Upload 16 files
Browse files- .gitattributes +1 -0
- LICENSE +54 -0
- README.md +317 -0
- added_tokens.json +39 -0
- chat_template.json +3 -0
- config.json +50 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +832 -0
- preprocessor_config.json +19 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +328 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Qwen RESEARCH LICENSE AGREEMENT
|
| 2 |
+
|
| 3 |
+
Qwen RESEARCH LICENSE AGREEMENT Release Date: September 19, 2024
|
| 4 |
+
|
| 5 |
+
By clicking to agree or by using or distributing any portion or element of the Qwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
|
| 6 |
+
|
| 7 |
+
1. Definitions
|
| 8 |
+
a. This Qwen 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.
|
| 9 |
+
b. "We" (or "Us") shall mean Alibaba Cloud.
|
| 10 |
+
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.
|
| 11 |
+
d. "Third Parties" shall mean individuals or legal entities that are not under common control with us or you.
|
| 12 |
+
e. "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 us.
|
| 13 |
+
f. "Materials" shall mean, collectively, Alibaba Cloud's proprietary Qwen and Documentation (and any portion thereof) made available under this Agreement.
|
| 14 |
+
g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
|
| 15 |
+
h. "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.
|
| 16 |
+
i. "Non-Commercial" shall mean for research or evaluation purposes only.
|
| 17 |
+
|
| 18 |
+
2. Grant of Rights
|
| 19 |
+
a. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Alibaba Cloud's 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.
|
| 20 |
+
b. If you are commercially using the Materials, you shall request a license from us.
|
| 21 |
+
|
| 22 |
+
3. Redistribution
|
| 23 |
+
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:
|
| 24 |
+
a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
|
| 25 |
+
b. You shall cause any modified files to carry prominent notices stating that you changed the files;
|
| 26 |
+
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
|
| 27 |
+
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.
|
| 28 |
+
|
| 29 |
+
4. Rules of use
|
| 30 |
+
a. The 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.
|
| 31 |
+
b. If you use the 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.
|
| 32 |
+
|
| 33 |
+
5. Intellectual Property
|
| 34 |
+
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, 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.
|
| 35 |
+
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.
|
| 36 |
+
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.
|
| 37 |
+
|
| 38 |
+
6. Disclaimer of Warranty and Limitation of Liability
|
| 39 |
+
a. We are not obligated to support, update, provide training for, or develop any further version of the Qwen Materials or to grant any license thereto.
|
| 40 |
+
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.
|
| 41 |
+
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.
|
| 42 |
+
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.
|
| 43 |
+
|
| 44 |
+
7. Survival and Termination.
|
| 45 |
+
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.
|
| 46 |
+
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. Sections 6 and 8 shall survive the termination of this Agreement.
|
| 47 |
+
|
| 48 |
+
8. Governing Law and Jurisdiction.
|
| 49 |
+
a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, 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.
|
| 50 |
+
b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.
|
| 51 |
+
|
| 52 |
+
9. Other Terms and Conditions.
|
| 53 |
+
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.
|
| 54 |
+
b. We shall not be bound by any additional or different terms or conditions communicated by you unless expressly agreed.
|
README.md
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license_name: qwen-research
|
| 3 |
+
license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
benchmarks:
|
| 7 |
+
- ChatDoc/OCRFlux-bench-single
|
| 8 |
+
- ChatDoc/OCRFlux-bench-cross
|
| 9 |
+
- ChatDoc/OCRFlux-pubtabnet-single
|
| 10 |
+
- ChatDoc/OCRFlux-pubtabnet-cross
|
| 11 |
+
base_model:
|
| 12 |
+
- Qwen/Qwen2.5-VL-3B-Instruct
|
| 13 |
+
library_name: transformers
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# OCRFlux-3B
|
| 18 |
+
|
| 19 |
+
This is a preview release of the OCRFlux-3B model that's fine tuned from Qwen2.5-VL-3B-Instruct using the our private document datasets and some data from
|
| 20 |
+
[olmOCR-mix-0225](https://huggingface.co/datasets/allenai/olmOCR-mix-0225) dataset.
