xrx commited on
Commit ·
c3314a5
1
Parent(s): ceab9d5
Initial commit
Browse files- ._README.md +0 -0
- ._config.json +0 -0
- ._demo.py +0 -0
- ._modeling_mixsense_llama.py +0 -0
- LICENSE +84 -0
- README.md +83 -3
- config.json +49 -0
- demo.py +46 -0
- example.jpg +0 -0
- generation_config.json +6 -0
- llama3mixsense.py +50 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +702 -0
- modeling_mixsense_llama.py +1233 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2071 -0
._README.md
ADDED
|
Binary file (4.1 kB). View file
|
|
|
._config.json
ADDED
|
Binary file (4.1 kB). View file
|
|
|
._demo.py
ADDED
|
Binary file (4.1 kB). View file
|
|
|
._modeling_mixsense_llama.py
ADDED
|
Binary file (4.1 kB). View file
|
|
|
LICENSE
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
META LLAMA 3 COMMUNITY LICENSE AGREEMENT
|
| 2 |
+
|
| 3 |
+
Meta Llama 3 Version Release Date: April 18, 2024
|
| 4 |
+
“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
|
| 5 |
+
|
| 6 |
+
“Documentation” means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.
|
| 7 |
+
|
| 8 |
+
“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
|
| 9 |
+
|
| 10 |
+
“Meta Llama 3” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.
|
| 11 |
+
|
| 12 |
+
“Llama Materials” means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.
|
| 13 |
+
|
| 14 |
+
“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
|
| 15 |
+
|
| 16 |
+
By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
|
| 17 |
+
|
| 18 |
+
1. License Rights and Redistribution.
|
| 19 |
+
|
| 20 |
+
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
|
| 21 |
+
b. Redistribution and Use.
|
| 22 |
+
i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model name.
|
| 23 |
+
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.
|
| 24 |
+
iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
|
| 25 |
+
iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.
|
| 26 |
+
v. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).
|
| 27 |
+
|
| 28 |
+
2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
|
| 29 |
+
|
| 30 |
+
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
|
| 31 |
+
|
| 32 |
+
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
|
| 33 |
+
|
| 34 |
+
5. Intellectual Property.
|
| 35 |
+
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
|
| 36 |
+
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
|
| 37 |
+
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
|
| 38 |
+
|
| 39 |
+
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
|
| 40 |
+
|
| 41 |
+
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
Meta Llama 3 Acceptable Use Policy
|
| 45 |
+
Meta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at https://llama.meta.com/llama3/use-policy
|
| 46 |
+
Prohibited Uses
|
| 47 |
+
We want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to:
|
| 48 |
+
1. Violate the law or others’ rights, including to:
|
| 49 |
+
a. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
|
| 50 |
+
i. Violence or terrorism
|
| 51 |
+
ii. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
|
| 52 |
+
iii. Human trafficking, exploitation, and sexual violence
|
| 53 |
+
iv. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
|
| 54 |
+
v. Sexual solicitation
|
| 55 |
+
vi. Any other criminal activity
|
| 56 |
+
b. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
|
| 57 |
+
c. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
|
| 58 |
+
d. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
|
| 59 |
+
e. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
|
| 60 |
+
f. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
|
| 61 |
+
g. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
|
| 62 |
+
|
| 63 |
+
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:
|
| 64 |
+
a. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
|
| 65 |
+
b. Guns and illegal weapons (including weapon development)
|
| 66 |
+
c. Illegal drugs and regulated/controlled substances
|
| 67 |
+
d. Operation of critical infrastructure, transportation technologies, or heavy machinery
|
| 68 |
+
e. Self-harm or harm to others, including suicide, cutting, and eating disorders
|
| 69 |
+
f. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
|
| 70 |
+
|
| 71 |
+
3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:
|
| 72 |
+
a. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
|
| 73 |
+
b. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
|
| 74 |
+
c. Generating, promoting, or further distributing spam
|
| 75 |
+
d. Impersonating another individual without consent, authorization, or legal right
|
| 76 |
+
e. Representing that the use of Meta Llama 3 or outputs are human-generated
|
| 77 |
+
f. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
|
| 78 |
+
g. Fail to appropriately disclose to end users any known dangers of your AI system
|
| 79 |
+
|
| 80 |
+
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
|
| 81 |
+
* Reporting issues with the model: https://github.com/meta-llama/llama3
|
| 82 |
+
* Reporting risky content generated by the model: developers.facebook.com/llama_output_feedback
|
| 83 |
+
* Reporting bugs and security concerns: facebook.com/whitehat/info
|
| 84 |
+
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com
|
README.md
CHANGED
|
@@ -1,3 +1,83 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Introduction
|
| 2 |
+
|
| 3 |
+
MixSense is a series of models based on the widely adopted vision encoder-projector-LLM architecture. In this resource, we release Llama-3-MixSenseV1.1 checkpoint. Compared to [version 1.0](https://huggingface.co/Zero-Vision/Llama-3-MixSense), we changed the vision encoder from [SigLIP 400M](https://huggingface.co/google/siglip-so400m-patch14-384) to [Florence-2-large-ft's vision encoder DaViT](https://huggingface.co/microsoft/Florence-2-large-ft) and add more VQA data in finetune stage.
