfaces, manipulate elements, and answer questions about content, enabling powerful automation and productivity tools. CU agents are becoming increasingly important as they allow humans to delegate complex digital tasks safely and efficiently.
|
||||
|
||||
Our **Holo1.5** series provides state-of-the-art foundational models for building such agents. Holo1.5 models excel at **user interface (UI) localization** and **UI-based question answering (QA)** across web, computer, and mobile environments, with strong performance on benchmarks including [Screenspot-V2](https://huggingface.co/datasets/HongxinLi/ScreenSpot_v2), [Screenspot-Pro](https://huggingface.co/datasets/likaixin/ScreenSpot-Pro), [GroundUI-Web](https://huggingface.co/datasets/agent-studio/GroundUI-1K), [Showdown](https://github.com/generalagents/showdown), and our newly introduced [WebClick](https://huggingface.co/datasets/Hcompany/WebClick).
|
||||
|
||||
The Holo1.5 family comes in **three model sizes** to fit different deployment needs:
|
||||
|
||||
- **3B:** inherits its license from Qwen
|
||||
- **7B:** fully open under Apache 2.0
|
||||
- **72B:** research-only license (non-commercial). For commercial use, please contact us.
|
||||
|
||||
These models are designed to provide reliable, accurate, and efficient foundations for next-generation CU agents, like Surfer-H, enabling them to manipulate real applications with unprecedented capability.
|
||||
|
||||
- **Developed by:** [**H Company**](https://www.hcompany.ai/)
|
||||
- **Model type:** VLM for Computer Use agents
|
||||
- **Fine-tuned from model:** Qwen/Qwen2.5-VL-3B-Instruct
|
||||
- **Blog Post:** https://www.hcompany.ai/blog/holo-1-5
|
||||
- **License:** Qwen Research License
|
||||
|
||||
## Training strategy
|
||||
|
||||
Our models are trained using high-quality proprietary data for UI understanding and action prediction, following a multi-stage training pipeline. The training dataset is a carefully curated mix of open-source datasets, large-scale synthetic data, and human-annotated samples.
|
||||
|
||||
Training proceeds in two stages: large-scale supervised fine-tuning, followed by online reinforcement learning (GRPO). The resulting Holo1.5 models are natively high-resolution (up to 3840 × 2160 pixels), capable of interpreting UIs and performing actions on large, complex screens with accuracy and efficiency.
|
||||
|
||||
## **Results**
|
||||
|
||||
### **Holo1.5: SOTA UI Localization**
|
||||
|
||||
UI Localization refers to an agent’s ability to find the exact positions of elements on a user interface (buttons, text boxes, images, etc.). This capability is essential for Computer Use (CU) agents because, to interact with an application—click a button, fill out a form, or read information—the agent must know where elements are located on the screen.
|
||||
|
||||
Our Holo1.5 models were evaluated on several standard UI localization benchmarks ([Screenspot-V2](https://huggingface.co/datasets/HongxinLi/ScreenSpot_v2), [Screenspot-Pro](https://huggingface.co/datasets/likaixin/ScreenSpot-Pro), [GroundUI-Web](https://huggingface.co/datasets/agent-studio/GroundUI-1K), [Showdown](https://github.com/generalagents/showdown), and our newly introduced [WebClick](https://huggingface.co/datasets/Hcompany/WebClick)) to measure how accurately they can predict these coordinates.
|
||||
|
||||
The results:
|
||||
|
||||
- Our 7B and 72B models outperform all previous models, achieving an average 4.5% improvement in localization accuracy.
|
||||
- Our 3B model, while smaller, remains competitive with previous 7B models, demonstrating strong capabilities even with fewer resources.
|
||||
|
||||
These results establish a new Pareto frontier in open-source UI localization: the best trade-off yet between model size and localization accuracy, setting a new standard for CU agents.