|
| 21 |
+
|
| 22 |
+
Quick links:
|
| 23 |
+
- 🛠️ [Code](https://github.com/chatdoc-com/OCRFlux)
|
| 24 |
+
|
| 25 |
+
OCRFlux is a multimodal large language model based toolkit for converting PDFs and images into clean, readable, plain Markdown text. It aims to push the current state-of-the-art to a significantly higher level.
|
| 26 |
+
|
| 27 |
+
Try the online demo: https://ocrflux.pdfparser.io/
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
## Key features:
|
| 31 |
+
Superior parsing quality on each page
|
| 32 |
+
|
| 33 |
+
It respectively achieves 0.095 higher (from 0.872 to 0.967), 0.109 higher (from 0.858 to 0.967) and 0.187 higher (from 0.780 to 0.967) Edit Distance Similarity (EDS) on our released benchmark OCRFlux-bench-single than the baseline model olmOCR-7B-0225-preview, Nanonets-OCR-s and MonkeyOCR.
|
| 34 |
+
|
| 35 |
+
Native support for cross-page table/paragraph merging (to our best this is the first to support this feature in all the open sourced project).
|
| 36 |
+
|
| 37 |
+
Based on a 3B parameter VLM, so it can run even on GTX 3090 GPU.
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
## Usage
|
| 41 |
+
|
| 42 |
+
The best way to use this model is via the [OCRFlux toolkit](https://github.com/chatdoc-com/OCRFlux).
|
| 43 |
+
The toolkit comes with an efficient inference setup via vllm that can handle millions of documents
|
| 44 |
+
at scale.
|
| 45 |
+
|
| 46 |
+
### API for directly calling OCRFlux (New)
|
| 47 |
+
You can use the inference API to directly call OCRFlux in your codes without using an online vllm server like following:
|
| 48 |
+
|
| 49 |
+
```
|
| 50 |
+
from vllm import LLM
|
| 51 |
+
from ocrflux.inference import parse
|
| 52 |
+
|
| 53 |
+
file_path = 'test.pdf'
|
| 54 |
+
# file_path = 'test.png'
|
| 55 |
+
llm = LLM(model="model_dir/OCRFlux-3B",gpu_memory_utilization=0.8,max_model_len=8192)
|
| 56 |
+
result = parse(llm,file_path)
|
| 57 |
+
document_markdown = result['document_text']
|
| 58 |
+
with open('test.md','w') as f:
|
| 59 |
+
f.write(document_markdown)
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
### Docker Usage
|
| 63 |
+
|
| 64 |
+
Requirements:
|
| 65 |
+
|
| 66 |
+
- Docker with GPU support [(NVIDIA Toolkit)](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
|
| 67 |
+
- Pre-downloaded model: [OCRFlux-3B](https://huggingface.co/ChatDOC/OCRFlux-3B)
|
| 68 |
+
|
| 69 |
+
To use OCRFlux in a docker container, you can use the following example command to start the docker container firstly:
|
| 70 |
+
|
| 71 |
+
```bash
|
| 72 |
+
docker run -it --gpus all \
|
| 73 |
+
-v /path/to/localworkspace:/localworkspace \
|
| 74 |
+
-v /path/to/test_pdf_dir:/test_pdf_dir \
|
| 75 |
+
-v /path/to/OCRFlux-3B:/OCRFlux-3B \
|
| 76 |
+
--entrypoint bash \
|
| 77 |
+
chatdoc/ocrflux:latest
|
| 78 |
+
```
|
| 79 |
+
|
| 80 |
+
and then run the following command on the docker container to parse document files:
|
| 81 |
+
|
| 82 |
+
```bash
|
| 83 |
+
python3.12 -m ocrflux.pipeline /localworkspace/ocrflux_results --data /test_pdf_dir/* --model /OCRFlux-3B/
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
The parsing results will be stored in `/localworkspace/ocrflux_results` directory.
