Instructions to use HuiLin0220/Medcat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HuiLin0220/Medcat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="HuiLin0220/Medcat")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("HuiLin0220/Medcat", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HuiLin0220/Medcat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HuiLin0220/Medcat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HuiLin0220/Medcat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HuiLin0220/Medcat
- SGLang
How to use HuiLin0220/Medcat with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "HuiLin0220/Medcat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HuiLin0220/Medcat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "HuiLin0220/Medcat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HuiLin0220/Medcat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HuiLin0220/Medcat with Docker Model Runner:
docker model run hf.co/HuiLin0220/Medcat
Add files using upload-large-folder tool
Browse files- .gitattributes +3 -35
- LICENSE-INTERNVL +21 -0
- LICENSE-MEDCAT +201 -0
- LICENSE-QWEN +51 -0
- NOTICE +17 -0
- README.md +77 -0
- SHA256SUMS.models +46 -0
- models/FLARE-InternVL3-8B-hf/classification/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/classification/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/counting/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/counting/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/detection/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/detection/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/instance_detection/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/instance_detection/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/internvl-all/lora/sft/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/internvl-all/lora/sft/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/multi_label_binary_focal_v2_best/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/multi_label_binary_focal_v2_best/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/multi_label_classification/adapter_config.json +65 -0
- models/FLARE-InternVL3-8B-hf/multi_label_classification/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/multi_label_joint_linear/metadata.json +189 -0
- models/FLARE-InternVL3-8B-hf/multi_label_joint_mlp/head.npz +3 -0
- models/FLARE-InternVL3-8B-hf/multi_label_joint_mlp/metadata.json +189 -0
- models/FLARE-InternVL3-8B-hf/regression/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/regression/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/report_generation/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/report_generation/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/source_classification/bone_marrow_feature_head/metadata.json +246 -0
- models/FLARE-InternVL3-8B-hf/source_classification/dental/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/source_classification/fundus/adapter_config.json +39 -0
- models/FLARE-InternVL3-8B-hf/source_classification/fundus/adapter_model.safetensors +3 -0
- models/FLARE-InternVL3-8B-hf/source_classification/selection.json +47 -0
- models/FLARE-InternVL3-8B-hf/source_classification/template_routes.json +4 -0
- models/InternVL3-8B-hf/added_tokens.json +34 -0
- models/InternVL3-8B-hf/chat_template.jinja +6 -0
- models/InternVL3-8B-hf/config.json +79 -0
- models/InternVL3-8B-hf/generation_config.json +6 -0
- models/InternVL3-8B-hf/merges.txt +0 -0
- models/InternVL3-8B-hf/model-00001-of-00004.safetensors +3 -0
- models/InternVL3-8B-hf/model-00002-of-00004.safetensors +3 -0
- models/InternVL3-8B-hf/model-00003-of-00004.safetensors +3 -0
- models/InternVL3-8B-hf/model-00004-of-00004.safetensors +3 -0
- models/InternVL3-8B-hf/model.safetensors.index.json +788 -0
- models/InternVL3-8B-hf/preprocessor_config.json +34 -0
- models/InternVL3-8B-hf/processor_config.json +4 -0
- models/InternVL3-8B-hf/special_tokens_map.json +44 -0
- models/InternVL3-8B-hf/tokenizer.json +3 -0
- models/InternVL3-8B-hf/tokenizer_config.json +306 -0
- models/InternVL3-8B-hf/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -1,36 +1,4 @@
|
|
| 1 |
-
*
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
-
*.xz 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 |
-
Medcat-V10-four-task-sanity.mp4 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 1 |
+
* text=auto eol=lf
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
models/InternVL3-8B-hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
LICENSE-INTERNVL
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MIT License
|
| 2 |
+
|
| 3 |
+
Copyright (c) 2023 OpenGVLab
|
| 4 |
+
|
| 5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 6 |
+
of this software and associated documentation files (the "Software"), to deal
|
| 7 |
+
in the Software without restriction, including without limitation the rights
|
| 8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
| 9 |
+
copies of the Software, and to permit persons to whom the Software is
|
| 10 |
+
furnished to do so, subject to the following conditions:
|
| 11 |
+
|
| 12 |
+
The above copyright notice and this permission notice shall be included in all
|
| 13 |
+
copies or substantial portions of the Software.
|
| 14 |
+
|
| 15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
| 16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
| 17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
| 18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
| 19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
| 20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
| 21 |
+
SOFTWARE.
|
LICENSE-MEDCAT
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
| 178 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 179 |
+
|
| 180 |
+
To apply the Apache License to your work, attach the following
|
| 181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 182 |
+
replaced with your own identifying information. (Don't include
|
| 183 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 184 |
+
comment syntax for the file format. We also recommend that a
|
| 185 |
+
file or class name and description of purpose be included on the
|
| 186 |
+
same "printed page" as the copyright notice for easier
|
| 187 |
+
identification within third-party archives.
|
| 188 |
+
|
| 189 |
+
Copyright [yyyy] [name of copyright owner]
|
| 190 |
+
|
| 191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 192 |
+
you may not use this file except in compliance with the License.
|
| 193 |
+
You may obtain a copy of the License at
|
| 194 |
+
|
| 195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 196 |
+
|
| 197 |
+
Unless required by applicable law or agreed to in writing, software
|
| 198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 200 |
+
See the License for the specific language governing permissions and
|
| 201 |
+
limitations under the License.
|
LICENSE-QWEN
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Qwen LICENSE AGREEMENT
|
| 2 |
+
|
| 3 |
+
Qwen 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 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 |
+
|
| 17 |
+
2. Grant of Rights
|
| 18 |
+
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.
|
| 19 |
+
|
| 20 |
+
3. Redistribution
|
| 21 |
+
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:
|
| 22 |
+
a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
|
| 23 |
+
b. You shall cause any modified files to carry prominent notices stating that you changed the files;
|
| 24 |
+
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 LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
|
| 25 |
+
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.
|
| 26 |
+
|
| 27 |
+
4. Restrictions
|
| 28 |
+
If you are commercially using the Materials, and your product or service has more than 100 million monthly active users, you shall request a license from us. You cannot exercise your rights under this Agreement without our express authorization.
|
| 29 |
+
|
| 30 |
+
5. Rules of use
|
| 31 |
+
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.
|
| 32 |
+
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.
|
| 33 |
+
|
| 34 |
+
6. Intellectual Property
|
| 35 |
+
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.
|
| 36 |
+
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.
|
| 37 |
+
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.
|
| 38 |
+
|
| 39 |
+
7. Disclaimer of Warranty and Limitation of Liability
|
| 40 |
+
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.
|
| 41 |
+
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.
|
| 42 |
+
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.
|
| 43 |
+
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.
|
| 44 |
+
|
| 45 |
+
8. Survival and Termination.
|
| 46 |
+
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.
|
| 47 |
+
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 7 and 9 shall survive the termination of this Agreement.
|
| 48 |
+
|
| 49 |
+
9. Governing Law and Jurisdiction.
|
| 50 |
+
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.
|
| 51 |
+
b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.
|
NOTICE
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Medcat V10
|
| 2 |
+
Copyright 2026 Hui Lin
|
| 3 |
+
|
| 4 |
+
Medcat inference code and adapters derive in part from ME-VLIP, distributed
|
| 5 |
+
under the Apache License, Version 2.0:
|
| 6 |
+
https://github.com/BioMedIA-MBZUAI/ME-VLIP
|
| 7 |
+
|
| 8 |
+
The bundled InternVL3-8B-hf base model derives from InternVL by OpenGVLab.
|
| 9 |
+
InternVL is distributed under the MIT License; see LICENSE-INTERNVL.
|
| 10 |
+
|
| 11 |
+
Qwen is licensed under the Qwen LICENSE AGREEMENT, Copyright (c) Alibaba
|
| 12 |
+
Cloud. All Rights Reserved. See LICENSE-QWEN.
|
| 13 |
+
|
| 14 |
+
The bundled base-model files are redistributed without numerical
|
| 15 |
+
modification from OpenGVLab/InternVL3-8B-hf. Medcat task/source adapters and
|
| 16 |
+
auxiliary heads are separate fine-tuned components loaded at inference time.
|
| 17 |
+
|
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: qwen
|
| 4 |
+
license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
|
| 5 |
+
base_model: OpenGVLab/InternVL3-8B-hf
|
| 6 |
+
library_name: transformers
|
| 7 |
+
pipeline_tag: image-text-to-text
|
| 8 |
+
tags:
|
| 9 |
+
- medical
|
| 10 |
+
- vision-language
|
| 11 |
+
- internvl
|
| 12 |
+
- flare
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Medcat V10 Weights
|
| 16 |
+
|
| 17 |
+
This repository contains the model assets for the public Medcat V10
|
| 18 |
+
four-task inference release. The executable inference source is maintained at
|
| 19 |
+
[HuiLin0220/Medcat](https://github.com/HuiLin0220/Medcat).
|
| 20 |
+
|
| 21 |
+
**Built with Qwen.** The bundle contains the InternVL3-8B-hf base model,
|
| 22 |
+
task/source LoRA adapters, and compact classification heads required for
|
| 23 |
+
disease classification, multi-label classification, detection, and
|
| 24 |
+
regression.
|
| 25 |
+
|
| 26 |
+
## Download Into the Source Repository
|
| 27 |
+
|
| 28 |
+
Clone the inference source, install the Hugging Face CLI, and download only
|
| 29 |
+
the model tree into the repository root:
|
| 30 |
+
|
| 31 |
+
```bash
|
| 32 |
+
git clone https://github.com/HuiLin0220/Medcat.git
|
| 33 |
+
cd Medcat
|
| 34 |
+
python -m pip install --upgrade huggingface_hub
|
| 35 |
+
hf download HuiLin0220/Medcat --include "models/**" --local-dir .
|
| 36 |
+
sha256sum --check SHA256SUMS
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
The resulting layout is:
|
| 40 |
+
|
| 41 |
+
```text
|
| 42 |
+
Medcat/
|
| 43 |
+
|-- inference.py
|
| 44 |
+
|-- predict.sh
|
| 45 |
+
`-- models/
|
| 46 |
+
|-- InternVL3-8B-hf/
|
| 47 |
+
`-- FLARE-InternVL3-8B-hf/
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
The model directory is approximately 16 GB. Downloads use the Hugging Face
|
| 51 |
+
Hub's resumable transfer mechanism.
|
| 52 |
+
|
| 53 |
+
## Integrity
|
| 54 |
+
|
| 55 |
+
`SHA256SUMS.models` records every file in the model tree. From a checkout of
|
| 56 |
+
this weight repository, verify it with:
|
| 57 |
+
|
| 58 |
+
```bash
|
| 59 |
+
sha256sum --check SHA256SUMS.models
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
All tensor files were compared byte-for-byte with the evaluated Medcat V10
|
| 63 |
+
container. One unused predecessor focal checkpoint was omitted, and two
|
| 64 |
+
machine-local provenance paths in non-tensor metadata were replaced with
|
| 65 |
+
portable descriptions.
|
| 66 |
+
|
| 67 |
+
## Licenses
|
| 68 |
+
|
| 69 |
+
- Medcat and ME-VLIP components: `LICENSE-MEDCAT` (Apache-2.0)
|
| 70 |
+
- InternVL components: `LICENSE-INTERNVL` (MIT)
|
| 71 |
+
- Qwen components: `LICENSE-QWEN` (Qwen License Agreement)
|
| 72 |
+
- Required attribution notices: `NOTICE`
|
| 73 |
+
|
| 74 |
+
Users must comply with all applicable upstream terms. These weights are
|
| 75 |
+
released for research and challenge reproduction and are not intended for
|
| 76 |
+
clinical diagnosis or treatment.