|
| 4 |
+
|
| 5 |
+
We have developed an innovative data processing method that complements the training process, reducing training costs while improving training effectiveness.,The models are trained on our restructured dataset. Details of the data organization and related research papers will be available soon.
|
| 6 |
+
|
| 7 |
+
# QuickStart
|
| 8 |
+
|
| 9 |
+
## Requirements
|
| 10 |
+
|
| 11 |
+
```
|
| 12 |
+
conda create -n mixsense python==3.10 -y
|
| 13 |
+
conda activate mixsense
|
| 14 |
+
pip install torch transformers==4.37.2 accelerate pillow
|
| 15 |
+
```
|
| 16 |
+
|
| 17 |
+
## Usage
|
| 18 |
+
|
| 19 |
+
Llama-3-Mixsense/demo.py
|
| 20 |
+
|
| 21 |
+
```python
|
| 22 |
+
import torch
|
| 23 |
+
import transformers
|
| 24 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 25 |
+
from PIL import Image
|
| 26 |
+
import warnings
|
| 27 |
+
import os
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
# disable some warnings
|
| 31 |
+
transformers.logging.set_verbosity_error()
|
| 32 |
+
transformers.logging.disable_progress_bar()
|
| 33 |
+
warnings.filterwarnings("ignore")
|
| 34 |
+
|
| 35 |
+
# set device
|
| 36 |
+
device = "cuda" # or cpu, or npu (ASCEND 910B support)
|
| 37 |
+
|
| 38 |
+
# create model
|
| 39 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 40 |
+
"Zero-Vision/Llama-3-MixSenseV1_1",
|
| 41 |
+
torch_dtype=torch.float16, # float32 for cpu
|
| 42 |
+
device_map="auto",
|
| 43 |
+
trust_remote_code=True,
|
| 44 |
+
)
|
| 45 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 46 |
+
"Zero-Vision/Llama-3-MixSenseV1_1",
|
| 47 |
+
trust_remote_code=True,
|
| 48 |
+
)
|
| 49 |
+
|
| 50 |
+
qs = "describe the image detailly."
|
| 51 |
+
input_ids = model.text_process(qs, tokenizer).to(device)
|
| 52 |
+
|
| 53 |
+
image = Image.open("example.jpg")
|
| 54 |
+
image_tensor = model.image_process([image]).to(dtype=model.dtype, device=device)
|
| 55 |
+
|
| 56 |
+
# generate
|
| 57 |
+
with torch.inference_mode():
|
| 58 |
+
output_ids = model.generate(
|
| 59 |
+
input_ids,
|
| 60 |
+
images=image_tensor,
|
| 61 |
+
max_new_tokens=2048,
|
| 62 |
+
use_cache=True,
|
| 63 |
+
eos_token_id=[
|
| 64 |
+
tokenizer.eos_token_id,
|
| 65 |
+
tokenizer.convert_tokens_to_ids(["<|eot_id|>"])[0],
|
| 66 |
+
],
|
| 67 |
+
)
|
| 68 |
+
|
| 69 |
+
print(tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip())
|
| 70 |
+
```
|
| 71 |
+
|
| 72 |
+
## Eval
|
| 73 |
+
|
| 74 |
+
We offer Llama-3-Mixsense/llama3mixsense.py for [VLMEvalKit](https://github.com/open-compass/VLMEvalKit).
|
| 75 |
+
|
| 76 |
+
# License
|
| 77 |
+
|
| 78 |
+
This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses.including but not limited to Llama3 and SigLIP. Meta Llama 3 is licensed under the [Meta Llama 3 Community License](https://llama.meta.com/llama3/license/), Copyright © Meta Platforms, Inc. All Rights Reserved. And [MIT LICENSE](https://www.apache.org/licenses/LICENSE-2.0) for Florence2 model. The project itself is licensed under the [Apache LICENSE 2.0](https://www.apache.org/licenses/LICENSE-2.0) .