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
#### Viewing Results
|
| 90 |
+
Generate the final Markdown files by running the following command. Generated Markdown files will be in `./localworkspace/markdowns/DOCUMENT_NAME` directory.
|
| 91 |
+
|
| 92 |
+
```bash
|
| 93 |
+
python -m ocrflux.jsonl_to_markdown ./localworkspace
|
| 94 |
+
```
|
| 95 |
+
|
| 96 |
+
### Full documentation for the pipeline
|
| 97 |
+
|
| 98 |
+
```bash
|
| 99 |
+
python -m ocrflux.pipeline --help
|
| 100 |
+
usage: pipeline.py [-h] [--task {pdf2markdown,merge_pages,merge_tables}] [--data [DATA ...]] [--pages_per_group PAGES_PER_GROUP] [--max_page_retries MAX_PAGE_RETRIES]
|
| 101 |
+
[--max_page_error_rate MAX_PAGE_ERROR_RATE] [--workers WORKERS] [--model MODEL] [--model_max_context MODEL_MAX_CONTEXT] [--model_chat_template MODEL_CHAT_TEMPLATE]
|
| 102 |
+
[--target_longest_image_dim TARGET_LONGEST_IMAGE_DIM] [--skip_cross_page_merge] [--port PORT]
|
| 103 |
+
workspace
|
| 104 |
+
|
| 105 |
+
Manager for running millions of PDFs through a batch inference pipeline
|
| 106 |
+
|
| 107 |
+
positional arguments:
|
| 108 |
+
workspace The filesystem path where work will be stored, can be a local folder
|
| 109 |
+
|
| 110 |
+
options:
|
| 111 |
+
-h, --help show this help message and exit
|
| 112 |
+
--data [DATA ...] List of paths to files to process
|
| 113 |
+
--pages_per_group PAGES_PER_GROUP
|
| 114 |
+
Aiming for this many pdf pages per work item group
|
| 115 |
+
--max_page_retries MAX_PAGE_RETRIES
|
| 116 |
+
Max number of times we will retry rendering a page
|
| 117 |
+
--max_page_error_rate MAX_PAGE_ERROR_RATE
|
| 118 |
+
Rate of allowable failed pages in a document, 1/250 by default
|
| 119 |
+
--workers WORKERS Number of workers to run at a time
|
| 120 |
+
--model MODEL The path to the model
|
| 121 |
+
--model_max_context MODEL_MAX_CONTEXT
|
| 122 |
+
Maximum context length that the model was fine tuned under
|
| 123 |
+
--model_chat_template MODEL_CHAT_TEMPLATE
|
| 124 |
+
Chat template to pass to vllm server
|
| 125 |
+
--target_longest_image_dim TARGET_LONGEST_IMAGE_DIM
|
| 126 |
+
Dimension on longest side to use for rendering the pdf pages
|
| 127 |
+
--skip_cross_page_merge
|
| 128 |
+
Whether to skip cross-page merging
|
| 129 |
+
--port PORT Port to use for the VLLM server
|
| 130 |
+
```
|
| 131 |
+
|
| 132 |
+
## Code overview
|
| 133 |
+
|
| 134 |
+
There are some nice reusable pieces of the code that may be useful for your own projects:
|
| 135 |
+
- Processing millions of PDFs through our released model using VLLM - [pipeline.py](https://github.com/chatdoc-com/OCRFlux/blob/main/ocrflux/pipeline.py)
|
| 136 |
+
- Generating final Markdowns from jsonl files - [jsonl_to_markdown.py](https://github.com/chatdoc-com/OCRFlux/blob/main/ocrflux/jsonl_to_markdown.py)
|
| 137 |
+
- Evaluating the model on the single-page parsing task - [eval_page_to_markdown.py](https://github.com/chatdoc-com/OCRFlux/blob/main/eval/eval_page_to_markdown.py)
|
| 138 |
+
- Evaluating the model on the table parising task - [eval_table_to_html.py](https://github.com/chatdoc-com/OCRFlux/blob/main/eval/eval_table_to_html.py)
|
| 139 |
+
- Evaluating the model on the paragraphs/tables merging detection task - [eval_element_merge_detect.py](https://github.com/chatdoc-com/OCRFlux/blob/main/eval/eval_element_merge_detect.py)
|
| 140 |
+
- Evaluating the model on the table merging task - [eval_html_table_merge.py](https://github.com/chatdoc-com/OCRFlux/blob/main/eval/eval_html_table_merge.py)
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
|
| 144 |
+
### Benchmark for single-page parsing
|
| 145 |
+
|
| 146 |
+
We ship two comprehensive benchmarks to help measure the performance of our OCR system in single-page parsing:
|
| 147 |
+
|
| 148 |
+
- [OCRFlux-bench-single](https://huggingface.co/datasets/ChatDOC/OCRFlux-bench-single): Containing 2000 pdf pages (1000 English pages and 1000 Chinese pages) and their ground-truth Markdowns (manually labeled with multi-round check).