|
| 77 |
+
|
SHA256SUMS.models
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
3d032d56ac8be44c78ed7ef91364f8234162ab76808759f76afb1eed3acdeb81 models/FLARE-InternVL3-8B-hf/classification/adapter_config.json
|
| 2 |
+
90f9852b491636ddd8a22414aee983cc4c13337296dcd70dca393a55e926abd6 models/FLARE-InternVL3-8B-hf/classification/adapter_model.safetensors
|
| 3 |
+
beca68d4d2033b0f9a0dd60f71af45ef92c033eba37e28525f47a0b75c8a00ec models/FLARE-InternVL3-8B-hf/counting/adapter_config.json
|
| 4 |
+
01b448ea3f42491104e968dde4e0ed4d1085f8fcb80cd241a51eece620958724 models/FLARE-InternVL3-8B-hf/counting/adapter_model.safetensors
|
| 5 |
+
59426667dad238defbca767576d0359a21c103175461fbe983481a61c10ce871 models/FLARE-InternVL3-8B-hf/detection/adapter_config.json
|
| 6 |
+
2e005ac2b87807733a41dabf8821a19df6085d69ac06211e6d4e7911d97d93d9 models/FLARE-InternVL3-8B-hf/detection/adapter_model.safetensors
|
| 7 |
+
3ca9b0d0f2f39f73490729d6ff836f61514debb4e49e87be532254974df31c38 models/FLARE-InternVL3-8B-hf/instance_detection/adapter_config.json
|
| 8 |
+
22ead29cddbc78da63791447014ffb53e78cd590410f87b2b1228d0055f83636 models/FLARE-InternVL3-8B-hf/instance_detection/adapter_model.safetensors
|
| 9 |
+
b91cc891923ca1abc729049b1df94cf484c9d8216b242e9066edd29bac13adad models/FLARE-InternVL3-8B-hf/internvl-all/lora/sft/adapter_config.json
|
| 10 |
+
759e3b7853c054e699c2f80948bc374ac070ef4526c743e14512600a0bdd5f15 models/FLARE-InternVL3-8B-hf/internvl-all/lora/sft/adapter_model.safetensors
|
| 11 |
+
aeec0212d29c739bbd14dc5ca8ecda84654b2f38c6eaa385d990272a7740b248 models/FLARE-InternVL3-8B-hf/multi_label_binary_focal_v2_best/adapter_config.json
|
| 12 |
+
30d9bc38faddef85290850b9134163c5d56af07de6354059c89c5a9d1369a90d models/FLARE-InternVL3-8B-hf/multi_label_binary_focal_v2_best/adapter_model.safetensors
|
| 13 |
+
76519ee9fbfd861b9bf6f3889cc41bf4252dc93f3e6794bc456e2b11a7300884 models/FLARE-InternVL3-8B-hf/multi_label_classification/adapter_config.json
|
| 14 |
+
916027dd00c743aa4945fd611c8442e2c35dcee26a6c79f836eeb55a0eb91ce5 models/FLARE-InternVL3-8B-hf/multi_label_classification/adapter_model.safetensors
|
| 15 |
+
2f859f6e872a4a5ae76231714e88c4850977092be679c3a49344ed9a6f753d4a models/FLARE-InternVL3-8B-hf/multi_label_joint_linear/head.npz
|
| 16 |
+
d87631fa79ae1d4ad1ec04ef28578aeaa3139547d1b5d0624d8c4a9873c34654 models/FLARE-InternVL3-8B-hf/multi_label_joint_linear/metadata.json
|
| 17 |
+
3a84cf3446250edaf5c2903278b1991fff4f9b5ba57d48b1603d1539c076344b models/FLARE-InternVL3-8B-hf/multi_label_joint_mlp/head.npz
|
| 18 |
+
5ff574938233c668b09fa245979148f645086dcdd3a8f9297b356167a93399e0 models/FLARE-InternVL3-8B-hf/multi_label_joint_mlp/metadata.json
|
| 19 |
+
4cb08c314bf041ae3cad13a8a322694a5532c2955f67d3108e6befa39bcb954f models/FLARE-InternVL3-8B-hf/regression/adapter_config.json
|
| 20 |
+
b538b46ea37a3fb145e3ca7c24d41b439d189ae15bf986cb7d75d17556814d83 models/FLARE-InternVL3-8B-hf/regression/adapter_model.safetensors
|
| 21 |
+
dbeff761b0ebdec388fc4e2422123b05cc2da466df6df02832070b8c9df4a597 models/FLARE-InternVL3-8B-hf/report_generation/adapter_config.json
|
| 22 |
+
2cb69a952b13efa953ce7894cedb81984cdb63516f4dfb5c8079a2dc54ebfe5a models/FLARE-InternVL3-8B-hf/report_generation/adapter_model.safetensors
|
| 23 |
+
9d73f02c2e6be4738c61995c7d6df3470c64d6f985b988ea7ffbb462edab6f4d models/FLARE-InternVL3-8B-hf/source_classification/bone_marrow_feature_head/head.npz
|
| 24 |
+
c0d1c2a9193c8400433ef512e72455a20427b5525bfb7d7b101a51368f7666ec models/FLARE-InternVL3-8B-hf/source_classification/bone_marrow_feature_head/metadata.json
|
| 25 |
+
cd63f8335a2ed3e57484799fd7a6b186ea18a960a7136ad874ab13dae876a25c models/FLARE-InternVL3-8B-hf/source_classification/dental/adapter_config.json
|
| 26 |
+
67082c99bd1870691037cc84da06812afc89366d1c389dc5f0f660d8d9ab7502 models/FLARE-InternVL3-8B-hf/source_classification/dental/adapter_model.safetensors
|
| 27 |
+
aa609d427b2ada3a7729573ad6ebf99ae992ca80b3b7bb8c8d70a37155ca32b8 models/FLARE-InternVL3-8B-hf/source_classification/fundus/adapter_config.json
|
| 28 |
+
97f2c8feae51a52b23810a0dc0b861bb636a7be840ee629f1d1c9fae87f89cb3 models/FLARE-InternVL3-8B-hf/source_classification/fundus/adapter_model.safetensors
|
| 29 |
+
3dae1cdd4d104656621be28949459327792166b65d851ee48c5f1521f88ddb27 models/FLARE-InternVL3-8B-hf/source_classification/selection.json
|
| 30 |
+
384a5610a8c430ad3024534cafa6fc655886ed9a4160a59a9624c8db17b47cd7 models/FLARE-InternVL3-8B-hf/source_classification/template_routes.json
|
| 31 |
+
222d504fd2fb42e08a43b7ef6383a130483d34233f506b6ccc799655de48dff8 models/InternVL3-8B-hf/added_tokens.json
|
| 32 |
+
b3e3fa7cdeceec1d3dfe0d17b77724baf3857714e688f3a700261567e96140eb models/InternVL3-8B-hf/chat_template.jinja
|
| 33 |
+
2f651cf5dcad81635fcd688dc8aa569797a3d829b9d0644f489e1c7272b1c637 models/InternVL3-8B-hf/config.json
|
| 34 |
+
c142bebeae7dfc9ef119d3f12fb03022261ceef51320c75ead103af4d8e150c2 models/InternVL3-8B-hf/generation_config.json
|
| 35 |
+
8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 models/InternVL3-8B-hf/merges.txt
|
| 36 |
+
7a34fa2f58c41aa1e6dbf28e9f4e43be590fb6077d33e4befe54a8413db03641 models/InternVL3-8B-hf/model-00001-of-00004.safetensors
|
| 37 |
+
11a0e1a80e29b9451771e03b9b2da118cfd8da0912631b6de0d4e1137f63dffc models/InternVL3-8B-hf/model-00002-of-00004.safetensors
|
| 38 |
+
8b578604029b9046396b61bf4ae223e0e85c9e89e138da067505bc6f7f9de921 models/InternVL3-8B-hf/model-00003-of-00004.safetensors
|
| 39 |
+
6814f162cc1ca061db92cb8808c7202876d8c1a56a0e7e856db12b21cba23a28 models/InternVL3-8B-hf/model-00004-of-00004.safetensors
|
| 40 |
+
5551d292e2be31ed9c4fd016d99389127e55a6f2316519c7621cd2fdd9b0dfd4 models/InternVL3-8B-hf/model.safetensors.index.json
|
| 41 |
+
af09ffbe57900d5ae07f93f4c20693559a272e32fa6c5f816132cb71985aac98 models/InternVL3-8B-hf/preprocessor_config.json
|
| 42 |
+
3511f4ae65c2fa5c1ab6a0fb2bb2fe767d6f0ee53ba412953b33acc892327c2a models/InternVL3-8B-hf/processor_config.json
|
| 43 |
+
e847a86633f2470a0d9fed41b5a36ff1f4435050929aa80b28c41d28420501b2 models/InternVL3-8B-hf/special_tokens_map.json
|
| 44 |
+
7cc80b7e20adf8bf6f6ca442bf1abfac8056bb3b7d3e0b11c9d497d3e79398c9 models/InternVL3-8B-hf/tokenizer.json
|
| 45 |
+
b336af8282760f5e596726eb9834ce20dd6625d55aa7df73030ef4c59028567f models/InternVL3-8B-hf/tokenizer_config.json
|
| 46 |
+
ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 models/InternVL3-8B-hf/vocab.json
|
models/FLARE-InternVL3-8B-hf/classification/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"self_attn.k_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"self_attn.q_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"self_attn.v_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/classification/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90f9852b491636ddd8a22414aee983cc4c13337296dcd70dca393a55e926abd6
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/counting/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"self_attn.q_proj",
|
| 30 |
+
"self_attn.v_proj",
|
| 31 |
+
"self_attn.k_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"up_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/counting/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01b448ea3f42491104e968dde4e0ed4d1085f8fcb80cd241a51eece620958724
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/detection/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"self_attn.k_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"self_attn.v_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"self_attn.q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/detection/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e005ac2b87807733a41dabf8821a19df6085d69ac06211e6d4e7911d97d93d9
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/instance_detection/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"self_attn.v_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"self_attn.q_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"self_attn.k_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"up_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/instance_detection/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22ead29cddbc78da63791447014ffb53e78cd590410f87b2b1228d0055f83636
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/internvl-all/lora/sft/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"o_proj",
|
| 28 |
+
"self_attn.q_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"self_attn.k_proj",
|
| 31 |
+
"self_attn.v_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/internvl-all/lora/sft/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:759e3b7853c054e699c2f80948bc374ac070ef4526c743e14512600a0bdd5f15
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/multi_label_binary_focal_v2_best/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"o_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"self_attn.q_proj",
|
| 30 |
+
"self_attn.k_proj",
|
| 31 |
+
"self_attn.v_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"up_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/multi_label_binary_focal_v2_best/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30d9bc38faddef85290850b9134163c5d56af07de6354059c89c5a9d1369a90d
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/multi_label_classification/adapter_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"vision_tower.encoder.layer.22.mlp.fc2",
|
| 28 |
+
"vision_tower.encoder.layer.21.attention.k_proj",
|
| 29 |
+
"vision_tower.encoder.layer.21.attention.projection_layer",
|
| 30 |
+
"vision_tower.encoder.layer.22.attention.v_proj",
|
| 31 |
+
"vision_tower.encoder.layer.20.attention.v_proj",
|
| 32 |
+
"vision_tower.encoder.layer.21.mlp.fc1",
|
| 33 |
+
"vision_tower.encoder.layer.20.mlp.fc2",
|
| 34 |
+
"up_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"vision_tower.encoder.layer.23.mlp.fc1",
|
| 37 |
+
"vision_tower.encoder.layer.22.attention.k_proj",
|
| 38 |
+
"vision_tower.encoder.layer.20.attention.k_proj",
|
| 39 |
+
"vision_tower.encoder.layer.20.attention.projection_layer",
|
| 40 |
+
"multi_modal_projector.linear_2",
|
| 41 |
+
"vision_tower.encoder.layer.21.attention.v_proj",
|
| 42 |
+
"vision_tower.encoder.layer.23.mlp.fc2",
|
| 43 |
+
"vision_tower.encoder.layer.22.attention.q_proj",
|
| 44 |
+
"self_attn.q_proj",
|
| 45 |
+
"vision_tower.encoder.layer.21.attention.q_proj",
|
| 46 |
+
"down_proj",
|
| 47 |
+
"vision_tower.encoder.layer.20.mlp.fc1",
|
| 48 |
+
"vision_tower.encoder.layer.22.attention.projection_layer",
|
| 49 |
+
"vision_tower.encoder.layer.20.attention.q_proj",
|
| 50 |
+
"vision_tower.encoder.layer.22.mlp.fc1",
|
| 51 |
+
"vision_tower.encoder.layer.21.mlp.fc2",
|
| 52 |
+
"vision_tower.encoder.layer.23.attention.q_proj",
|
| 53 |
+
"multi_modal_projector.linear_1",
|
| 54 |
+
"gate_proj",
|
| 55 |
+
"self_attn.v_proj",
|
| 56 |
+
"self_attn.k_proj",
|
| 57 |
+
"vision_tower.encoder.layer.23.attention.v_proj",
|
| 58 |
+
"vision_tower.encoder.layer.23.attention.projection_layer",
|
| 59 |
+
"vision_tower.encoder.layer.23.attention.k_proj"
|
| 60 |
+
],
|
| 61 |
+
"task_type": "CAUSAL_LM",
|
| 62 |
+
"trainable_token_indices": null,
|
| 63 |
+
"use_dora": false,
|
| 64 |
+
"use_rslora": false
|
| 65 |
+
}
|
models/FLARE-InternVL3-8B-hf/multi_label_classification/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:916027dd00c743aa4945fd611c8442e2c35dcee26a6c79f836eeb55a0eb91ce5
|
| 3 |
+
size 167215664
|
models/FLARE-InternVL3-8B-hf/multi_label_joint_linear/metadata.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"method": "frozen_internvl_shared_representation_seven_label_head",
|
| 3 |
+
"base_model": "InternVL3-8B",
|
| 4 |
+
"adapter": "multi_label_classification",
|
| 5 |
+
"train_jsonl": "FLARE 2026 periapical training split",
|
| 6 |
+
"holdout_json": "image-grouped periapical holdout split",
|
| 7 |
+
"samples": {
|
| 8 |
+
"train": 2604,
|
| 9 |
+
"holdout": 652
|
| 10 |
+
},
|
| 11 |
+
"unique_train_images": 1297,
|
| 12 |
+
"labels": [
|
| 13 |
+
"Dental Caries",
|
| 14 |
+
"Periradicular Lesions",
|
| 15 |
+
"Pulp Diseases",
|
| 16 |
+
"Chronic Injury of Tooth Hard Tissues",
|
| 17 |
+
"Disturbances of Eruption of Teeth",
|
| 18 |
+
"Periodontal Diseases",
|
| 19 |
+
"Endodontic Treatment, Restorative Treatment, and Complications"
|
| 20 |
+
],
|
| 21 |
+
"max_patches": 4,
|
| 22 |
+
"feature_dimension": 3584,
|
| 23 |
+
"folds": 5,
|
| 24 |
+
"candidates": [
|
| 25 |
+
{
|
| 26 |
+
"c": 0.01,
|
| 27 |
+
"class_weight": null,
|
| 28 |
+
"thresholds": [
|
| 29 |
+
0.33,
|
| 30 |
+
0.29000000000000004,
|
| 31 |
+
0.5,
|
| 32 |
+
0.15000000000000002,
|
| 33 |
+
0.1,
|
| 34 |
+
0.5,
|
| 35 |
+
0.6
|
| 36 |
+
],
|
| 37 |
+
"oof": {
|
| 38 |
+
"f1": 0.6059496567505721,
|