|
| 79 |
+
|
| 80 |
+
# Acknowledgement
|
| 81 |
+
|
| 82 |
+
Our code is largely borrowed from [LLaVA](https://github.com/haotian-liu/LLaVA)
|
| 83 |
+
We bulid this demo according to [bunny](https://huggingface.co/BAAI/Bunny-Llama-3-8B-V)
|
config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Zero-Vision/Llama-3-MixSenseV1_1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixsenseLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "modeling_mixsense_llama.MixsenseConfig",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_mixsense_llama.MixsenseLlamaForCausalLM"
|
| 9 |
+
},
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 128000,
|
| 13 |
+
"eos_token_id": 128001,
|
| 14 |
+
"freeze_mm_mlp_adapter": false,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"image_aspect_ratio": "pad",
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 14336,
|
| 20 |
+
"max_position_embeddings": 8192,
|
| 21 |
+
"mm_hidden_size": 2048,
|
| 22 |
+
"mm_patch_merge_type": "flat",
|
| 23 |
+
"mm_projector_lr": null,
|
| 24 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 25 |
+
"mm_use_im_patch_token": false,
|
| 26 |
+
"mm_use_im_start_end": false,
|
| 27 |
+
"mm_vision_select_feature": "patch",
|
| 28 |
+
"mm_vision_select_layer": -2,
|
| 29 |
+
"mm_vision_tower": "microsoft/Florence-2-large-ft",
|
| 30 |
+
"model_type": "mixsense_llama",
|
| 31 |
+
"num_attention_heads": 32,
|
| 32 |
+
"num_hidden_layers": 32,
|
| 33 |
+
"num_key_value_heads": 8,
|
| 34 |
+
"pretraining_tp": 1,
|
| 35 |
+
"rms_norm_eps": 1e-05,
|
| 36 |
+
"rope_scaling": null,
|
| 37 |
+
"rope_theta": 500000.0,
|
| 38 |
+
"size": 768,
|
| 39 |
+
"tie_word_embeddings": false,
|
| 40 |
+
"tokenizer_model_max_length": 3072,
|
| 41 |
+
"tokenizer_padding_side": "right",
|
| 42 |
+
"torch_dtype": "bfloat16",
|
| 43 |
+
"transformers_version": "4.37.2",
|
| 44 |
+
"tune_mm_mlp_adapter": false,
|
| 45 |
+
"unfreeze_mm_vision_tower": true,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"use_mm_proj": true,
|
| 48 |
+
"vocab_size": 128257
|
| 49 |
+
}
|
demo.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import transformers
|
| 3 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 4 |
+
from PIL import Image
|
| 5 |
+
import warnings
|
| 6 |
+
import os
|
| 7 |
+
|
| 8 |
+
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
|
| 9 |
+
# disable some warnings
|
| 10 |
+
transformers.logging.set_verbosity_error()
|
| 11 |
+
transformers.logging.disable_progress_bar()
|
| 12 |
+
warnings.filterwarnings("ignore")
|
| 13 |
+
|
| 14 |
+
# set device
|
| 15 |
+
device = "cuda" # or cpu
|
| 16 |
+
|
| 17 |
+
# create model
|
| 18 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 19 |
+
"Zero-Vision/Llama-3-MixSenseV1_1",
|
| 20 |
+
torch_dtype=torch.float16,
|
| 21 |
+
device_map="auto",
|
| 22 |
+
trust_remote_code=True,
|
| 23 |
+
)
|
| 24 |
+
tokenizer = AutoTokenizer.from_pretrained(
|
| 25 |
+
"Zero-Vision/Llama-3-MixSenseV1_1",
|
| 26 |
+
trust_remote_code=True,
|
| 27 |
+
)
|
| 28 |
+
qs = "describe the image detailly."
|
| 29 |
+
input_ids = model.text_process(qs, tokenizer).to(device)
|
| 30 |
+
|
| 31 |
+
image = Image.open("example.jpg")
|
| 32 |
+
image_tensor = model.image_process([image]).to(dtype=model.dtype, device=device)
|
| 33 |
+
|
| 34 |
+
# generate
|
| 35 |
+
with torch.inference_mode():
|
| 36 |
+
output_ids = model.generate(
|
| 37 |
+
input_ids,
|
| 38 |
+
images=image_tensor,
|
| 39 |
+
max_new_tokens=2048,
|
| 40 |
+
use_cache=True,
|
| 41 |
+
eos_token_id=[
|
| 42 |
+
tokenizer.eos_token_id,
|
| 43 |
+
tokenizer.convert_tokens_to_ids(["<|eot_id|>"])[0],
|
| 44 |
+
],
|
| 45 |
+
)
|
| 46 |
+
print(tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip())
|
example.jpg
ADDED
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": 128001,
|
| 5 |
+
"transformers_version": "4.37.2"
|
| 6 |
+
}
|
llama3mixsense.py
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
'''
|
| 2 |
+
This file if for VLMEvalKit.