|
| 149 |
+
|
| 150 |
+
- [OCRFlux-pubtabnet-single](https://huggingface.co/datasets/ChatDOC/OCRFlux-pubtabnet-single): Derived from the public [PubTabNet](https://github.com/ibm-aur-nlp/PubTabNet) benchmark with some format transformation. It contains 9064 HTML table samples, which are split into simple tables and complex tables according to whether they have rowspan and colspan cells.
|
| 151 |
+
|
| 152 |
+
We emphasize that the released benchmarks are NOT included in our training and evaluation data. The following is the main result:
|
| 153 |
+
|
| 154 |
+
|
| 155 |
+
1. In [OCRFlux-bench-single](https://huggingface.co/datasets/ChatDOC/OCRFlux-bench-single), we calculated the Edit Distance Similarity (EDS) between the generated Markdowns and the ground-truth Markdowns as the metric.
|
| 156 |
+
|
| 157 |
+
<table>
|
| 158 |
+
<thead>
|
| 159 |
+
<tr>
|
| 160 |
+
<th>Language</th>
|
| 161 |
+
<th>Model</th>
|
| 162 |
+
<th>Avg EDS ↑</th>
|
| 163 |
+
</tr>
|
| 164 |
+
</thead>
|
| 165 |
+
<tbody>
|
| 166 |
+
<tr>
|
| 167 |
+
<td rowspan="4">English</td>
|
| 168 |
+
<td>olmOCR-7B-0225-preview</td>
|
| 169 |
+
<td>0.885</td>
|
| 170 |
+
</tr>
|
| 171 |
+
<tr>
|
| 172 |
+
<td>Nanonets-OCR-s</td>
|
| 173 |
+
<td>0.870</td>
|
| 174 |
+
</tr>
|
| 175 |
+
<tr>
|
| 176 |
+
<td>MonkeyOCR</td>
|
| 177 |
+
<td>0.828</td>
|
| 178 |
+
</tr>
|
| 179 |
+
<tr>
|
| 180 |
+
<td><strong><a href="https://huggingface.co/ChatDOC/OCRFlux-3B">OCRFlux-3B</a></strong></td>
|
| 181 |
+
<td>0.971</td>
|
| 182 |
+
</tr>
|
| 183 |
+
<tr>
|
| 184 |
+
<td rowspan="4">Chinese</td>
|
| 185 |
+
<td>olmOCR-7B-0225-preview</td>
|
| 186 |
+
<td>0.859</td>
|
| 187 |
+
</tr>
|
| 188 |
+
<tr>
|
| 189 |
+
<td>Nanonets-OCR-s</td>
|
| 190 |
+
<td>0.846</td>
|
| 191 |
+
</tr>
|
| 192 |
+
<tr>
|
| 193 |
+
<td>MonkeyOCR</td>
|
| 194 |
+
<td>0.731</td>
|
| 195 |
+
</tr>
|
| 196 |
+
<tr>
|
| 197 |
+
<td><strong><a href="https://huggingface.co/ChatDOC/OCRFlux-3B">OCRFlux-3B</a></strong></td>
|
| 198 |
+
<td>0.962</td>
|
| 199 |
+
</tr>
|
| 200 |
+
<tr>
|
| 201 |
+
<td rowspan="4">Total</td>
|
| 202 |
+
<td>olmOCR-7B-0225-preview</td>
|
| 203 |
+
<td>0.872</td>
|
| 204 |
+
</tr>
|
| 205 |
+
<tr>
|
| 206 |
+
<td>Nanonets-OCR-s</td>
|
| 207 |
+
<td>0.858</td>
|
| 208 |
+
</tr>
|
| 209 |
+
<tr>
|
| 210 |
+
<td>MonkeyOCR</td>
|
| 211 |
+
<td>0.780</td>
|
| 212 |
+
</tr>
|
| 213 |
+
<tr>
|
| 214 |
+
<td><strong><a href="https://huggingface.co/ChatDOC/OCRFlux-3B">OCRFlux-3B</a></strong></td>
|
| 215 |
+
<td>0.967</td>
|
| 216 |
+
</tr>
|
| 217 |
+
</tbody>
|
| 218 |
+
</table>
|
| 219 |
+
|
| 220 |
+
2. In [OCRFlux-pubtabnet-single](https://huggingface.co/datasets/ChatDOC/OCRFlux-pubtabnet-single), we calculated the Tree Edit Distance-based Similarity (TEDS) between the generated HTML tables and the ground-truth HTML tables as the metric.