| 39 |
+
"precision": 0.5291766586730615,
|
| 40 |
+
"recall": 0.708779443254818,
|
| 41 |
+
"true_positive": 2648,
|
| 42 |
+
"false_positive": 2356,
|
| 43 |
+
"false_negative": 1088,
|
| 44 |
+
"predicted_cardinality": 1.9216589861751152
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"c": 0.01,
|
| 49 |
+
"class_weight": "balanced",
|
| 50 |
+
"thresholds": [
|
| 51 |
+
0.5,
|
| 52 |
+
0.5,
|
| 53 |
+
0.52,
|
| 54 |
+
0.51,
|
| 55 |
+
0.54,
|
| 56 |
+
0.51,
|
| 57 |
+
0.49
|
| 58 |
+
],
|
| 59 |
+
"oof": {
|
| 60 |
+
"f1": 0.6859103276943097,
|
| 61 |
+
"precision": 0.6145855416578334,
|
| 62 |
+
"recall": 0.7759635974304069,
|
| 63 |
+
"true_positive": 2899,
|
| 64 |
+
"false_positive": 1818,
|
| 65 |
+
"false_negative": 837,
|
| 66 |
+
"predicted_cardinality": 1.8114439324116745
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"c": 0.1,
|
| 71 |
+
"class_weight": null,
|
| 72 |
+
"thresholds": [
|
| 73 |
+
0.33999999999999997,
|
| 74 |
+
0.28,
|
| 75 |
+
0.5,
|
| 76 |
+
0.12000000000000001,
|
| 77 |
+
0.1,
|
| 78 |
+
0.5,
|
| 79 |
+
0.5700000000000001
|
| 80 |
+
],
|
| 81 |
+
"oof": {
|
| 82 |
+
"f1": 0.6764119601328904,
|
| 83 |
+
"precision": 0.6716811823700185,
|
| 84 |
+
"recall": 0.6812098501070664,
|
| 85 |
+
"true_positive": 2545,
|
| 86 |
+
"false_positive": 1244,
|
| 87 |
+
"false_negative": 1191,
|
| 88 |
+
"predicted_cardinality": 1.455069124423963
|
| 89 |
+
}
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"c": 0.1,
|
| 93 |
+
"class_weight": "balanced",
|
| 94 |
+
"thresholds": [
|
| 95 |
+
0.51,
|
| 96 |
+
0.51,
|
| 97 |
+
0.61,
|
| 98 |
+
0.55,
|
| 99 |
+
0.73,
|
| 100 |
+
0.5700000000000001,
|
| 101 |
+
0.45000000000000007
|
| 102 |
+
],
|
| 103 |
+
"oof": {
|
| 104 |
+
"f1": 0.7048732943469785,
|
| 105 |
+
"precision": 0.685021470068199,
|
| 106 |
+
"recall": 0.7259100642398287,
|
| 107 |
+
"true_positive": 2712,
|
| 108 |
+
"false_positive": 1247,
|
| 109 |
+
"false_negative": 1024,
|
| 110 |
+
"predicted_cardinality": 1.5203533026113671
|
| 111 |
+
}
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"c": 1.0,
|
| 115 |
+
"class_weight": null,
|
| 116 |
+
"thresholds": [
|
| 117 |
+
0.37,
|
| 118 |
+
0.30000000000000004,
|
| 119 |
+
0.12000000000000001,
|
| 120 |
+
0.19,
|
| 121 |
+
0.23,
|
| 122 |
+
0.5,
|
| 123 |
+
0.42000000000000004
|
| 124 |
+
],
|
| 125 |
+
"oof": {
|
| 126 |
+
"f1": 0.7074088490982224,
|
| 127 |
+
"precision": 0.686476957945102,
|
| 128 |
+
"recall": 0.7296573875802997,
|
| 129 |
+
"true_positive": 2726,
|
| 130 |
+
"false_positive": 1245,
|
| 131 |
+
"false_negative": 1010,
|
| 132 |
+
"predicted_cardinality": 1.5249615975422428
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"c": 1.0,
|
| 137 |
+
"class_weight": "balanced",
|
| 138 |
+
"thresholds": [
|
| 139 |
+
0.56,
|
| 140 |
+
0.54,
|
| 141 |
+
0.79,
|
| 142 |
+
0.74,
|
| 143 |
+
0.87,
|
| 144 |
+
0.74,
|
| 145 |
+
0.31
|
| 146 |
+
],
|
| 147 |
+
"oof": {
|
| 148 |
+
"f1": 0.7141917664079969,
|
| 149 |
+
"precision": 0.7020946470131885,
|
| 150 |
+
"recall": 0.7267130620985011,
|
| 151 |
+
"true_positive": 2715,
|
| 152 |
+
"false_positive": 1152,
|
| 153 |
+
"false_negative": 1021,
|
| 154 |
+
"predicted_cardinality": 1.4850230414746544
|
| 155 |
+
}
|
| 156 |
+
}
|
| 157 |
+
],
|
| 158 |
+
"selected": {
|
| 159 |
+
"c": 1.0,
|
| 160 |
+
"class_weight": "balanced",
|
| 161 |
+
"thresholds": [
|
| 162 |
+
0.56,
|
| 163 |
+
0.54,
|
| 164 |
+
0.79,
|
| 165 |
+
0.74,
|
| 166 |
+
0.87,
|
| 167 |
+
0.74,
|
| 168 |
+
0.31
|
| 169 |
+
],
|
| 170 |
+
"oof": {
|
| 171 |
+
"f1": 0.7141917664079969,
|
| 172 |
+
"precision": 0.7020946470131885,
|
| 173 |
+
"recall": 0.7267130620985011,
|
| 174 |
+
"true_positive": 2715,
|
| 175 |
+
"false_positive": 1152,
|
| 176 |
+
"false_negative": 1021,
|
| 177 |
+
"predicted_cardinality": 1.4850230414746544
|
| 178 |
+
}
|
| 179 |
+
},
|
| 180 |
+
"holdout": {
|
| 181 |
+
"f1": 0.7205493924986793,
|
| 182 |
+
"precision": 0.7111574556830031,
|
| 183 |
+
"recall": 0.7301927194860813,
|
| 184 |
+
"true_positive": 682,
|
| 185 |
+
"false_positive": 277,
|
| 186 |
+
"false_negative": 252,
|
| 187 |
+
"predicted_cardinality": 1.4708588957055215
|
| 188 |
+
}
|
| 189 |
+
}
|
models/FLARE-InternVL3-8B-hf/multi_label_joint_mlp/head.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a84cf3446250edaf5c2903278b1991fff4f9b5ba57d48b1603d1539c076344b
|
| 3 |
+
size 3428239
|
models/FLARE-InternVL3-8B-hf/multi_label_joint_mlp/metadata.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"method": "frozen_internvl_nonlinear_joint_seven_label_head",
|
| 3 |
+
"labels": [
|
| 4 |
+
"Dental Caries",
|
| 5 |
+
"Periradicular Lesions",
|
| 6 |
+
"Pulp Diseases",
|
| 7 |
+
"Chronic Injury of Tooth Hard Tissues",
|
| 8 |
+
"Disturbances of Eruption of Teeth",
|
| 9 |
+
"Periodontal Diseases",
|
| 10 |
+
"Endodontic Treatment, Restorative Treatment, and Complications"
|
| 11 |
+
],
|
| 12 |
+
"samples": {
|
| 13 |
+
"train": 2604,
|
| 14 |
+
"holdout": 652
|
| 15 |
+
},
|
| 16 |
+
"unique_train_images": 1297,
|
| 17 |
+
"folds": 3,
|
| 18 |
+
"candidates": [
|
| 19 |
+
{
|
| 20 |
+
"name": "bce_h128",
|
| 21 |
+
"hidden_size": 128,
|
| 22 |
+
"dropout": 0.2,
|
| 23 |
+
"learning_rate": 0.0003,
|
| 24 |
+
"loss": "bce",
|
| 25 |
+
"gamma_negative": 0.0,
|
| 26 |
+
"best_epochs": [
|
| 27 |
+
11,
|
| 28 |
+
50,
|
| 29 |
+
32
|
| 30 |
+
],
|
| 31 |
+
"final_epochs": 32,
|
| 32 |
+
"thresholds": [
|
| 33 |
+
0.33,
|
| 34 |
+
0.39,
|
| 35 |
+
0.30000000000000004,
|
| 36 |
+
0.39,
|
| 37 |
+
0.5700000000000001,
|
| 38 |
+
0.49,
|
| 39 |
+
0.36
|
| 40 |
+
],
|
| 41 |
+
"oof": {
|
| 42 |
+
"f1": 0.7204030226700252,
|
| 43 |
+
"precision": 0.7136853165221959,
|
| 44 |
+
"recall": 0.7272483940042827,
|
| 45 |
+
"true_positive": 2717,
|
| 46 |
+
"false_positive": 1090,
|
| 47 |
+
"false_negative": 1019,
|
| 48 |
+
"predicted_cardinality": 1.4619815668202765
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"name": "bce_h256",
|
| 53 |
+
"hidden_size": 256,
|
| 54 |
+
"dropout": 0.3,
|
| 55 |
+
"learning_rate": 0.0003,
|
| 56 |
+
"loss": "bce",
|
| 57 |
+
"gamma_negative": 0.0,
|
| 58 |
+
"best_epochs": [
|
| 59 |
+
37,
|
| 60 |
+
29,
|
| 61 |
+
48
|
| 62 |
+
],
|
| 63 |
+
"final_epochs": 37,
|
| 64 |
+
"thresholds": [
|
| 65 |
+
0.41000000000000003,
|
| 66 |
+
0.4,
|
| 67 |
+
0.32,
|
| 68 |
+
0.41000000000000003,
|
| 69 |
+
0.53,
|
| 70 |
+
0.23,
|
| 71 |
+
0.29000000000000004
|
| 72 |
+
],
|
| 73 |
+
"oof": {
|
| 74 |
+
"f1": 0.7249056112485354,
|
| 75 |
+
"precision": 0.7057034220532319,
|
| 76 |
+
"recall": 0.7451820128479657,
|
| 77 |
+
"true_positive": 2784,
|
| 78 |
+
"false_positive": 1161,
|
| 79 |
+
"false_negative": 952,
|
| 80 |
+
"predicted_cardinality": 1.5149769585253456
|
| 81 |
+
}
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"name": "asl2_h128",
|
| 85 |
+
"hidden_size": 128,
|
| 86 |
+
"dropout": 0.2,
|
| 87 |
+
"learning_rate": 0.0003,
|
| 88 |
+
"loss": "asymmetric",
|
| 89 |
+
"gamma_negative": 2.0,
|
| 90 |
+
"best_epochs": [
|
| 91 |
+
31,
|
| 92 |
+
25,
|
| 93 |
+
26
|
| 94 |
+
],
|
| 95 |
+
"final_epochs": 26,
|
| 96 |
+
"thresholds": [
|
| 97 |
+
0.5,
|
| 98 |
+
0.5,
|
| 99 |
+
0.5,
|
| 100 |
+
0.52,
|
| 101 |
+
0.55,
|
| 102 |
+
0.5,
|
| 103 |
+
0.5
|
| 104 |
+
],
|
| 105 |
+
"oof": {
|
| 106 |
+
"f1": 0.7227284561312158,
|
| 107 |
+
"precision": 0.7034972123669538,
|
| 108 |
+
"recall": 0.7430406852248393,
|
| 109 |
+
"true_positive": 2776,
|
| 110 |
+
"false_positive": 1170,
|
| 111 |
+
"false_negative": 960,
|
| 112 |
+
"predicted_cardinality": 1.5153609831029187
|
| 113 |
+
}
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"name": "asl4_h256",
|
| 117 |
+
"hidden_size": 256,
|
| 118 |
+
"dropout": 0.3,
|
| 119 |
+
"learning_rate": 0.0003,
|
| 120 |
+
"loss": "asymmetric",
|
| 121 |
+
"gamma_negative": 4.0,
|
| 122 |
+
"best_epochs": [
|
| 123 |
+
28,
|
| 124 |
+
26,
|
| 125 |
+
11
|
| 126 |
+
],
|
| 127 |
+
"final_epochs": 26,
|
| 128 |
+
"thresholds": [
|
| 129 |
+
0.59,
|
| 130 |
+
0.54,
|
| 131 |
+
0.54,
|
| 132 |
+
0.61,
|
| 133 |
+
0.66,
|
| 134 |
+
0.54,
|
| 135 |
+
0.5700000000000001
|
| 136 |
+
],
|
| 137 |
+
"oof": {
|
| 138 |
+
"f1": 0.719291389865833,
|
| 139 |
+
"precision": 0.7005836082212636,
|
| 140 |
+
"recall": 0.7390256959314775,
|
| 141 |
+
"true_positive": 2761,
|
| 142 |
+
"false_positive": 1180,
|
| 143 |
+
"false_negative": 975,
|
| 144 |
+
"predicted_cardinality": 1.5134408602150538
|
| 145 |
+
}
|
| 146 |
+
}
|
| 147 |
+
],
|
| 148 |
+
"selected": {
|
| 149 |
+
"name": "bce_h256",
|
| 150 |
+
"hidden_size": 256,
|
| 151 |
+
"dropout": 0.3,
|
| 152 |
+
"learning_rate": 0.0003,
|
| 153 |
+
"loss": "bce",
|
| 154 |
+
"gamma_negative": 0.0,
|
| 155 |
+
"best_epochs": [
|
| 156 |
+
37,
|
| 157 |
+
29,
|
| 158 |
+
48
|
| 159 |
+
],
|
| 160 |
+
"final_epochs": 37,
|
| 161 |
+
"thresholds": [
|
| 162 |
+
0.41000000000000003,
|
| 163 |
+
0.4,
|
| 164 |
+
0.32,
|
| 165 |
+
0.41000000000000003,
|
| 166 |
+
0.53,
|
| 167 |
+
0.23,
|
| 168 |
+
0.29000000000000004
|
| 169 |
+
],
|
| 170 |
+
"oof": {
|
| 171 |
+
"f1": 0.7249056112485354,
|
| 172 |
+
"precision": 0.7057034220532319,
|
| 173 |
+
"recall": 0.7451820128479657,
|
| 174 |
+
"true_positive": 2784,
|
| 175 |
+
"false_positive": 1161,
|
| 176 |
+
"false_negative": 952,
|
| 177 |
+
"predicted_cardinality": 1.5149769585253456
|
| 178 |
+
}
|
| 179 |
+
},
|
| 180 |
+
"holdout": {
|
| 181 |
+
"f1": 0.7288135593220338,
|
| 182 |
+
"precision": 0.7211740041928721,
|
| 183 |
+
"recall": 0.7366167023554604,
|
| 184 |
+
"true_positive": 688,
|
| 185 |
+
"false_positive": 266,
|
| 186 |
+
"false_negative": 246,
|
| 187 |
+
"predicted_cardinality": 1.4631901840490797
|
| 188 |
+
}
|
| 189 |
+
}
|
models/FLARE-InternVL3-8B-hf/regression/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"o_proj",
|
| 28 |
+
"self_attn.v_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"self_attn.k_proj",
|
| 33 |
+
"self_attn.q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/regression/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b538b46ea37a3fb145e3ca7c24d41b439d189ae15bf986cb7d75d17556814d83
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/report_generation/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"self_attn.v_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"self_attn.k_proj",
|
| 32 |
+
"up_proj",
|
| 33 |
+
"self_attn.q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/report_generation/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cb69a952b13efa953ce7894cedb81984cdb63516f4dfb5c8079a2dc54ebfe5a
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/source_classification/bone_marrow_feature_head/metadata.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"method": "class_balanced_multinomial_head_over_frozen_internvl_features",
|
| 3 |
+
"labels": [
|
| 4 |
+
"A",
|
| 5 |
+
"B",
|
| 6 |
+
"C",
|
| 7 |
+
"D",
|
| 8 |
+
"E",
|
| 9 |
+
"F",
|
| 10 |
+
"G",
|
| 11 |
+
"H",
|
| 12 |
+
"I",
|
| 13 |
+
"J",
|
| 14 |
+
"K"
|
| 15 |
+
],
|
| 16 |
+
"samples": {
|
| 17 |
+
"train": 578,
|
| 18 |
+
"holdout": 144
|
| 19 |
+
},
|
| 20 |
+
"folds": 5,
|
| 21 |
+
"candidates": [
|
| 22 |
+
{
|
| 23 |
+
"c": 0.001,
|
| 24 |
+
"oof": {
|
| 25 |
+
"balanced_accuracy": 0.6301208903491365,
|
| 26 |
+
"exact_accuracy": 0.6453287197231834,
|
| 27 |
+
"per_class_recall": {
|
| 28 |
+
"A": 0.4,
|
| 29 |
+
"B": 0.9473684210526315,
|
| 30 |
+
"C": 0.3584905660377358,
|
| 31 |
+
"D": 0.27586206896551724,
|
| 32 |
+
"E": 1.0,
|
| 33 |
+
"F": 0.7454545454545455,
|
| 34 |
+
"G": 0.9830508474576272,
|
| 35 |
+
"H": 0.35714285714285715,
|
| 36 |
+
"I": 0.7894736842105263,
|
| 37 |
+
"J": 0.12903225806451613,
|
| 38 |
+
"K": 0.9454545454545454
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"holdout": {
|
| 42 |
+
"balanced_accuracy": 0.6686813186813187,
|
| 43 |
+
"exact_accuracy": 0.6736111111111112,
|
| 44 |
+
"per_class_recall": {
|
| 45 |
+
"A": 0.6666666666666666,
|
| 46 |
+
"B": 0.9375,
|
| 47 |
+
"C": 0.07692307692307693,
|
| 48 |
+
"D": 0.25,
|
| 49 |
+
"E": 1.0,
|
| 50 |
+
"F": 0.9333333333333333,
|
| 51 |
+
"G": 1.0,
|
| 52 |
+
"H": 0.5,
|
| 53 |
+
"I": 0.9285714285714286,
|
| 54 |
+
"J": 0.0625,
|
| 55 |
+
"K": 1.0
|
| 56 |
+
}
|
| 57 |
+
}
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"c": 0.01,
|
| 61 |
+
"oof": {
|
| 62 |
+
"balanced_accuracy": 0.6301473529147841,
|
| 63 |
+
"exact_accuracy": 0.6453287197231834,
|
| 64 |
+
"per_class_recall": {
|
| 65 |
+
"A": 0.4,
|
| 66 |
+
"B": 0.9473684210526315,
|
| 67 |
+
"C": 0.3584905660377358,
|
| 68 |
+
"D": 0.25862068965517243,
|
| 69 |
+
"E": 1.0,
|
| 70 |
+
"F": 0.7272727272727273,
|
| 71 |
+
"G": 0.9830508474576272,
|
| 72 |
+
"H": 0.39285714285714285,
|
| 73 |
+
"I": 0.7894736842105263,
|
| 74 |
+
"J": 0.12903225806451613,