|
| 3 |
+
'''
|
| 4 |
+
import torch
|
| 5 |
+
import transformers
|
| 6 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 7 |
+
from PIL import Image
|
| 8 |
+
import warnings
|
| 9 |
+
|
| 10 |
+
from .base import BaseModel
|
| 11 |
+
from ..smp import *
|
| 12 |
+
from ..utils import DATASET_TYPE
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
class LLama3Mixsense(BaseModel):
|
| 16 |
+
|
| 17 |
+
INSTALL_REQ = False
|
| 18 |
+
INTERLEAVE = False
|
| 19 |
+
|
| 20 |
+
def __init__(self, model_path="Zero-Vision/Llama-3-MixSenseV1_1", **kwargs):
|
| 21 |
+
assert model_path is not None
|
| 22 |
+
transformers.logging.set_verbosity_error()
|
| 23 |
+
transformers.logging.disable_progress_bar()
|
| 24 |
+
warnings.filterwarnings("ignore")
|
| 25 |
+
self.tokenizer = AutoTokenizer.from_pretrained(
|
| 26 |
+
model_path, trust_remote_code=True
|
| 27 |
+
)
|
| 28 |
+
self.model = AutoModelForCausalLM.from_pretrained(
|
| 29 |
+
model_path, device_map="auto", trust_remote_code=True
|
| 30 |
+
)
|
| 31 |
+
self.kwargs = kwargs
|
| 32 |
+
|
| 33 |
+
def generate_inner(self, message, dataset=None):
|
| 34 |
+
prompt, image_path = self.message_to_promptimg(message)
|
| 35 |
+
input_ids=self.model.text_process(prompt, self.tokenizer)
|
| 36 |
+
image = Image.open(image_path).convert("RGB")
|
| 37 |
+
image_tensor = self.model.image_process([image]).to(dtype=self.model.dtype, device=device)
|
| 38 |
+
# generate
|
| 39 |
+
with torch.inference_mode():
|
| 40 |
+
output_ids = self.model.generate(
|
| 41 |
+
input_ids,
|
| 42 |
+
images=image_tensor,
|
| 43 |
+
max_new_tokens=2048,
|
| 44 |
+
use_cache=True,
|
| 45 |
+
eos_token_id=[
|
| 46 |
+
self.tokenizer.eos_token_id,
|
| 47 |
+
self.tokenizer.convert_tokens_to_ids(["<|eot_id|>"])[0],
|
| 48 |
+
],
|
| 49 |
+
)
|
| 50 |
+
return self.tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d5a78df4feb4fbcb01176d679792d494d65f7acefd74fd8c5dd6ed541084970
|
| 3 |
+
size 4976706864
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f79a62169af0c70e9955fad01ea2ac2078d31754477faa8a24377944f28c358
|
| 3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae471b0cd3de60917f6fbb27d71b491f61ff878ba51758ce38e21304ef052a39
|
| 3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b9e7c0dab83d5328ae4b74e429ee4eec2aaf98c43a41f90547ee2cd389a1a02
|
| 3 |
+
size 1939820800
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16832151552
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 301 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 302 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 303 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 304 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 305 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 306 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.vision_tower.vision_tower.blocks.0.0.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 317 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 319 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 320 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 322 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 323 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 326 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 327 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.vision_tower.vision_tower.blocks.0.0.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 340 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 341 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 342 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 343 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 344 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 345 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.vision_tower.vision_tower.blocks.1.0.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.blocks.1.0.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.blocks.2.0.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.blocks.2.0.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.blocks.2.1.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.blocks.2.1.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.blocks.2.2.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.blocks.2.2.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.blocks.2.3.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.blocks.2.3.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.blocks.2.4.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.blocks.2.4.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.blocks.2.5.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.blocks.2.5.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.blocks.2.6.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.blocks.2.6.