|
| 221 |
+
<table>
|
| 222 |
+
<thead>
|
| 223 |
+
<tr>
|
| 224 |
+
<th>Type</th>
|
| 225 |
+
<th>Model</th>
|
| 226 |
+
<th>Avg TEDS ↑</th>
|
| 227 |
+
</tr>
|
| 228 |
+
</thead>
|
| 229 |
+
<tbody>
|
| 230 |
+
<tr>
|
| 231 |
+
<td rowspan="4">Simple</td>
|
| 232 |
+
<td>olmOCR-7B-0225-preview</td>
|
| 233 |
+
<td>0.810</td>
|
| 234 |
+
</tr>
|
| 235 |
+
<tr>
|
| 236 |
+
<td>Nanonets-OCR-s</td>
|
| 237 |
+
<td>0.882</td>
|
| 238 |
+
</tr>
|
| 239 |
+
<tr>
|
| 240 |
+
<td>MonkeyOCR</td>
|
| 241 |
+
<td>0.880</td>
|
| 242 |
+
</tr>
|
| 243 |
+
<tr>
|
| 244 |
+
<td><strong><a href="https://huggingface.co/ChatDOC/OCRFlux-3B">OCRFlux-3B</a></strong></td>
|
| 245 |
+
<td>0.912</td>
|
| 246 |
+
</tr>
|
| 247 |
+
<tr>
|
| 248 |
+
<td rowspan="4">Complex</td>
|
| 249 |
+
<td>olmOCR-7B-0225-preview</td>
|
| 250 |
+
<td>0.676</td>
|
| 251 |
+
</tr>
|
| 252 |
+
<tr>
|
| 253 |
+
<td>Nanonets-OCR-s</td>
|
| 254 |
+
<td>0.772</td>
|
| 255 |
+
</tr>
|
| 256 |
+
<tr>
|
| 257 |
+
<td><strong>MonkeyOCR<strong></td>
|
| 258 |
+
<td>0.826</td>
|
| 259 |
+
</tr>
|
| 260 |
+
<tr>
|
| 261 |
+
<td><a href="https://huggingface.co/ChatDOC/OCRFlux-3B">OCRFlux-3B</a></td>
|
| 262 |
+
<td>0.807</td>
|
| 263 |
+
</tr>
|
| 264 |
+
<tr>
|
| 265 |
+
<td rowspan="4">Total</td>
|
| 266 |
+
<td>olmOCR-7B-0225-preview</td>
|
| 267 |
+
<td>0.744</td>
|
| 268 |
+
</tr>
|
| 269 |
+
<tr>
|
| 270 |
+
<td>Nanonets-OCR-s</td>
|
| 271 |
+
<td>0.828</td>
|
| 272 |
+
</tr>
|
| 273 |
+
<tr>
|
| 274 |
+
<td>MonkeyOCR</td>
|
| 275 |
+
<td>0.853</td>
|
| 276 |
+
</tr>
|
| 277 |
+
<tr>
|
| 278 |
+
<td><strong><a href="https://huggingface.co/ChatDOC/OCRFlux-3B">OCRFlux-3B</a></strong></td>
|
| 279 |
+
<td>0.861</td>
|
| 280 |
+
</tr>
|
| 281 |
+
</tbody>
|
| 282 |
+
</table>
|
| 283 |
+
|
| 284 |
+
We also conduct some case studies to show the superiority of our model in the [blog](https://ocrflux.pdfparser.io/#/blog) article.