|
| 75 |
+
"K": 0.9454545454545454
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"holdout": {
|
| 79 |
+
"balanced_accuracy": 0.6686813186813187,
|
| 80 |
+
"exact_accuracy": 0.6736111111111112,
|
| 81 |
+
"per_class_recall": {
|
| 82 |
+
"A": 0.6666666666666666,
|
| 83 |
+
"B": 0.9375,
|
| 84 |
+
"C": 0.07692307692307693,
|
| 85 |
+
"D": 0.25,
|
| 86 |
+
"E": 1.0,
|
| 87 |
+
"F": 0.9333333333333333,
|
| 88 |
+
"G": 1.0,
|
| 89 |
+
"H": 0.5,
|
| 90 |
+
"I": 0.9285714285714286,
|
| 91 |
+
"J": 0.0625,
|
| 92 |
+
"K": 1.0
|
| 93 |
+
}
|
| 94 |
+
}
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"c": 0.1,
|
| 98 |
+
"oof": {
|
| 99 |
+
"balanced_accuracy": 0.6774411054754033,
|
| 100 |
+
"exact_accuracy": 0.6972318339100346,
|
| 101 |
+
"per_class_recall": {
|
| 102 |
+
"A": 0.4,
|
| 103 |
+
"B": 0.9473684210526315,
|
| 104 |
+
"C": 0.4339622641509434,
|
| 105 |
+
"D": 0.41379310344827586,
|
| 106 |
+
"E": 1.0,
|
| 107 |
+
"F": 0.7818181818181819,
|
| 108 |
+
"G": 0.9661016949152542,
|
| 109 |
+
"H": 0.48214285714285715,
|
| 110 |
+
"I": 0.8070175438596491,
|
| 111 |
+
"J": 0.27419354838709675,
|
| 112 |
+
"K": 0.9454545454545454
|
| 113 |
+
}
|
| 114 |
+
},
|
| 115 |
+
"holdout": {
|
| 116 |
+
"balanced_accuracy": 0.6916083916083916,
|
| 117 |
+
"exact_accuracy": 0.7013888888888888,
|
| 118 |
+
"per_class_recall": {
|
| 119 |
+
"A": 0.6666666666666666,
|
| 120 |
+
"B": 0.9375,
|
| 121 |
+
"C": 0.3076923076923077,
|
| 122 |
+
"D": 0.25,
|
| 123 |
+
"E": 1.0,
|
| 124 |
+
"F": 0.8,
|
| 125 |
+
"G": 0.8333333333333334,
|
| 126 |
+
"H": 0.5714285714285714,
|
| 127 |
+
"I": 0.9285714285714286,
|
| 128 |
+
"J": 0.3125,
|
| 129 |
+
"K": 1.0
|
| 130 |
+
}
|
| 131 |
+
}
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"c": 1.0,
|
| 135 |
+
"oof": {
|
| 136 |
+
"balanced_accuracy": 0.7851868293966185,
|
| 137 |
+
"exact_accuracy": 0.801038062283737,
|
| 138 |
+
"per_class_recall": {
|
| 139 |
+
"A": 0.6,
|
| 140 |
+
"B": 0.9298245614035088,
|
| 141 |
+
"C": 0.5849056603773585,
|
| 142 |
+
"D": 0.6724137931034483,
|
| 143 |
+
"E": 0.9642857142857143,
|
| 144 |
+
"F": 0.7272727272727273,
|
| 145 |
+
"G": 0.9661016949152542,
|
| 146 |
+
"H": 0.6964285714285714,
|
| 147 |
+
"I": 0.8245614035087719,
|
| 148 |
+
"J": 0.7258064516129032,
|
| 149 |
+
"K": 0.9454545454545454
|
| 150 |
+
}
|
| 151 |
+
},
|
| 152 |
+
"holdout": {
|
| 153 |
+
"balanced_accuracy": 0.7295662670662671,
|
| 154 |
+
"exact_accuracy": 0.7708333333333334,
|
| 155 |
+
"per_class_recall": {
|
| 156 |
+
"A": 0.3333333333333333,
|
| 157 |
+
"B": 0.9375,
|
| 158 |
+
"C": 0.46153846153846156,
|
| 159 |
+
"D": 0.3333333333333333,
|
| 160 |
+
"E": 1.0,
|
| 161 |
+
"F": 0.7333333333333333,
|
| 162 |
+
"G": 0.8333333333333334,
|
| 163 |
+
"H": 0.7142857142857143,
|
| 164 |
+
"I": 0.9285714285714286,
|
| 165 |
+
"J": 0.75,
|
| 166 |
+
"K": 1.0
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"c": 10.0,
|
| 172 |
+
"oof": {
|
| 173 |
+
"balanced_accuracy": 0.838462112166659,
|
| 174 |
+
"exact_accuracy": 0.8581314878892734,
|
| 175 |
+
"per_class_recall": {
|
| 176 |
+
"A": 0.6,
|
| 177 |
+
"B": 0.9298245614035088,
|
| 178 |
+
"C": 0.6792452830188679,
|
| 179 |
+
"D": 0.7758620689655172,
|
| 180 |
+
"E": 0.9642857142857143,
|
| 181 |
+
"F": 0.8909090909090909,
|
| 182 |
+
"G": 0.9661016949152542,
|
| 183 |
+
"H": 0.8214285714285714,
|
| 184 |
+
"I": 0.8596491228070176,
|
| 185 |
+
"J": 0.7903225806451613,
|
| 186 |
+
"K": 0.9454545454545454
|
| 187 |
+
}
|
| 188 |
+
},
|
| 189 |
+
"holdout": {
|
| 190 |
+
"balanced_accuracy": 0.7970404595404595,
|
| 191 |
+
"exact_accuracy": 0.8402777777777778,
|
| 192 |
+
"per_class_recall": {
|
| 193 |
+
"A": 0.3333333333333333,
|
| 194 |
+
"B": 0.9375,
|
| 195 |
+
"C": 0.7692307692307693,
|
| 196 |
+
"D": 0.5,
|
| 197 |
+
"E": 1.0,
|
| 198 |
+
"F": 0.7333333333333333,
|
| 199 |
+
"G": 0.8333333333333334,
|
| 200 |
+
"H": 0.7857142857142857,
|
| 201 |
+
"I": 1.0,
|
| 202 |
+
"J": 0.875,
|
| 203 |
+
"K": 1.0
|
| 204 |
+
}
|
| 205 |
+
}
|
| 206 |
+
}
|
| 207 |
+
],
|
| 208 |
+
"selected": {
|
| 209 |
+
"c": 10.0,
|
| 210 |
+
"oof": {
|
| 211 |
+
"balanced_accuracy": 0.838462112166659,
|
| 212 |
+
"exact_accuracy": 0.8581314878892734,
|
| 213 |
+
"per_class_recall": {
|
| 214 |
+
"A": 0.6,
|
| 215 |
+
"B": 0.9298245614035088,
|
| 216 |
+
"C": 0.6792452830188679,
|
| 217 |
+
"D": 0.7758620689655172,
|
| 218 |
+
"E": 0.9642857142857143,
|
| 219 |
+
"F": 0.8909090909090909,
|
| 220 |
+
"G": 0.9661016949152542,
|
| 221 |
+
"H": 0.8214285714285714,
|
| 222 |
+
"I": 0.8596491228070176,
|
| 223 |
+
"J": 0.7903225806451613,
|
| 224 |
+
"K": 0.9454545454545454
|
| 225 |
+
}
|
| 226 |
+
},
|
| 227 |
+
"holdout": {
|
| 228 |
+
"balanced_accuracy": 0.7970404595404595,
|
| 229 |
+
"exact_accuracy": 0.8402777777777778,
|
| 230 |
+
"per_class_recall": {
|
| 231 |
+
"A": 0.3333333333333333,
|
| 232 |
+
"B": 0.9375,
|
| 233 |
+
"C": 0.7692307692307693,
|
| 234 |
+
"D": 0.5,
|
| 235 |
+
"E": 1.0,
|
| 236 |
+
"F": 0.7333333333333333,
|
| 237 |
+
"G": 0.8333333333333334,
|
| 238 |
+
"H": 0.7857142857142857,
|
| 239 |
+
"I": 1.0,
|
| 240 |
+
"J": 0.875,
|
| 241 |
+
"K": 1.0
|
| 242 |
+
}
|
| 243 |
+
}
|
| 244 |
+
},
|
| 245 |
+
"final_fit_samples": 722
|
| 246 |
+
}
|
models/FLARE-InternVL3-8B-hf/source_classification/dental/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"self_attn.q_proj",
|
| 29 |
+
"self_attn.k_proj",
|
| 30 |
+
"self_attn.v_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"up_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/source_classification/fundus/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "OpenGVLab/InternVL3-8B-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"self_attn.v_proj",
|
| 28 |
+
"self_attn.k_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"self_attn.q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
models/FLARE-InternVL3-8B-hf/source_classification/fundus/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97f2c8feae51a52b23810a0dc0b861bb636a7be840ee629f1d1c9fae87f89cb3
|
| 3 |
+
size 80797976
|
models/FLARE-InternVL3-8B-hf/source_classification/selection.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metric": "balanced_accuracy",
|
| 3 |
+
"selection_policy": "Enable only when tuned adapted holdout accuracy exceeds tuned generic holdout accuracy.",
|
| 4 |
+
"sources": {
|
| 5 |
+
"fundus": {
|
| 6 |
+
"enabled": true,
|
| 7 |
+
"selected_checkpoint": "training/classification/fundus",
|
| 8 |
+
"prior_strength": -0.35,
|
| 9 |
+
"generic_balanced_accuracy": 0.866923076923077,
|
| 10 |
+
"adapted_balanced_accuracy": 0.8793101343101343,
|
| 11 |
+
"source_priors": {
|
| 12 |
+
"a": 0.20108205590622183,
|
| 13 |
+
"b": 0.25788999098286747,
|
| 14 |
+
"c": 0.23715058611361586,
|
| 15 |
+
"d": 0.07484220018034266,
|
| 16 |
+
"e": 0.2290351668169522
|
| 17 |
+
}
|
| 18 |
+
},
|
| 19 |
+
"bone_marrow": {
|
| 20 |
+
"enabled": false,
|
| 21 |
+
"generic_balanced_accuracy": 0.7664252414252414,
|
| 22 |
+
"best_adapted_balanced_accuracy": 0.721432733932734,
|
| 23 |
+
"best_adapted_checkpoint": 50
|
| 24 |
+
},
|
| 25 |
+
"iugc": {
|
| 26 |
+
"enabled": false,
|
| 27 |
+
"generic_balanced_accuracy": 0.9937106918238994,
|
| 28 |
+
"best_adapted_balanced_accuracy": 0.9905660377358491
|
| 29 |
+
},
|
| 30 |
+
"dental": {
|
| 31 |
+
"enabled": true,
|
| 32 |
+
"selected_checkpoint": "training/classification/dental/checkpoint-600",
|
| 33 |
+
"prior_strength": 0.75,
|
| 34 |
+
"generic_balanced_accuracy": 0.8892946937854443,
|
| 35 |
+
"checkpoint_400_balanced_accuracy": 0.9056199675822011,
|
| 36 |
+
"adapted_balanced_accuracy": 0.9071861693795303,
|
| 37 |
+
"source_priors": {
|
| 38 |
+
"a": 0.386417556346382,
|
| 39 |
+
"b": 0.3125741399762752,
|
| 40 |
+
"c": 0.18623962040332148,
|
| 41 |
+
"d": 0.006227758007117438,
|
| 42 |
+
"e": 0.003262158956109134,
|
| 43 |
+
"f": 0.10527876631079477
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
}
|
| 47 |
+
}
|
models/FLARE-InternVL3-8B-hf/source_classification/template_routes.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"method": "disabled_after_v4_hidden_leaderboard_regression",
|
| 3 |
+
"sources": {}
|
| 4 |
+
}
|
models/InternVL3-8B-hf/added_tokens.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</box>": 151673,
|
| 3 |
+
"</img>": 151666,
|
| 4 |
+
"</quad>": 151669,
|
| 5 |
+
"</ref>": 151671,
|
| 6 |
+
"</tool_call>": 151658,
|
| 7 |
+
"<IMG_CONTEXT>": 151667,
|
| 8 |
+
"<box>": 151672,
|
| 9 |
+
"<img>": 151665,
|
| 10 |
+
"<quad>": 151668,
|
| 11 |
+
"<ref>": 151670,
|
| 12 |
+
"<tool_call>": 151657,
|
| 13 |
+
"<video>": 151674,
|
| 14 |
+
"<|box_end|>": 151649,
|
| 15 |
+
"<|box_start|>": 151648,
|
| 16 |
+
"<|endoftext|>": 151643,
|
| 17 |
+
"<|file_sep|>": 151664,
|
| 18 |
+
"<|fim_middle|>": 151660,
|
| 19 |
+
"<|fim_pad|>": 151662,
|
| 20 |
+
"<|fim_prefix|>": 151659,
|
| 21 |
+
"<|fim_suffix|>": 151661,
|
| 22 |
+
"<|im_end|>": 151645,
|
| 23 |
+
"<|im_start|>": 151644,
|
| 24 |
+
"<|image_pad|>": 151655,
|
| 25 |
+
"<|object_ref_end|>": 151647,
|
| 26 |
+
"<|object_ref_start|>": 151646,
|
| 27 |
+
"<|quad_end|>": 151651,
|
| 28 |
+
"<|quad_start|>": 151650,
|
| 29 |
+
"<|repo_name|>": 151663,
|
| 30 |
+
"<|video_pad|>": 151656,
|
| 31 |
+
"<|vision_end|>": 151653,
|
| 32 |
+
"<|vision_pad|>": 151654,
|
| 33 |
+
"<|vision_start|>": 151652
|
| 34 |
+
}
|
models/InternVL3-8B-hf/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
|
| 3 |
+
' }}{% elif content['type'] == 'video' %}{{ '<video>
|
| 4 |
+
' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
models/InternVL3-8B-hf/config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"InternVLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"downsample_ratio": 0.5,
|
| 6 |
+
"image_seq_length": 256,
|
| 7 |
+
"image_token_id": 151667,
|
| 8 |
+
"model_type": "internvl",
|
| 9 |
+
"projector_hidden_act": "gelu",
|
| 10 |
+
"text_config": {
|
| 11 |
+
"architectures": [
|
| 12 |
+
"Qwen2ForCausalLM"
|
| 13 |
+
],
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"bos_token_id": 151643,
|
| 16 |
+
"eos_token_id": 151645,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 3584,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 18944,
|
| 21 |
+
"max_position_embeddings": 32768,
|
| 22 |
+
"max_window_layers": 70,
|
| 23 |
+
"model_type": "qwen2",
|
| 24 |
+
"num_attention_heads": 28,
|
| 25 |
+
"num_hidden_layers": 28,
|
| 26 |
+
"num_key_value_heads": 4,
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_scaling": {
|
| 29 |
+
"factor": 2.0,
|
| 30 |
+
"rope_type": "dynamic",
|
| 31 |
+
"type": "dynamic"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 1000000.0,
|
| 34 |
+
"sliding_window": null,
|
| 35 |
+
"torch_dtype": "bfloat16",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"use_sliding_window": false,
|
| 38 |
+
"vocab_size": 151674
|
| 39 |
+
},
|
| 40 |
+
"torch_dtype": "bfloat16",
|
| 41 |
+
"transformers_version": "4.52.0.dev0",
|
| 42 |
+
"vision_config": {
|
| 43 |
+
"architectures": [
|
| 44 |
+
"InternVisionModel"
|
| 45 |
+
],
|
| 46 |
+
"attention_bias": true,
|
| 47 |
+
"attention_dropout": 0.0,
|
| 48 |
+
"dropout": 0.0,
|
| 49 |
+
"hidden_act": "gelu",
|
| 50 |
+
"hidden_dropout_prob": 0.0,
|
| 51 |
+
"hidden_size": 1024,
|
| 52 |
+
"image_size": [
|
| 53 |
+
448,
|
| 54 |
+
448
|
| 55 |
+
],
|
| 56 |
+
"initializer_factor": 0.1,
|
| 57 |
+
"initializer_range": 1e-10,
|
| 58 |
+
"intermediate_size": 4096,
|
| 59 |
+
"layer_norm_eps": 1e-06,
|
| 60 |
+
"layer_scale_init_value": 0.1,
|
| 61 |
+
"model_type": "internvl_vision",
|
| 62 |
+
"norm_type": "layer_norm",
|
| 63 |
+
"num_attention_heads": 16,
|
| 64 |
+
"num_channels": 3,
|
| 65 |
+
"num_hidden_layers": 24,
|
| 66 |
+
"patch_size": [
|
| 67 |
+
14,
|
| 68 |
+
14
|
| 69 |
+
],
|
| 70 |
+
"projection_dropout": 0.0,
|
| 71 |
+
"torch_dtype": "bfloat16",
|
| 72 |
+
"use_absolute_position_embeddings": true,
|
| 73 |
+
"use_mask_token": false,
|
| 74 |
+
"use_mean_pooling": true,
|
| 75 |
+
"use_qk_norm": false
|
| 76 |
+
},
|
| 77 |
+
"vision_feature_layer": -1,
|
| 78 |
+
"vision_feature_select_strategy": "default"
|
| 79 |
+
}
|
models/InternVL3-8B-hf/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "4.52.0.dev0"
|
| 6 |
+
}
|
models/InternVL3-8B-hf/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models/InternVL3-8B-hf/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a34fa2f58c41aa1e6dbf28e9f4e43be590fb6077d33e4befe54a8413db03641
|
| 3 |
+
size 4877374576
|
models/InternVL3-8B-hf/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11a0e1a80e29b9451771e03b9b2da118cfd8da0912631b6de0d4e1137f63dffc
|
| 3 |
+
size 4991497800
|
models/InternVL3-8B-hf/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b578604029b9046396b61bf4ae223e0e85c9e89e138da067505bc6f7f9de921