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.blocks.2.7.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.blocks.2.7.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.blocks.2.8.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.blocks.2.8.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.channel_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.blocks.3.0.channel_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.bias": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.weight": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.bias": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.weight": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.bias": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.weight": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.bias": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.ffn.norm.weight": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.bias": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.weight": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.bias": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.blocks.3.0.spatial_block.window_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.convs.0.norm.bias": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.convs.0.norm.weight": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.convs.0.proj.bias": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.convs.0.proj.weight": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.convs.1.norm.bias": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.convs.1.norm.weight": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.convs.1.proj.bias": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.convs.1.proj.weight": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.convs.2.norm.bias": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.convs.2.norm.weight": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.convs.2.proj.bias": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.convs.2.proj.weight": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.convs.3.norm.bias": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.convs.3.norm.weight": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.convs.3.proj.bias": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.convs.3.proj.weight": "model-00004-of-00004.safetensors"
|
| 701 |
+
}
|
| 702 |
+
}
|
modeling_mixsense_llama.py
ADDED
|
@@ -0,0 +1,1233 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn as nn
|
| 3 |
+
from transformers import AutoConfig, CLIPImageProcessor
|
| 4 |
+
import os
|
| 5 |
+
from einops import rearrange
|
| 6 |
+
from collections import OrderedDict
|
| 7 |
+
from timm.models.layers import DropPath, trunc_normal_
|
| 8 |
+
import torch.nn.functional as F
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
"""
|
| 14 |
+
DaViT : Copied from https://huggingface.co/microsoft/Florence-2-large/blob/main/modeling_florence2.py
|
| 15 |
+
"""
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
class MySequential(nn.Sequential):
|
| 19 |
+
def forward(self, *inputs):
|
| 20 |
+
for module in self._modules.values():
|
| 21 |
+
if type(inputs) == tuple:
|
| 22 |
+
inputs = module(*inputs)
|
| 23 |
+
else:
|
| 24 |
+
inputs = module(inputs)
|
| 25 |
+
return inputs
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
class PreNorm(nn.Module):
|
| 29 |
+
def __init__(self, norm, fn, drop_path=None):
|
| 30 |
+
super().__init__()
|
| 31 |
+
self.norm = norm
|
| 32 |
+
self.fn = fn
|
| 33 |
+
self.drop_path = drop_path
|
| 34 |
+
|
| 35 |
+
def forward(self, x, *args, **kwargs):
|
| 36 |
+
shortcut = x
|
| 37 |
+
if self.norm != None:
|
| 38 |
+
x, size = self.fn(self.norm(x), *args, **kwargs)
|
| 39 |
+
else:
|
| 40 |
+
x, size = self.fn(x, *args, **kwargs)
|
| 41 |
+
|
| 42 |
+
if self.drop_path:
|
| 43 |
+
x = self.drop_path(x)
|
| 44 |
+
|
| 45 |
+
x = shortcut + x
|
| 46 |
+
|
| 47 |
+
return x, size
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
class Mlp(nn.Module):
|
| 51 |
+
def __init__(
|
| 52 |
+
self,
|
| 53 |
+
in_features,
|
| 54 |
+
hidden_features=None,
|
| 55 |
+
out_features=None,
|
| 56 |
+
act_layer=nn.GELU,
|
| 57 |
+
):
|
| 58 |
+
super().__init__()
|
| 59 |
+
out_features = out_features or in_features
|
| 60 |
+
hidden_features = hidden_features or in_features
|
| 61 |
+
self.net = nn.Sequential(
|
| 62 |
+
OrderedDict(
|
| 63 |
+
[
|
| 64 |
+
("fc1", nn.Linear(in_features, hidden_features)),
|
| 65 |
+
("act", act_layer()),
|
| 66 |
+
("fc2", nn.Linear(hidden_features, out_features)),
|
| 67 |
+
]
|
| 68 |
+
)
|
| 69 |
+
)
|
| 70 |
+
|
| 71 |
+
def forward(self, x, size):
|
| 72 |
+
return self.net(x), size
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