|
| 285 |
+
|
| 286 |
+
### Benchmark for cross-page table/paragraph merging
|
| 287 |
+
|
| 288 |
+
PDF documents are typically paginated, which often results in tables or paragraphs being split across consecutive pages. Accurately detecting and merging such cross-page structures is crucial to avoid generating incomplete or fragmented content.
|
| 289 |
+
|
| 290 |
+
The detection task can be formulated as follows: given the Markdowns of two consecutive pages—each structured as a list of Markdown elements (e.g., paragraphs and tables)—the goal is to identify the indexes of elements that should be merged across the pages.
|
| 291 |
+
|
| 292 |
+
Then for the merging task, if the elements to be merged are paragraphs, we can just concate them. However, for two table fragments, their merging is much more challenging. For example, the table spanning multiple pages will repeat the header of the first page on the second page. Another difficult scenario is that the table cell contains long content that spans multiple lines within the cell, with the first few lines appearing on the previous page and the remaining lines continuing on the next page. We also observe some cases where tables with a large number of columns are split vertically and placed on two consecutive pages. More examples of cross-page tables can be found in our [blog](https://ocrflux.pdfparser.io/#/blog) article. To address these issues, we develop the LLM model for cross-page table merging. Specifically, this model takes two split table fragments as input and generates a complete, well-structured table as output.
|
| 293 |
+
|
| 294 |
+
We ship two comprehensive benchmarks to help measure the performance of our OCR system in cross-page table/paragraph detection and merging tasks respectively:
|
| 295 |
+
|
| 296 |
+
- [OCRFlux-bench-cross](https://huggingface.co/datasets/ChatDOC/OCRFlux-bench-cross): Containing 1000 samples (500 English samples and 500 Chinese samples), each sample contains the Markdown element lists of two consecutive pages, along with the indexes of elements that need to be merged (manually labeled through multiple rounds of review). If no tables or paragraphs require merging, the indexes in the annotation data are left empty.
|
| 297 |
+
|
| 298 |
+
- [OCRFlux-pubtabnet-cross](https://huggingface.co/datasets/ChatDOC/OCRFlux-pubtabnet-cross): Containing 9064 pairs of split table fragments, along with their corresponding ground-truth merged versions.
|
| 299 |
+
|
| 300 |
+
The released benchmarks are NOT included in our training and evaluation data neither. The following is the main result:
|
| 301 |
+
|
| 302 |
+
1. In [OCRFlux-bench-cross](https://huggingface.co/datasets/ChatDOC/OCRFlux-bench-cross), we caculated the Accuracy, Precision, Recall and F1 score as the metric. Notice that the detection results are right only when it accurately judges whether there are elements that need to be merged across the two pages and output the right indexes of them.
|
| 303 |
+
|
| 304 |
+
| Language | Precision ↑ | Recall ↑ | F1 ↑ | Accuracy ↑ |
|
| 305 |
+
|----------|-------------|----------|-------|------------|
|
| 306 |
+
| English | 0.992 | 0.964 | 0.978 | 0.978 |
|
| 307 |
+
| Chinese | 1.000 | 0.988 | 0.994 | 0.994 |
|
| 308 |
+
| Total | 0.996 | 0.976 | 0.986 | 0.986 |
|
| 309 |
+
|
| 310 |
+
2. In [OCRFlux-pubtabnet-cross](https://huggingface.co/datasets/ChatDOC/OCRFlux-pubtabnet-cross), we calculate the Tree Edit Distance-based Similarity (TEDS) between the generated merged table and the ground-truth merged table as the metric.