|
| 3 |
+
size 4932774744
|
models/InternVL3-8B-hf/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6814f162cc1ca061db92cb8808c7202876d8c1a56a0e7e856db12b21cba23a28
|
| 3 |
+
size 1087199376
|
models/InternVL3-8B-hf/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,788 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 15888747520
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"language_model.lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 14 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 17 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 19 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 26 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 29 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 31 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 38 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 41 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 43 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 50 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 53 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 55 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 62 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 65 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 67 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 74 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 77 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 79 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 86 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 89 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 91 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 98 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 101 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 103 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 110 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 113 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 115 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 117 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 122 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 125 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 127 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 134 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 137 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 139 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 146 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 149 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 151 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 158 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 159 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 161 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
+
"language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 163 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 164 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 170 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 173 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 175 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 182 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 185 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 187 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 194 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 197 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 199 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 206 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 209 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 211 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 218 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 221 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 223 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 230 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 233 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 235 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 242 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 245 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 247 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 254 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 257 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 259 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 266 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 269 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 271 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 278 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 281 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 283 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 290 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 291 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 293 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 294 |
+
"language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 295 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 296 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 297 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 302 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 303 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 305 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 306 |
+
"language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 307 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 308 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 312 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 314 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 317 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 319 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 326 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 328 |
+
"language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 329 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 330 |
+
"language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 331 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 332 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 333 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 338 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 339 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 341 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 342 |
+
"language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 343 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 344 |
+
"language_model.model.norm.weight": "model-00003-of-00004.safetensors",
|
| 345 |
+
"multi_modal_projector.layer_norm.bias": "model-00001-of-00004.safetensors",
|
| 346 |
+
"multi_modal_projector.layer_norm.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
|
| 348 |
+
"multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
|
| 350 |
+
"multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"vision_tower.embeddings.cls_token": "model-00001-of-00004.safetensors",
|
| 352 |
+
"vision_tower.embeddings.patch_embeddings.projection.bias": "model-00001-of-00004.safetensors",
|
| 353 |
+
"vision_tower.embeddings.patch_embeddings.projection.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"vision_tower.embeddings.position_embeddings": "model-00001-of-00004.safetensors",
|
| 355 |
+
"vision_tower.encoder.layer.0.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 356 |
+
"vision_tower.encoder.layer.0.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"vision_tower.encoder.layer.0.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 358 |
+
"vision_tower.encoder.layer.0.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"vision_tower.encoder.layer.0.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 360 |
+
"vision_tower.encoder.layer.0.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"vision_tower.encoder.layer.0.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 362 |
+
"vision_tower.encoder.layer.0.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"vision_tower.encoder.layer.0.lambda_1": "model-00001-of-00004.safetensors",
|
| 364 |
+
"vision_tower.encoder.layer.0.lambda_2": "model-00001-of-00004.safetensors",
|
| 365 |
+
"vision_tower.encoder.layer.0.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 366 |
+
"vision_tower.encoder.layer.0.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"vision_tower.encoder.layer.0.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 368 |
+
"vision_tower.encoder.layer.0.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"vision_tower.encoder.layer.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 370 |
+
"vision_tower.encoder.layer.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"vision_tower.encoder.layer.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 372 |
+
"vision_tower.encoder.layer.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"vision_tower.encoder.layer.1.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 374 |
+
"vision_tower.encoder.layer.1.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"vision_tower.encoder.layer.1.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 376 |
+
"vision_tower.encoder.layer.1.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"vision_tower.encoder.layer.1.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 378 |
+
"vision_tower.encoder.layer.1.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"vision_tower.encoder.layer.1.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 380 |
+
"vision_tower.encoder.layer.1.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"vision_tower.encoder.layer.1.lambda_1": "model-00001-of-00004.safetensors",
|
| 382 |
+
"vision_tower.encoder.layer.1.lambda_2": "model-00001-of-00004.safetensors",
|
| 383 |
+
"vision_tower.encoder.layer.1.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 384 |
+
"vision_tower.encoder.layer.1.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"vision_tower.encoder.layer.1.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 386 |
+
"vision_tower.encoder.layer.1.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"vision_tower.encoder.layer.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 388 |
+
"vision_tower.encoder.layer.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"vision_tower.encoder.layer.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 390 |
+
"vision_tower.encoder.layer.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"vision_tower.encoder.layer.10.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 392 |
+
"vision_tower.encoder.layer.10.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"vision_tower.encoder.layer.10.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 394 |
+
"vision_tower.encoder.layer.10.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"vision_tower.encoder.layer.10.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 396 |
+
"vision_tower.encoder.layer.10.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"vision_tower.encoder.layer.10.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 398 |
+
"vision_tower.encoder.layer.10.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"vision_tower.encoder.layer.10.lambda_1": "model-00001-of-00004.safetensors",
|
| 400 |
+
"vision_tower.encoder.layer.10.lambda_2": "model-00001-of-00004.safetensors",
|
| 401 |
+
"vision_tower.encoder.layer.10.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 402 |
+
"vision_tower.encoder.layer.10.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"vision_tower.encoder.layer.10.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 404 |
+
"vision_tower.encoder.layer.10.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"vision_tower.encoder.layer.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 406 |
+
"vision_tower.encoder.layer.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 407 |
+
"vision_tower.encoder.layer.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 408 |
+
"vision_tower.encoder.layer.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 409 |
+
"vision_tower.encoder.layer.11.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 410 |
+
"vision_tower.encoder.layer.11.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 411 |
+
"vision_tower.encoder.layer.11.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 412 |
+
"vision_tower.encoder.layer.11.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 413 |
+
"vision_tower.encoder.layer.11.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 414 |
+
"vision_tower.encoder.layer.11.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 415 |
+
"vision_tower.encoder.layer.11.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 416 |
+
"vision_tower.encoder.layer.11.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"vision_tower.encoder.layer.11.lambda_1": "model-00001-of-00004.safetensors",