class DepthWiseConv2d(nn.Module):
|
| 76 |
+
def __init__(
|
| 77 |
+
self,
|
| 78 |
+
dim_in,
|
| 79 |
+
kernel_size,
|
| 80 |
+
padding,
|
| 81 |
+
stride,
|
| 82 |
+
bias=True,
|
| 83 |
+
):
|
| 84 |
+
super().__init__()
|
| 85 |
+
self.dw = nn.Conv2d(
|
| 86 |
+
dim_in,
|
| 87 |
+
dim_in,
|
| 88 |
+
kernel_size=kernel_size,
|
| 89 |
+
padding=padding,
|
| 90 |
+
groups=dim_in,
|
| 91 |
+
stride=stride,
|
| 92 |
+
bias=bias,
|
| 93 |
+
)
|
| 94 |
+
|
| 95 |
+
def forward(self, x, size):
|
| 96 |
+
B, N, C = x.shape
|
| 97 |
+
H, W = size
|
| 98 |
+
assert N == H * W
|
| 99 |
+
|
| 100 |
+
x = self.dw(x.transpose(1, 2).view(B, C, H, W))
|
| 101 |
+
size = (x.size(-2), x.size(-1))
|
| 102 |
+
x = x.flatten(2).transpose(1, 2)
|
| 103 |
+
return x, size
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
class ConvEmbed(nn.Module):
|
| 107 |
+
"""Image to Patch Embedding"""
|
| 108 |
+
|
| 109 |
+
def __init__(
|
| 110 |
+
self,
|
| 111 |
+
patch_size=7,
|
| 112 |
+
in_chans=3,
|
| 113 |
+
embed_dim=64,
|
| 114 |
+
stride=4,
|
| 115 |
+
padding=2,
|
| 116 |
+
norm_layer=None,
|
| 117 |
+
pre_norm=True,
|
| 118 |
+
):
|
| 119 |
+
super().__init__()
|
| 120 |
+
self.patch_size = patch_size
|
| 121 |
+
|
| 122 |
+
self.proj = nn.Conv2d(
|
| 123 |
+
in_chans, embed_dim, kernel_size=patch_size, stride=stride, padding=padding
|
| 124 |
+
)
|
| 125 |
+
|
| 126 |
+
dim_norm = in_chans if pre_norm else embed_dim
|
| 127 |
+
self.norm = norm_layer(dim_norm) if norm_layer else None
|
| 128 |
+
|
| 129 |
+
self.pre_norm = pre_norm
|
| 130 |
+
|
| 131 |
+
def forward(self, x, size):
|
| 132 |
+
H, W = size
|
| 133 |
+
if len(x.size()) == 3:
|
| 134 |
+
if self.norm and self.pre_norm:
|
| 135 |
+
x = self.norm(x)
|
| 136 |
+
x = rearrange(x, "b (h w) c -> b c h w", h=H, w=W)
|
| 137 |
+
|
| 138 |
+
x = self.proj(x)
|
| 139 |
+
|
| 140 |
+
_, _, H, W = x.shape
|
| 141 |
+
x = rearrange(x, "b c h w -> b (h w) c")
|
| 142 |
+
if self.norm and not self.pre_norm:
|
| 143 |
+
x = self.norm(x)
|
| 144 |
+
|
| 145 |
+
return x, (H, W)
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
class ChannelAttention(nn.Module):
|
| 149 |
+
|
| 150 |
+
def __init__(self, dim, groups=8, qkv_bias=True):
|
| 151 |
+
super().__init__()
|
| 152 |
+
|
| 153 |
+
self.groups = groups
|
| 154 |
+
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
|
| 155 |
+
self.proj = nn.Linear(dim, dim)
|
| 156 |
+
|
| 157 |
+
def forward(self, x, size):
|
| 158 |
+
B, N, C = x.shape
|
| 159 |
+
|
| 160 |
+
qkv = (
|
| 161 |
+
self.qkv(x)
|
| 162 |
+
.reshape(B, N, 3, self.groups, C // self.groups)
|
| 163 |
+
.permute(2, 0, 3, 1, 4)
|
| 164 |
+
)
|
| 165 |
+
q, k, v = qkv[0], qkv[1], qkv[2]
|
| 166 |
+
|
| 167 |
+
q = q * (float(N) ** -0.5)
|
| 168 |
+
attention = q.transpose(-1, -2) @ k
|
| 169 |
+
attention = attention.softmax(dim=-1)
|
| 170 |
+
x = (attention @ v.transpose(-1, -2)).transpose(-1, -2)
|
| 171 |
+
x = x.transpose(1, 2).reshape(B, N, C)
|
| 172 |
+
x = self.proj(x)
|
| 173 |
+
return x, size
|
| 174 |
+
|
| 175 |
+
|
| 176 |
+
class ChannelBlock(nn.Module):
|
| 177 |
+
|
| 178 |
+
def __init__(
|
| 179 |
+
self,
|
| 180 |
+
dim,
|
| 181 |
+
groups,
|
| 182 |
+
mlp_ratio=4.0,
|
| 183 |
+
qkv_bias=True,
|
| 184 |
+
drop_path_rate=0.0,
|
| 185 |
+
act_layer=nn.GELU,
|
| 186 |
+
norm_layer=nn.LayerNorm,
|
| 187 |
+
conv_at_attn=True,
|
| 188 |
+
conv_at_ffn=True,
|
| 189 |
+
):
|
| 190 |
+
super().__init__()
|
| 191 |
+
|
| 192 |
+
drop_path = DropPath(drop_path_rate) if drop_path_rate > 0.0 else nn.Identity()
|
| 193 |
+
|
| 194 |
+
self.conv1 = (
|
| 195 |
+
PreNorm(None, DepthWiseConv2d(dim, 3, 1, 1)) if conv_at_attn else None
|
| 196 |
+
)
|
| 197 |
+
self.channel_attn = PreNorm(
|
| 198 |
+
norm_layer(dim),
|
| 199 |
+
ChannelAttention(dim, groups=groups, qkv_bias=qkv_bias),
|
| 200 |
+
drop_path,
|
| 201 |
+
)
|
| 202 |
+
self.conv2 = (
|
| 203 |
+
PreNorm(None, DepthWiseConv2d(dim, 3, 1, 1)) if conv_at_ffn else None
|
| 204 |
+
)
|
| 205 |
+
self.ffn = PreNorm(
|
| 206 |
+
norm_layer(dim),
|
| 207 |
+
Mlp(
|
| 208 |
+
in_features=dim,
|
| 209 |
+
hidden_features=int(dim * mlp_ratio),
|
| 210 |
+
act_layer=act_layer,
|
| 211 |
+
),
|
| 212 |
+
drop_path,
|
| 213 |
+
)
|
| 214 |
+
|
| 215 |
+
def forward(self, x, size):
|
| 216 |
+
if self.conv1:
|
| 217 |
+
x, size = self.conv1(x, size)
|
| 218 |
+
x, size = self.channel_attn(x, size)
|
| 219 |
+
|
| 220 |
+
if self.conv2:
|
| 221 |
+
x, size = self.conv2(x, size)
|
| 222 |
+
x, size = self.ffn(x, size)
|
| 223 |
+
|
| 224 |
+
return x, size
|
| 225 |
+
|
| 226 |
+
|
| 227 |
+
def window_partition(x, window_size: int):
|
| 228 |
+
B, H, W, C = x.shape
|
| 229 |
+
x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
|
| 230 |
+
windows = (
|
| 231 |