|
||||
|
||||
<p align="center"><img width=800 src="https://assets.hcompanyprod.fr/loc_pareto.png"/><em>Pareto frontier of UI Localization accuracy versus Model size</em></p>
|
||||
|
||||
<p align="center"><img width=1000 src="https://assets.hcompanyprod.fr/loc_chart.png"/><em>Accuracy of our and competitors' models on UI Localization benchmarks.</em></p>
|
||||
|
||||
| | WebClick | Showdown | ScreenSpot-v2 | ScreenSpot-Pro | Ground-UI-1K | OSWorld-G | Average |
|
||||
| --- | --- | --- | --- | --- | --- | --- | --- |
|
||||
| Holo1.5-3B | 81.45 | 67.50 | 91.66 | 51.49 | 83.20 | 61.57 | 72.81 |
|
||||
| Holo1.5-7B | 90.24 | 72.17 | 93.31 | 57.94 | 84.00 | 66.27 | 77.32 |
|
||||
| Holo1.5-72B | 92.43 | **76.84** | 94.41 | **63.25** | 84.50 | **71.80** | **80.54** |
|
||||
| Qwen2.5-VL-3B | 71.20 | *50.30* | *80.00* | *29.30* | 76.40 | 34.31 | 56.92 |
|
||||
| Qwen2.5-VL-7B | 76.51 | *52.00* | *85.60* | *29.00* | 80.70 | 40.59 | 60.73 |
|
||||
| Qwen2.5-VL-72B | 88.29 | *41.00* | *93.30* | *55.60* | **85.40** | 61.96 | 70.93 |
|
||||
| UI-TARS-1.5-7B | 86.10 | *58.00* | *94.00* | *39.00* | 84.20 | 61.40 | 70.45 |
|
||||
| Holo1-7B | 84.04 | 64.27 | 89.85 | 26.06 | 78.50 | 47.25 | 65.00 |
|
||||
| Holo1-3B | 79.35 | 59.96 | 88.91 | 23.66 | 74.75 | 42.16 | 61.47 |
|
||||
| UI-Venus-7B | 84.44 | 67.32 | *94.10* | *50.80* | 82.30 | *58.80* | 72.96 |
|
||||
| UI-Venus-72B | 77.00 | 75.58 | ***95.30*** | *61.90* | 75.50 | 70.40 | 75.95 |
|
||||
| Sonnet 4 | **93.00** | 72.00 | 93.00 | 19.10 | 84.00 | 59.60 | 70.12 |
|
||||
|
||||
Table 1: Localization benchmark scores for leading models. Bold values show state-of-the-art performance, scores in italic were obtained from previously reported sources and scores in non-italic were reproduced in-house
|
||||
|
||||
### Holo1.5: SOTA Screen Content Understanding via Question Answering
|
||||
|
||||
While precise localization is essential for GUI agents, it is equally important for models to comprehend the structure and functionality of user interfaces to interact with them effectively. To evaluate these capabilities, we tested our Holo1.5 models on several GUI-focused question answering (QA) benchmarks, including [ScreenQA Short](https://github.com/google-research-datasets/screen_qa), [ScreenQA Complex](https://github.com/google-research-datasets/screen_qa), [VisualWebBench](https://huggingface.co/datasets/visualwebbench/VisualWebBench), and [WebSRC](https://x-lance.github.io/WebSRC/). These benchmarks measure the models’ ability to understand and reason about UIs, ensuring they can perform tasks accurately across diverse applications.
|
||||
|
||||
<p align="center"><img width=800 src="https://assets.hcompanyprod.fr/qa_pareto.png"/><em>Pareto Frontier of UI Question Answering Performance versus Model size</em></p>
|
||||
|
||||
<p align="center"><img width=1000 src="https://assets.hcompanyprod.fr/qa_chart.png"/><em>UI Understanding and Visual Question Answering performance</em></p>
|
||||
|
||||
|
||||
| | VisualWebBench | WebSRC | ScreenQAShort | ScreenQAComplex | Average |
|
||||
| --- | --- | --- | --- | --- | --- |
|
||||
| Holo1.5-3B | 78.50 | 94.80 | 87.90 | 81.40 | 85.65 |
|
||||
| Holo1.5-7B | 82.60 | 95.90 | 91.00 | 83.20 | 88.17 |
|
||||
| Holo1.5-72B | **83.80** | **97.20** | **91.90** | **87.10** | **90.00** |
|
||||
| Qwen2.5-VL-3B | 58.00 | 93.00 | 86.00 | 76.00 | 78.25 |
|
||||
| Qwen2.5-VL-7B | 69.00 | 95.00 | 87.00 | 81.10 | 83.02 |
|
||||
| Qwen2.5-VL-72B | 76.30 | 97.00 | 87.90 | 83.20 | 86.10 |
|
||||
| UI-TARS-1.5-7B | 79.70 | 92.90 | 88.70 | 79.20 | 85.12 |
|
||||
| Holo1-3B | 54.10 | 93.90 | 78.30 | 53.50 | 69.95 |
|
||||
| Holo1-7B | 38.10 | 95.30 | 83.30 | 65.10 | 70.45 |
|
||||
| UI-Venus-7B | 60.90 | 96.60 | 86.30 | 82.30 | 81.52 |
|
||||
| UI-Venus-72B | 74.10 | 96.70 | 88.60 | 83.30 | 85.67 |
|
||||
| Claude-Sonnet-4 | 58.90 | 96.00 | 87.00 | 75.70 | 79.40 |
|
||||
|
||||
Table 2: Screen content QA benchmark scores for leading models. Bold values show state-of-the-art performance
|
||||
|
||||
Holo1.5 models show impressive capabilities in GUI QA tasks by improving on state-of-the-art models by 3.9%. This demonstrates strong visual perception capabilities in web and desktop environments, which is crucial for computer-use agents
|
||||
|
||||
## Demo
|
||||
|
||||