|
| 418 |
+
"vision_tower.encoder.layer.11.lambda_2": "model-00001-of-00004.safetensors",
|
| 419 |
+
"vision_tower.encoder.layer.11.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 420 |
+
"vision_tower.encoder.layer.11.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 421 |
+
"vision_tower.encoder.layer.11.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 422 |
+
"vision_tower.encoder.layer.11.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 423 |
+
"vision_tower.encoder.layer.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 424 |
+
"vision_tower.encoder.layer.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 425 |
+
"vision_tower.encoder.layer.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 426 |
+
"vision_tower.encoder.layer.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 427 |
+
"vision_tower.encoder.layer.12.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 428 |
+
"vision_tower.encoder.layer.12.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 429 |
+
"vision_tower.encoder.layer.12.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 430 |
+
"vision_tower.encoder.layer.12.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 431 |
+
"vision_tower.encoder.layer.12.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 432 |
+
"vision_tower.encoder.layer.12.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 433 |
+
"vision_tower.encoder.layer.12.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 434 |
+
"vision_tower.encoder.layer.12.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 435 |
+
"vision_tower.encoder.layer.12.lambda_1": "model-00001-of-00004.safetensors",
|
| 436 |
+
"vision_tower.encoder.layer.12.lambda_2": "model-00001-of-00004.safetensors",
|
| 437 |
+
"vision_tower.encoder.layer.12.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 438 |
+
"vision_tower.encoder.layer.12.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 439 |
+
"vision_tower.encoder.layer.12.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 440 |
+
"vision_tower.encoder.layer.12.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 441 |
+
"vision_tower.encoder.layer.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 442 |
+
"vision_tower.encoder.layer.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 443 |
+
"vision_tower.encoder.layer.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 444 |
+
"vision_tower.encoder.layer.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 445 |
+
"vision_tower.encoder.layer.13.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 446 |
+
"vision_tower.encoder.layer.13.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 447 |
+
"vision_tower.encoder.layer.13.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 448 |
+
"vision_tower.encoder.layer.13.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 449 |
+
"vision_tower.encoder.layer.13.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 450 |
+
"vision_tower.encoder.layer.13.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 451 |
+
"vision_tower.encoder.layer.13.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 452 |
+
"vision_tower.encoder.layer.13.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 453 |
+
"vision_tower.encoder.layer.13.lambda_1": "model-00001-of-00004.safetensors",
|
| 454 |
+
"vision_tower.encoder.layer.13.lambda_2": "model-00001-of-00004.safetensors",
|
| 455 |
+
"vision_tower.encoder.layer.13.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 456 |
+
"vision_tower.encoder.layer.13.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 457 |
+
"vision_tower.encoder.layer.13.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 458 |
+
"vision_tower.encoder.layer.13.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 459 |
+
"vision_tower.encoder.layer.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 460 |
+
"vision_tower.encoder.layer.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 461 |
+
"vision_tower.encoder.layer.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 462 |
+
"vision_tower.encoder.layer.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 463 |
+
"vision_tower.encoder.layer.14.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 464 |
+
"vision_tower.encoder.layer.14.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 465 |
+
"vision_tower.encoder.layer.14.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 466 |
+
"vision_tower.encoder.layer.14.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 467 |
+
"vision_tower.encoder.layer.14.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 468 |
+
"vision_tower.encoder.layer.14.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 469 |
+
"vision_tower.encoder.layer.14.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 470 |
+
"vision_tower.encoder.layer.14.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 471 |
+
"vision_tower.encoder.layer.14.lambda_1": "model-00001-of-00004.safetensors",
|
| 472 |
+
"vision_tower.encoder.layer.14.lambda_2": "model-00001-of-00004.safetensors",
|
| 473 |
+
"vision_tower.encoder.layer.14.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 474 |
+
"vision_tower.encoder.layer.14.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 475 |
+
"vision_tower.encoder.layer.14.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 476 |
+
"vision_tower.encoder.layer.14.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 477 |
+
"vision_tower.encoder.layer.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 478 |
+
"vision_tower.encoder.layer.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 479 |
+
"vision_tower.encoder.layer.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 480 |
+
"vision_tower.encoder.layer.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 481 |
+
"vision_tower.encoder.layer.15.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 482 |
+
"vision_tower.encoder.layer.15.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 483 |
+
"vision_tower.encoder.layer.15.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 484 |
+
"vision_tower.encoder.layer.15.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 485 |
+
"vision_tower.encoder.layer.15.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 486 |
+
"vision_tower.encoder.layer.15.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 487 |
+
"vision_tower.encoder.layer.15.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 488 |
+
"vision_tower.encoder.layer.15.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 489 |
+
"vision_tower.encoder.layer.15.lambda_1": "model-00001-of-00004.safetensors",
|
| 490 |
+
"vision_tower.encoder.layer.15.lambda_2": "model-00001-of-00004.safetensors",
|
| 491 |
+
"vision_tower.encoder.layer.15.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 492 |
+
"vision_tower.encoder.layer.15.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 493 |
+
"vision_tower.encoder.layer.15.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 494 |
+
"vision_tower.encoder.layer.15.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 495 |
+
"vision_tower.encoder.layer.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 496 |
+
"vision_tower.encoder.layer.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 497 |
+
"vision_tower.encoder.layer.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 498 |
+
"vision_tower.encoder.layer.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 499 |
+
"vision_tower.encoder.layer.16.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 500 |
+
"vision_tower.encoder.layer.16.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 501 |
+
"vision_tower.encoder.layer.16.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 502 |
+
"vision_tower.encoder.layer.16.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 503 |
+
"vision_tower.encoder.layer.16.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 504 |
+
"vision_tower.encoder.layer.16.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 505 |
+
"vision_tower.encoder.layer.16.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 506 |
+
"vision_tower.encoder.layer.16.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 507 |
+
"vision_tower.encoder.layer.16.lambda_1": "model-00001-of-00004.safetensors",
|
| 508 |
+
"vision_tower.encoder.layer.16.lambda_2": "model-00001-of-00004.safetensors",
|
| 509 |
+
"vision_tower.encoder.layer.16.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 510 |
+
"vision_tower.encoder.layer.16.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 511 |
+
"vision_tower.encoder.layer.16.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 512 |
+
"vision_tower.encoder.layer.16.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"vision_tower.encoder.layer.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 514 |
+
"vision_tower.encoder.layer.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 515 |
+
"vision_tower.encoder.layer.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 516 |
+
"vision_tower.encoder.layer.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 517 |
+
"vision_tower.encoder.layer.17.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 518 |
+
"vision_tower.encoder.layer.17.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 519 |
+
"vision_tower.encoder.layer.17.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 520 |
+
"vision_tower.encoder.layer.17.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 521 |
+
"vision_tower.encoder.layer.17.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 522 |
+
"vision_tower.encoder.layer.17.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 523 |
+
"vision_tower.encoder.layer.17.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 524 |
+
"vision_tower.encoder.layer.17.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 525 |
+
"vision_tower.encoder.layer.17.lambda_1": "model-00001-of-00004.safetensors",
|
| 526 |
+
"vision_tower.encoder.layer.17.lambda_2": "model-00001-of-00004.safetensors",
|
| 527 |
+
"vision_tower.encoder.layer.17.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 528 |
+
"vision_tower.encoder.layer.17.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 529 |
+
"vision_tower.encoder.layer.17.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 530 |
+
"vision_tower.encoder.layer.17.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 531 |
+
"vision_tower.encoder.layer.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 532 |
+
"vision_tower.encoder.layer.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 533 |
+
"vision_tower.encoder.layer.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 534 |
+
"vision_tower.encoder.layer.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 535 |
+
"vision_tower.encoder.layer.18.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 536 |
+
"vision_tower.encoder.layer.18.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 537 |
+
"vision_tower.encoder.layer.18.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 538 |
+
"vision_tower.encoder.layer.18.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 539 |
+
"vision_tower.encoder.layer.18.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 540 |
+
"vision_tower.encoder.layer.18.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 541 |
+
"vision_tower.encoder.layer.18.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 542 |
+
"vision_tower.encoder.layer.18.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 543 |
+
"vision_tower.encoder.layer.18.lambda_1": "model-00001-of-00004.safetensors",
|
| 544 |
+
"vision_tower.encoder.layer.18.lambda_2": "model-00001-of-00004.safetensors",
|
| 545 |
+
"vision_tower.encoder.layer.18.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 546 |
+
"vision_tower.encoder.layer.18.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 547 |
+
"vision_tower.encoder.layer.18.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 548 |
+
"vision_tower.encoder.layer.18.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 549 |
+
"vision_tower.encoder.layer.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 550 |
+
"vision_tower.encoder.layer.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 551 |
+
"vision_tower.encoder.layer.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 552 |
+
"vision_tower.encoder.layer.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 553 |
+
"vision_tower.encoder.layer.19.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 554 |
+
"vision_tower.encoder.layer.19.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 555 |
+
"vision_tower.encoder.layer.19.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 556 |
+