+
x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
|
| 232 |
+
)
|
| 233 |
+
return windows
|
| 234 |
+
|
| 235 |
+
|
| 236 |
+
def window_reverse(windows, batch_size: int, window_size: int, H: int, W: int):
|
| 237 |
+
B = batch_size
|
| 238 |
+
# this will cause onnx conversion failed for dynamic axis, because treated as constant
|
| 239 |
+
# int(windows.shape[0] / (H * W / window_size / window_size))
|
| 240 |
+
x = windows.view(
|
| 241 |
+
B, H // window_size, W // window_size, window_size, window_size, -1
|
| 242 |
+
)
|
| 243 |
+
x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
|
| 244 |
+
return x
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
class WindowAttention(nn.Module):
|
| 248 |
+
def __init__(self, dim, num_heads, window_size, qkv_bias=True):
|
| 249 |
+
|
| 250 |
+
super().__init__()
|
| 251 |
+
self.dim = dim
|
| 252 |
+
self.window_size = window_size
|
| 253 |
+
self.num_heads = num_heads
|
| 254 |
+
head_dim = dim // num_heads
|
| 255 |
+
self.scale = float(head_dim) ** -0.5
|
| 256 |
+
|
| 257 |
+
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
|
| 258 |
+
self.proj = nn.Linear(dim, dim)
|
| 259 |
+
|
| 260 |
+
self.softmax = nn.Softmax(dim=-1)
|
| 261 |
+
|
| 262 |
+
def forward(self, x, size):
|
| 263 |
+
|
| 264 |
+
H, W = size
|
| 265 |
+
B, L, C = x.shape
|
| 266 |
+
assert L == H * W, "input feature has wrong size"
|
| 267 |
+
|
| 268 |
+
x = x.view(B, H, W, C)
|
| 269 |
+
|
| 270 |
+
pad_l = pad_t = 0
|
| 271 |
+
pad_r = (self.window_size - W % self.window_size) % self.window_size
|
| 272 |
+
pad_b = (self.window_size - H % self.window_size) % self.window_size
|
| 273 |
+
x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b))
|
| 274 |
+
_, Hp, Wp, _ = x.shape
|
| 275 |
+
|
| 276 |
+
x = window_partition(x, self.window_size)
|
| 277 |
+
x = x.view(-1, self.window_size * self.window_size, C)
|
| 278 |
+
|
| 279 |
+
# W-MSA/SW-MSA
|
| 280 |
+
# attn_windows = self.attn(x_windows)
|
| 281 |
+
|
| 282 |
+
B_, N, C = x.shape
|
| 283 |
+
qkv = (
|
| 284 |
+
self.qkv(x)
|
| 285 |
+
.reshape(B_, N, 3, self.num_heads, C // self.num_heads)
|
| 286 |
+
.permute(2, 0, 3, 1, 4)
|
| 287 |
+
)
|
| 288 |
+
q, k, v = qkv[0], qkv[1], qkv[2]
|
| 289 |
+
|
| 290 |
+
q = q * self.scale
|
| 291 |
+
attn = q @ k.transpose(-2, -1)
|
| 292 |
+
attn = self.softmax(attn)
|
| 293 |
+
|
| 294 |
+
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
|
| 295 |
+
x = self.proj(x)
|
| 296 |
+
|
| 297 |
+
# merge windows
|
| 298 |
+
x = x.view(-1, self.window_size, self.window_size, C)
|
| 299 |
+
x = window_reverse(x, B, self.window_size, Hp, Wp)
|
| 300 |
+
|
| 301 |
+
if pad_r > 0 or pad_b > 0:
|
| 302 |
+
x = x[:, :H, :W, :].contiguous()
|
| 303 |
+
|
| 304 |
+
x = x.view(B, H * W, C)
|
| 305 |
+
|
| 306 |
+
return x, size
|
| 307 |
+
|
| 308 |
+
|
| 309 |
+
class SpatialBlock(nn.Module):
|
| 310 |
+
|
| 311 |
+
def __init__(
|
| 312 |
+
self,
|
| 313 |
+
dim,
|
| 314 |
+
num_heads,
|
| 315 |
+
window_size,
|
| 316 |
+
mlp_ratio=4.0,
|
| 317 |
+
qkv_bias=True,
|
| 318 |
+
drop_path_rate=0.0,
|
| 319 |
+
act_layer=nn.GELU,
|
| 320 |
+
norm_layer=nn.LayerNorm,
|
| 321 |
+
conv_at_attn=True,
|
| 322 |
+
conv_at_ffn=True,
|
| 323 |
+
):
|
| 324 |
+
super().__init__()
|
| 325 |
+
|
| 326 |
+
drop_path = DropPath(drop_path_rate) if drop_path_rate > 0.0 else nn.Identity()
|
| 327 |
+
|
| 328 |
+
self.conv1 = (
|
| 329 |
+
PreNorm(None, DepthWiseConv2d(dim, 3, 1, 1)) if conv_at_attn else None
|
| 330 |
+
)
|
| 331 |
+
self.window_attn = PreNorm(
|
| 332 |
+
norm_layer(dim),
|
| 333 |
+
WindowAttention(dim, num_heads, window_size, qkv_bias=qkv_bias),
|
| 334 |
+
drop_path,
|
| 335 |
+
)
|
| 336 |
+
self.conv2 = (
|
| 337 |
+
PreNorm(None, DepthWiseConv2d(dim, 3, 1, 1)) if conv_at_ffn else None
|
| 338 |
+
)
|
| 339 |
+
self.ffn = PreNorm(
|
| 340 |
+
norm_layer(dim),
|
| 341 |
+
Mlp(
|
| 342 |
+
in_features=dim,
|
| 343 |
+
hidden_features=int(dim * mlp_ratio),
|
| 344 |
+
act_layer=act_layer,
|
| 345 |
+
),
|
| 346 |
+
drop_path,
|
| 347 |
+
)
|
| 348 |
+
|
| 349 |
+
def forward(self, x, size):
|
| 350 |
+
if self.conv1:
|
| 351 |
+
x, size = self.conv1(x, size)
|
| 352 |
+
x, size = self.window_attn(x, size)
|
| 353 |
+
|
| 354 |
+
if self.conv2:
|
| 355 |
+
x, size = self.conv2(x, size)
|
| 356 |
+
x, size = self.ffn(x, size)
|
| 357 |
+
return x, size
|
| 358 |
+
|
| 359 |
+
|
| 360 |
+
class DaViT(nn.Module):
|
| 361 |
+
"""DaViT: Dual-Attention Transformer
|
| 362 |
+
|
| 363 |
+
Args:
|
| 364 |
+
in_chans (int): Number of input image channels. Default: 3.
|
| 365 |
+
num_classes (int): Number of classes for classification head. Default: 1000.
|
| 366 |
+
patch_size (tuple(int)): Patch size of convolution in different stages. Default: (7, 2, 2, 2).