Watch a demo of how to prompt the model in a computer use setting:
|
||||
|
||||
|
||||
<p align="center">
|
||||
<video controls width="720">
|
||||
<source src="https://assets.hcompanyprod.fr/demo_video.mp4" type="video/mp4">
|
||||
</video>
|
||||
<p>
|
||||
|
||||
The demo is also live on our Hugging Face [Space](https://huggingface.co/spaces/Hcompany/Holo1.5-Navigation).
|
||||
|
||||
|
||||
## Next steps
|
||||
|
||||
Our goal is to build cost-efficient and reliable computer use agents. With the release of Holo1.5, we take an important step toward fostering trust and adoption of this technology.
|
||||
|
||||
This milestone is only the beginning—over the coming weeks, we will be unveiling new tools and agents powered by Holo models.
|
||||
|
||||
Stay tuned—we’re just getting started!
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{hai2025holo15modelfamily,
|
||||
title={Holo1.5 - Open Foundation Models for Computer Use Agents},
|
||||
author={H Company},
|
||||
year={2025},
|
||||
url={https://huggingface.co/collections/Hcompany/holo15-68c1a5736e8583a309d23d9b},
|
||||
}
|
||||
```
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||
}
|
||||
143
config.json
Normal file
143
config.json
Normal file
@@ -0,0 +1,143 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"text_config": {
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"image_token_id": null,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2_5_vl_text",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": null,
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 151936
|
||||
},
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.54.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"fullatt_block_indexes": [
|
||||
7,
|
||||
15,
|
||||
23,
|
||||
31
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1280,
|
||||
"in_channels": 3,
|
||||
"in_chans": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3420,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_heads": 16,
|
||||
"out_hidden_size": 2048,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"tokens_per_second": 2,
|
||||
"torch_dtype": "bfloat16",
|
||||
"window_size": 112
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"attn_implementation": "flash_attention_2",
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 1e-06,
|
||||
"transformers_version": "4.54.0"
|
||||
}
|
||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c1de40966d14e4de98b5c8b366a12e91b7e2fd4f8bc1338a3604fbb982a20ed7
|
||||
size 4997750760
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ee9764c7e2de0b5bc52787d0613947cb8b39b25e16f44784cea319a2ad882f58
|
||||
size 3133917248
|
||||
833
model.safetensors.index.json
Normal file
833
model.safetensors.index.json
Normal file
@@ -0,0 +1,833 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3754622976,
|
||||
"total_size": 8131575808
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
37
preprocessor_config.json
Normal file
37
preprocessor_config.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": 3686400,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 3686400,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
|
||||
size 11422063
|
||||
215
tokenizer_config.json
Normal file
215
tokenizer_config.json
Normal file
@@ -0,0 +1,215 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"max_pixels": 3686400,
|
||||
"min_pixels": 3136,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"use_fast": true
|
||||
}
|
||||
43
video_preprocessor_config.json
Normal file
43
video_preprocessor_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": false,
|
||||
"fps": null,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_frames": 768,
|
||||
"max_pixels": 3686400,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"min_pixels": 3136,
|
||||
"num_frames": null,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"longest_edge": 3686400,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"size_divisor": null,
|
||||
"temporal_patch_size": 2,
|
||||
"video_metadata": null,
|
||||
"video_processor_type": "Qwen2VLVideoProcessor"
|
||||
}
|
||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
760
zero_to_fp32.py
Normal file
760
zero_to_fp32.py
Normal file
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
Reference in New Issue
Block a user