"vision_tower.encoder.layer.19.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 557 |
+
"vision_tower.encoder.layer.19.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 558 |
+
"vision_tower.encoder.layer.19.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 559 |
+
"vision_tower.encoder.layer.19.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 560 |
+
"vision_tower.encoder.layer.19.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 561 |
+
"vision_tower.encoder.layer.19.lambda_1": "model-00001-of-00004.safetensors",
|
| 562 |
+
"vision_tower.encoder.layer.19.lambda_2": "model-00001-of-00004.safetensors",
|
| 563 |
+
"vision_tower.encoder.layer.19.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 564 |
+
"vision_tower.encoder.layer.19.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 565 |
+
"vision_tower.encoder.layer.19.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 566 |
+
"vision_tower.encoder.layer.19.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 567 |
+
"vision_tower.encoder.layer.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 568 |
+
"vision_tower.encoder.layer.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 569 |
+
"vision_tower.encoder.layer.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 570 |
+
"vision_tower.encoder.layer.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 571 |
+
"vision_tower.encoder.layer.2.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 572 |
+
"vision_tower.encoder.layer.2.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 573 |
+
"vision_tower.encoder.layer.2.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 574 |
+
"vision_tower.encoder.layer.2.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 575 |
+
"vision_tower.encoder.layer.2.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 576 |
+
"vision_tower.encoder.layer.2.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 577 |
+
"vision_tower.encoder.layer.2.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 578 |
+
"vision_tower.encoder.layer.2.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 579 |
+
"vision_tower.encoder.layer.2.lambda_1": "model-00001-of-00004.safetensors",
|
| 580 |
+
"vision_tower.encoder.layer.2.lambda_2": "model-00001-of-00004.safetensors",
|
| 581 |
+
"vision_tower.encoder.layer.2.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 582 |
+
"vision_tower.encoder.layer.2.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 583 |
+
"vision_tower.encoder.layer.2.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 584 |
+
"vision_tower.encoder.layer.2.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"vision_tower.encoder.layer.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 586 |
+
"vision_tower.encoder.layer.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 587 |
+
"vision_tower.encoder.layer.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 588 |
+
"vision_tower.encoder.layer.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 589 |
+
"vision_tower.encoder.layer.20.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 590 |
+
"vision_tower.encoder.layer.20.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 591 |
+
"vision_tower.encoder.layer.20.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 592 |
+
"vision_tower.encoder.layer.20.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 593 |
+
"vision_tower.encoder.layer.20.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 594 |
+
"vision_tower.encoder.layer.20.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"vision_tower.encoder.layer.20.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 596 |
+
"vision_tower.encoder.layer.20.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"vision_tower.encoder.layer.20.lambda_1": "model-00001-of-00004.safetensors",
|
| 598 |
+
"vision_tower.encoder.layer.20.lambda_2": "model-00001-of-00004.safetensors",
|
| 599 |
+
"vision_tower.encoder.layer.20.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 600 |
+
"vision_tower.encoder.layer.20.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 601 |
+
"vision_tower.encoder.layer.20.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 602 |
+
"vision_tower.encoder.layer.20.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 603 |
+
"vision_tower.encoder.layer.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 604 |
+
"vision_tower.encoder.layer.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 605 |
+
"vision_tower.encoder.layer.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 606 |
+
"vision_tower.encoder.layer.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"vision_tower.encoder.layer.21.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 608 |
+
"vision_tower.encoder.layer.21.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"vision_tower.encoder.layer.21.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 610 |
+
"vision_tower.encoder.layer.21.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 611 |
+
"vision_tower.encoder.layer.21.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 612 |
+
"vision_tower.encoder.layer.21.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 613 |
+
"vision_tower.encoder.layer.21.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 614 |
+
"vision_tower.encoder.layer.21.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 615 |
+
"vision_tower.encoder.layer.21.lambda_1": "model-00001-of-00004.safetensors",
|
| 616 |
+
"vision_tower.encoder.layer.21.lambda_2": "model-00001-of-00004.safetensors",
|
| 617 |
+
"vision_tower.encoder.layer.21.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 618 |
+
"vision_tower.encoder.layer.21.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"vision_tower.encoder.layer.21.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 620 |
+
"vision_tower.encoder.layer.21.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"vision_tower.encoder.layer.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 622 |
+
"vision_tower.encoder.layer.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 623 |
+
"vision_tower.encoder.layer.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 624 |
+
"vision_tower.encoder.layer.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 625 |
+
"vision_tower.encoder.layer.22.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 626 |
+
"vision_tower.encoder.layer.22.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 627 |
+
"vision_tower.encoder.layer.22.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 628 |
+
"vision_tower.encoder.layer.22.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 629 |
+
"vision_tower.encoder.layer.22.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 630 |
+
"vision_tower.encoder.layer.22.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 631 |
+
"vision_tower.encoder.layer.22.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 632 |
+
"vision_tower.encoder.layer.22.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"vision_tower.encoder.layer.22.lambda_1": "model-00001-of-00004.safetensors",
|
| 634 |
+
"vision_tower.encoder.layer.22.lambda_2": "model-00001-of-00004.safetensors",
|
| 635 |
+
"vision_tower.encoder.layer.22.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 636 |
+
"vision_tower.encoder.layer.22.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 637 |
+
"vision_tower.encoder.layer.22.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 638 |
+
"vision_tower.encoder.layer.22.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 639 |
+
"vision_tower.encoder.layer.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 640 |
+
"vision_tower.encoder.layer.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 641 |
+
"vision_tower.encoder.layer.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 642 |
+
"vision_tower.encoder.layer.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"vision_tower.encoder.layer.23.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 644 |
+
"vision_tower.encoder.layer.23.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 645 |
+
"vision_tower.encoder.layer.23.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 646 |
+
"vision_tower.encoder.layer.23.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 647 |
+
"vision_tower.encoder.layer.23.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 648 |
+
"vision_tower.encoder.layer.23.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 649 |
+
"vision_tower.encoder.layer.23.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 650 |
+
"vision_tower.encoder.layer.23.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 651 |
+
"vision_tower.encoder.layer.23.lambda_1": "model-00001-of-00004.safetensors",
|
| 652 |
+
"vision_tower.encoder.layer.23.lambda_2": "model-00001-of-00004.safetensors",
|
| 653 |
+
"vision_tower.encoder.layer.23.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 654 |
+
"vision_tower.encoder.layer.23.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"vision_tower.encoder.layer.23.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 656 |
+
"vision_tower.encoder.layer.23.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"vision_tower.encoder.layer.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 658 |
+
"vision_tower.encoder.layer.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 659 |
+
"vision_tower.encoder.layer.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 660 |
+
"vision_tower.encoder.layer.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 661 |
+
"vision_tower.encoder.layer.3.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 662 |
+
"vision_tower.encoder.layer.3.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 663 |
+
"vision_tower.encoder.layer.3.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 664 |
+
"vision_tower.encoder.layer.3.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 665 |
+
"vision_tower.encoder.layer.3.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 666 |
+
"vision_tower.encoder.layer.3.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"vision_tower.encoder.layer.3.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 668 |
+
"vision_tower.encoder.layer.3.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"vision_tower.encoder.layer.3.lambda_1": "model-00001-of-00004.safetensors",
|
| 670 |
+
"vision_tower.encoder.layer.3.lambda_2": "model-00001-of-00004.safetensors",
|
| 671 |
+
"vision_tower.encoder.layer.3.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 672 |
+
"vision_tower.encoder.layer.3.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 673 |
+
"vision_tower.encoder.layer.3.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 674 |
+
"vision_tower.encoder.layer.3.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 675 |
+
"vision_tower.encoder.layer.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 676 |
+
"vision_tower.encoder.layer.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 677 |
+
"vision_tower.encoder.layer.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 678 |
+
"vision_tower.encoder.layer.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 679 |
+
"vision_tower.encoder.layer.4.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 680 |
+
"vision_tower.encoder.layer.4.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 681 |
+
"vision_tower.encoder.layer.4.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 682 |
+
"vision_tower.encoder.layer.4.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 683 |
+
"vision_tower.encoder.layer.4.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 684 |
+
"vision_tower.encoder.layer.4.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 685 |
+
"vision_tower.encoder.layer.4.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 686 |
+
"vision_tower.encoder.layer.4.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 687 |
+
"vision_tower.encoder.layer.4.lambda_1": "model-00001-of-00004.safetensors",
|
| 688 |
+
"vision_tower.encoder.layer.4.lambda_2": "model-00001-of-00004.safetensors",
|
| 689 |
+
"vision_tower.encoder.layer.4.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 690 |
+
"vision_tower.encoder.layer.4.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 691 |
+
"vision_tower.encoder.layer.4.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 692 |
+
"vision_tower.encoder.layer.4.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 693 |
+
"vision_tower.encoder.layer.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 694 |
+
"vision_tower.encoder.layer.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 695 |
+
"vision_tower.encoder.layer.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 696 |
+
"vision_tower.encoder.layer.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 697 |