|
| 311 |
+
|
| 312 |
+
| Table type | Avg TEDS ↑ |
|
| 313 |
+
|------------|--------------|
|
| 314 |
+
| Simple | 0.965 |
|
| 315 |
+
| Complex | 0.935 |
|
| 316 |
+
| Total | 0.950 |
|
| 317 |
+
|
added_tokens.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|extra_0|>": 151665,
|
| 8 |
+
"<|extra_1|>": 151666,
|
| 9 |
+
"<|extra_2|>": 151667,
|
| 10 |
+
"<|extra_3|>": 151668,
|
| 11 |
+
"<|extra_4|>": 151669,
|
| 12 |
+
"<|extra_5|>": 151670,
|
| 13 |
+
"<|extra_6|>": 151671,
|
| 14 |
+
"<|extra_7|>": 151672,
|
| 15 |
+
"<|file_sep|>": 151664,
|
| 16 |
+
"<|fim_middle|>": 151660,
|
| 17 |
+
"<|fim_pad|>": 151662,
|
| 18 |
+
"<|fim_prefix|>": 151659,
|
| 19 |
+
"<|fim_suffix|>": 151661,
|
| 20 |
+
"<|im_end|>": 151645,
|
| 21 |
+
"<|im_start|>": 151644,
|
| 22 |
+
"<|image_pad|>": 151655,
|
| 23 |
+
"<|object_ref_end|>": 151647,
|
| 24 |
+
"<|object_ref_start|>": 151646,
|
| 25 |
+
"<|pad_0|>": 151673,
|
| 26 |
+
"<|pad_1|>": 151674,
|
| 27 |
+
"<|pad_2|>": 151675,
|
| 28 |
+
"<|pad_3|>": 151676,
|
| 29 |
+
"<|pad_4|>": 151677,
|
| 30 |
+
"<|pad_5|>": 151678,
|
| 31 |
+
"<|pad_6|>": 151679,
|
| 32 |
+
"<|quad_end|>": 151651,
|
| 33 |
+
"<|quad_start|>": 151650,
|
| 34 |
+
"<|repo_name|>": 151663,
|
| 35 |
+
"<|video_pad|>": 151656,
|
| 36 |
+
"<|vision_end|>": 151653,
|
| 37 |
+
"<|vision_pad|>": 151654,
|
| 38 |
+
"<|vision_start|>": 151652
|
| 39 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"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 %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/.cache/huggingface/hub/Qwen2.5-VL-3B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 128000,
|
| 15 |
+
"max_window_layers": 70,
|
| 16 |
+
"model_type": "qwen2_5_vl",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": {
|
| 22 |
+
"mrope_section": [
|
| 23 |
+
16,
|
| 24 |
+
24,
|
| 25 |
+
24
|
| 26 |
+
],
|
| 27 |
+
"rope_type": "default",
|
| 28 |
+
"type": "default"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 1000000.0,
|
| 31 |
+
"sliding_window": 32768,
|
| 32 |
+
"tie_word_embeddings": true,
|
| 33 |
+
"torch_dtype": "bfloat16",
|
| 34 |
+
"transformers_version": "4.49.0",
|
| 35 |
+
"use_cache": false,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"video_token_id": 151656,
|
| 38 |
+
"vision_config": {
|
| 39 |
+
"hidden_size": 1280,
|
| 40 |
+
"in_chans": 3,
|
| 41 |
+
"model_type": "qwen2_5_vl",
|
| 42 |
+
"out_hidden_size": 2048,
|
| 43 |
+
"spatial_patch_size": 14,
|
| 44 |
+
"tokens_per_second": 2
|
| 45 |
+
},
|
| 46 |
+
"vision_end_token_id": 151653,
|
| 47 |
+
"vision_start_token_id": 151652,
|
| 48 |
+
"vision_token_id": 151654,
|
| 49 |
+
"vocab_size": 151680
|
| 50 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"max_length": 16384,
|
| 9 |
+
"min_answer_history_tokens": 64,
|
| 10 |
+
"pad_token_id": 151643,
|
| 11 |
+
"repetition_penalty": 1.05,
|
| 12 |
+
"temperature": 0.1,
|
| 13 |
+
"top_k": 1,
|
| 14 |
+
"top_p": 0.001,
|
| 15 |
+
"transformers_version": "4.49.0"
|
| 16 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d2640c387e5bdce004e2a77b08ac714d39a6c49a2f088853e2ecf05a398d137
|
| 3 |
+
size 4996702184
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1ddaffaa0dc63e4e6aa4a9de8515ea3935d862b6474a198d9697999113ff5c9
|
| 3 |
+
size 3132868672
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,832 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8129478656
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 11 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 23 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 25 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 35 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 37 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 47 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 51 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 59 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 61 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 71 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 73 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 75 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 83 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 85 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 87 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 95 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 97 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 107 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 109 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 111 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 119 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 121 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 131 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 133 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 143 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 145 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 155 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 167 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 169 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 179 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 181 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 183 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 191 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 193 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 195 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 197 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 199 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 203 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 205 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 207 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 209 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 211 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 215 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 217 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 219 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 221 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 223 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 227 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 229 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 231 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 233 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 235 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 239 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 241 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 245 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 247 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 251 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 253 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 255 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 257 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 259 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 263 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 265 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 267 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 275 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 277 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 279 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 287 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 289 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 291 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 299 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 301 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 311 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 313 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 323 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 325 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 327 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 335 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 337 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 347 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 349 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 351 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 353 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 359 