+
"vision_tower.encoder.layer.5.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 698 |
+
"vision_tower.encoder.layer.5.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 699 |
+
"vision_tower.encoder.layer.5.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 700 |
+
"vision_tower.encoder.layer.5.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 701 |
+
"vision_tower.encoder.layer.5.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 702 |
+
"vision_tower.encoder.layer.5.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 703 |
+
"vision_tower.encoder.layer.5.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 704 |
+
"vision_tower.encoder.layer.5.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 705 |
+
"vision_tower.encoder.layer.5.lambda_1": "model-00001-of-00004.safetensors",
|
| 706 |
+
"vision_tower.encoder.layer.5.lambda_2": "model-00001-of-00004.safetensors",
|
| 707 |
+
"vision_tower.encoder.layer.5.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 708 |
+
"vision_tower.encoder.layer.5.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 709 |
+
"vision_tower.encoder.layer.5.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 710 |
+
"vision_tower.encoder.layer.5.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 711 |
+
"vision_tower.encoder.layer.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 712 |
+
"vision_tower.encoder.layer.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 713 |
+
"vision_tower.encoder.layer.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 714 |
+
"vision_tower.encoder.layer.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 715 |
+
"vision_tower.encoder.layer.6.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 716 |
+
"vision_tower.encoder.layer.6.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 717 |
+
"vision_tower.encoder.layer.6.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 718 |
+
"vision_tower.encoder.layer.6.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 719 |
+
"vision_tower.encoder.layer.6.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 720 |
+
"vision_tower.encoder.layer.6.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 721 |
+
"vision_tower.encoder.layer.6.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 722 |
+
"vision_tower.encoder.layer.6.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 723 |
+
"vision_tower.encoder.layer.6.lambda_1": "model-00001-of-00004.safetensors",
|
| 724 |
+
"vision_tower.encoder.layer.6.lambda_2": "model-00001-of-00004.safetensors",
|
| 725 |
+
"vision_tower.encoder.layer.6.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 726 |
+
"vision_tower.encoder.layer.6.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 727 |
+
"vision_tower.encoder.layer.6.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 728 |
+
"vision_tower.encoder.layer.6.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 729 |
+
"vision_tower.encoder.layer.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 730 |
+
"vision_tower.encoder.layer.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 731 |
+
"vision_tower.encoder.layer.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 732 |
+
"vision_tower.encoder.layer.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 733 |
+
"vision_tower.encoder.layer.7.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 734 |
+
"vision_tower.encoder.layer.7.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 735 |
+
"vision_tower.encoder.layer.7.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 736 |
+
"vision_tower.encoder.layer.7.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 737 |
+
"vision_tower.encoder.layer.7.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 738 |
+
"vision_tower.encoder.layer.7.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 739 |
+
"vision_tower.encoder.layer.7.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 740 |
+
"vision_tower.encoder.layer.7.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 741 |
+
"vision_tower.encoder.layer.7.lambda_1": "model-00001-of-00004.safetensors",
|
| 742 |
+
"vision_tower.encoder.layer.7.lambda_2": "model-00001-of-00004.safetensors",
|
| 743 |
+
"vision_tower.encoder.layer.7.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 744 |
+
"vision_tower.encoder.layer.7.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 745 |
+
"vision_tower.encoder.layer.7.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 746 |
+
"vision_tower.encoder.layer.7.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 747 |
+
"vision_tower.encoder.layer.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 748 |
+
"vision_tower.encoder.layer.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 749 |
+
"vision_tower.encoder.layer.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 750 |
+
"vision_tower.encoder.layer.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 751 |
+
"vision_tower.encoder.layer.8.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 752 |
+
"vision_tower.encoder.layer.8.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 753 |
+
"vision_tower.encoder.layer.8.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 754 |
+
"vision_tower.encoder.layer.8.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 755 |
+
"vision_tower.encoder.layer.8.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 756 |
+
"vision_tower.encoder.layer.8.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 757 |
+
"vision_tower.encoder.layer.8.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 758 |
+
"vision_tower.encoder.layer.8.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 759 |
+
"vision_tower.encoder.layer.8.lambda_1": "model-00001-of-00004.safetensors",
|
| 760 |
+
"vision_tower.encoder.layer.8.lambda_2": "model-00001-of-00004.safetensors",
|
| 761 |
+
"vision_tower.encoder.layer.8.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 762 |
+
"vision_tower.encoder.layer.8.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 763 |
+
"vision_tower.encoder.layer.8.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 764 |
+
"vision_tower.encoder.layer.8.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 765 |
+
"vision_tower.encoder.layer.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 766 |
+
"vision_tower.encoder.layer.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 767 |
+
"vision_tower.encoder.layer.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 768 |
+
"vision_tower.encoder.layer.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 769 |
+
"vision_tower.encoder.layer.9.attention.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 770 |
+
"vision_tower.encoder.layer.9.attention.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 771 |
+
"vision_tower.encoder.layer.9.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
|
| 772 |
+
"vision_tower.encoder.layer.9.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
|
| 773 |
+
"vision_tower.encoder.layer.9.attention.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 774 |
+
"vision_tower.encoder.layer.9.attention.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 775 |
+
"vision_tower.encoder.layer.9.attention.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 776 |
+
"vision_tower.encoder.layer.9.attention.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 777 |
+
"vision_tower.encoder.layer.9.lambda_1": "model-00001-of-00004.safetensors",
|
| 778 |
+
"vision_tower.encoder.layer.9.lambda_2": "model-00001-of-00004.safetensors",
|
| 779 |
+
"vision_tower.encoder.layer.9.layernorm_after.bias": "model-00001-of-00004.safetensors",
|
| 780 |
+
"vision_tower.encoder.layer.9.layernorm_after.weight": "model-00001-of-00004.safetensors",
|
| 781 |
+
"vision_tower.encoder.layer.9.layernorm_before.bias": "model-00001-of-00004.safetensors",
|
| 782 |
+
"vision_tower.encoder.layer.9.layernorm_before.weight": "model-00001-of-00004.safetensors",
|
| 783 |
+
"vision_tower.encoder.layer.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 784 |
+
"vision_tower.encoder.layer.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 785 |
+
"vision_tower.encoder.layer.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 786 |
+
"vision_tower.encoder.layer.9.mlp.fc2.weight": "model-00001-of-00004.safetensors"
|
| 787 |
+
}
|
| 788 |
+
}
|
models/InternVL3-8B-hf/preprocessor_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"crop_to_patches": false,
|
| 4 |
+
"data_format": "channels_first",
|
| 5 |
+
"default_to_square": true,
|
| 6 |
+
"device": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_rescale": true,
|
| 11 |
+
"do_resize": true,
|
| 12 |
+
"image_mean": [
|
| 13 |
+
0.485,
|
| 14 |
+
0.456,
|
| 15 |
+
0.406
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "GotOcr2ImageProcessorFast",
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.229,
|
| 20 |
+
0.224,
|
| 21 |
+
0.225
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_patches": 12,
|
| 25 |
+
"min_patches": 1,
|
| 26 |
+
"processor_class": "InternVLProcessor",
|
| 27 |
+
"resample": 3,
|
| 28 |
+
"rescale_factor": 0.00392156862745098,
|
| 29 |
+
"return_tensors": null,
|
| 30 |
+
"size": {
|
| 31 |
+
"height": 448,
|
| 32 |
+
"width": 448
|
| 33 |
+
}
|
| 34 |
+
}
|
models/InternVL3-8B-hf/processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "InternVLProcessor"
|
| 4 |
+
}
|
models/InternVL3-8B-hf/special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<img>",
|
| 17 |
+
"</img>",
|
| 18 |
+
"<IMG_CONTEXT>",
|
| 19 |
+
"<quad>",
|
| 20 |
+
"</quad>",
|
| 21 |
+
"<ref>",
|
| 22 |
+
"</ref>",
|
| 23 |
+
"<box>",
|
| 24 |
+
"</box>"
|
| 25 |
+
],
|
| 26 |
+
"context_image_token": "<IMG_CONTEXT>",
|
| 27 |
+
"end_image_token": "</img>",
|
| 28 |
+
"eos_token": {
|
| 29 |
+
"content": "<|im_end|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"pad_token": {
|
| 36 |
+
"content": "<|endoftext|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
},
|
| 42 |
+
"start_image_token": "<img>",
|
| 43 |
+
"video_token": "<video>"
|
| 44 |
+
}
|
models/InternVL3-8B-hf/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cc80b7e20adf8bf6f6ca442bf1abfac8056bb3b7d3e0b11c9d497d3e79398c9
|
| 3 |
+
size 11423732
|
models/InternVL3-8B-hf/tokenizer_config.json
ADDED
|
@@ -0,0 +1,306 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<img>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</img>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<IMG_CONTEXT>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "<quad>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"151669": {
|
| 214 |
+
"content": "</quad>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"151670": {
|
| 222 |
+
"content": "<ref>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"151671": {
|
| 230 |
+
"content": "</ref>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"151672": {
|
| 238 |
+
"content": "<box>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"151673": {
|
| 246 |
+
"content": "</box>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"151674": {
|
| 254 |
+
"content": "<video>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
}
|
| 261 |
+
},
|
| 262 |
+
"additional_special_tokens": [
|
| 263 |
+
"<|im_start|>",
|
| 264 |
+
"<|im_end|>",
|
| 265 |
+
"<|object_ref_start|>",
|
| 266 |
+
"<|object_ref_end|>",
|
| 267 |
+
"<|box_start|>",
|
| 268 |
+
"<|box_end|>",
|
| 269 |
+
"<|quad_start|>",
|
| 270 |
+
"<|quad_end|>",
|
| 271 |
+
"<|vision_start|>",
|
| 272 |
+
"<|vision_end|>",
|
| 273 |
+
"<|vision_pad|>",
|
| 274 |
+
"<|image_pad|>",
|
| 275 |
+
"<|video_pad|>",
|
| 276 |
+
"<img>",
|
| 277 |
+
"</img>",
|
| 278 |
+
"<IMG_CONTEXT>",
|
| 279 |
+
"<quad>",
|
| 280 |
+
"</quad>",
|
| 281 |
+
"<ref>",
|
| 282 |
+
"</ref>",
|
| 283 |
+
"<box>",
|
| 284 |
+
"</box>"
|
| 285 |
+
],
|
| 286 |
+
"bos_token": null,
|
| 287 |
+
"clean_up_tokenization_spaces": false,
|
| 288 |
+
"context_image_token": "<IMG_CONTEXT>",
|
| 289 |
+
"end_image_token": "</img>",
|
| 290 |
+
"eos_token": "<|im_end|>",
|
| 291 |
+
"errors": "replace",
|
| 292 |
+
"extra_special_tokens": {
|
| 293 |
+
"context_image_token": "<IMG_CONTEXT>",
|
| 294 |
+
"end_image_token": "</img>",
|
| 295 |
+
"start_image_token": "<img>",
|
| 296 |
+
"video_token": "<video>"
|
| 297 |
+
},
|
| 298 |
+
"model_max_length": 8192,
|
| 299 |
+
"pad_token": "<|endoftext|>",
|
| 300 |
+
"return_token_type_ids": false,
|
| 301 |
+
"split_special_tokens": false,
|
| 302 |
+
"start_image_token": "<img>",
|
| 303 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 304 |
+
"unk_token": null,
|
| 305 |
+
"video_token": "<video>"
|
| 306 |
+
}
|
models/InternVL3-8B-hf/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|