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 361 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 365 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 371 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 730 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 731 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 732 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 734 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 735 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 739 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 741 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 743 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 744 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 745 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 746 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 747 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 749 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 750 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 751 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 752 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 753 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 754 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 755 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 756 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 757 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 758 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 759 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 760 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 761 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 762 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 763 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 764 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 765 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 766 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 767 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 768 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 769 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 770 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 771 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 772 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 773 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 774 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 775 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 776 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 777 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 778 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 779 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 780 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 781 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 782 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 783 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 784 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 785 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 786 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 787 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 788 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 789 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 790 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 791 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 792 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 793 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 794 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 795 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 796 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 797 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 798 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 799 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 800 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 801 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 802 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 803 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 804 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 805 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 806 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 807 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 808 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 809 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 810 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 811 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 812 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 813 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 814 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 815 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 816 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 817 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 818 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 819 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 820 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 821 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 822 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 823 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 824 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 825 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 826 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 827 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 828 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 829 |
+
"model.norm.weight": "model-00002-of-00002.safetensors",
|
| 830 |
+
"lm_head.weight": "model-00002-of-00002.safetensors"
|
| 831 |
+
}
|
| 832 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:075aa21db84b26db9c87f0fd0254ad7bd5cbe86f1b55bebad04020e2a56a5130
|
| 3 |
+
size 11424702
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,328 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<|extra_0|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "<|extra_1|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<|extra_2|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "<|extra_3|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"151669": {
|
| 214 |
+
"content": "<|extra_4|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"151670": {
|
| 222 |
+
"content": "<|extra_5|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"151671": {
|
| 230 |
+
"content": "<|extra_6|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"151672": {
|
| 238 |
+
"content": "<|extra_7|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"151673": {
|
| 246 |
+
"content": "<|pad_0|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"151674": {
|
| 254 |
+
"content": "<|pad_1|>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"151675": {
|
| 262 |
+
"content": "<|pad_2|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"151676": {
|
| 270 |
+
"content": "<|pad_3|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"151677": {
|
| 278 |
+
"content": "<|pad_4|>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"151678": {
|
| 286 |
+
"content": "<|pad_5|>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"151679": {
|
| 294 |
+
"content": "<|pad_6|>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
}
|
| 301 |
+
},
|
| 302 |
+
"additional_special_tokens": [
|
| 303 |
+
"<|im_start|>",
|
| 304 |
+
"<|im_end|>",
|
| 305 |
+
"<|object_ref_start|>",
|
| 306 |
+
"<|object_ref_end|>",
|
| 307 |
+
"<|box_start|>",
|
| 308 |
+
"<|box_end|>",
|
| 309 |
+
"<|quad_start|>",
|
| 310 |
+
"<|quad_end|>",
|
| 311 |
+
"<|vision_start|>",
|
| 312 |
+
"<|vision_end|>",
|
| 313 |
+
"<|vision_pad|>",
|
| 314 |
+
"<|image_pad|>",
|
| 315 |
+
"<|video_pad|>"
|
| 316 |
+
],
|
| 317 |
+
"bos_token": null,
|
| 318 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 319 |
+
"clean_up_tokenization_spaces": false,
|
| 320 |
+
"eos_token": "<|im_end|>",
|
| 321 |
+
"errors": "replace",
|
| 322 |
+
"extra_special_tokens": {},
|
| 323 |
+
"model_max_length": 1000000000.0,
|
| 324 |
+
"pad_token": "<|endoftext|>",
|
| 325 |
+
"split_special_tokens": false,
|
| 326 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 327 |
+
"unk_token": null
|
| 328 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|