|
| 367 |
+
patch_stride (tuple(int)): Patch stride of convolution in different stages. Default: (4, 2, 2, 2).
|
| 368 |
+
patch_padding (tuple(int)): Patch padding of convolution in different stages. Default: (3, 0, 0, 0).
|
| 369 |
+
patch_prenorm (tuple(bool)): If True, perform norm before convlution layer. Default: (True, False, False, False).
|
| 370 |
+
embed_dims (tuple(int)): Patch embedding dimension in different stages. Default: (64, 128, 192, 256).
|
| 371 |
+
num_heads (tuple(int)): Number of spatial attention heads in different stages. Default: (4, 8, 12, 16).
|
| 372 |
+
num_groups (tuple(int)): Number of channel groups in different stages. Default: (4, 8, 12, 16).
|
| 373 |
+
window_size (int): Window size. Default: 7.
|
| 374 |
+
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
|
| 375 |
+
qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True.
|
| 376 |
+
drop_path_rate (float): Stochastic depth rate. Default: 0.1.
|
| 377 |
+
norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
|
| 378 |
+
enable_checkpoint (bool): If True, enable checkpointing. Default: False.
|
| 379 |
+
conv_at_attn (bool): If True, performe depthwise convolution before attention layer. Default: True.
|
| 380 |
+
conv_at_ffn (bool): If True, performe depthwise convolution before ffn layer. Default: True.
|
| 381 |
+
"""
|
| 382 |
+
|
| 383 |
+
def __init__(
|
| 384 |
+
self,
|
| 385 |
+
in_chans=3,
|
| 386 |
+
num_classes=1000,
|
| 387 |
+
depths=(1, 1, 3, 1),
|
| 388 |
+
patch_size=(7, 2, 2, 2),
|
| 389 |
+
patch_stride=(4, 2, 2, 2),
|
| 390 |
+
patch_padding=(3, 0, 0, 0),
|
| 391 |
+
patch_prenorm=(False, False, False, False),
|
| 392 |
+
embed_dims=(64, 128, 192, 256),
|
| 393 |
+
num_heads=(3, 6, 12, 24),
|
| 394 |
+
num_groups=(3, 6, 12, 24),
|
| 395 |
+
window_size=7,
|
| 396 |
+
mlp_ratio=4.0,
|
| 397 |
+
qkv_bias=True,
|
| 398 |
+
drop_path_rate=0.1,
|
| 399 |
+
norm_layer=nn.LayerNorm,
|
| 400 |
+
enable_checkpoint=False,
|
| 401 |
+
conv_at_attn=True,
|
| 402 |
+
conv_at_ffn=True,
|
| 403 |
+
):
|
| 404 |
+
super().__init__()
|
| 405 |
+
|
| 406 |
+
self.num_classes = num_classes
|
| 407 |
+
self.embed_dims = embed_dims
|
| 408 |
+
self.num_heads = num_heads
|
| 409 |
+
self.num_groups = num_groups
|
| 410 |
+
self.num_stages = len(self.embed_dims)
|
| 411 |
+
self.enable_checkpoint = enable_checkpoint
|
| 412 |
+
assert self.num_stages == len(self.num_heads) == len(self.num_groups)
|
| 413 |
+
|
| 414 |
+
num_stages = len(embed_dims)
|
| 415 |
+
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths) * 2)]
|
| 416 |
+
|
| 417 |
+
depth_offset = 0
|
| 418 |
+
convs = []
|
| 419 |
+
blocks = []
|
| 420 |
+
for i in range(num_stages):
|
| 421 |
+
conv_embed = ConvEmbed(
|
| 422 |
+
patch_size=patch_size[i],
|
| 423 |
+
stride=patch_stride[i],
|
| 424 |
+
padding=patch_padding[i],
|
| 425 |
+
in_chans=in_chans if i == 0 else self.embed_dims[i - 1],
|
| 426 |
+
embed_dim=self.embed_dims[i],
|
| 427 |
+
norm_layer=norm_layer,
|
| 428 |
+
pre_norm=patch_prenorm[i],
|
| 429 |
+
)
|
| 430 |
+
convs.append(conv_embed)
|
| 431 |
+
|
| 432 |
+
block = MySequential(
|
| 433 |
+
*[
|
| 434 |
+
MySequential(
|
| 435 |
+
OrderedDict(
|
| 436 |
+
[
|
| 437 |
+
(
|
| 438 |
+
"spatial_block",
|
| 439 |
+
SpatialBlock(
|
| 440 |
+
embed_dims[i],
|
| 441 |
+
num_heads[i],
|
| 442 |
+
window_size,
|
| 443 |
+
drop_path_rate=dpr[depth_offset + j * 2],
|
| 444 |
+
qkv_bias=qkv_bias,
|
| 445 |
+
mlp_ratio=mlp_ratio,
|
| 446 |
+
conv_at_attn=conv_at_attn,
|
| 447 |
+
conv_at_ffn=conv_at_ffn,
|
| 448 |
+
),
|
| 449 |
+
),
|
| 450 |
+
(
|
| 451 |
+
"channel_block",
|
| 452 |
+
ChannelBlock(
|
| 453 |
+
embed_dims[i],
|
| 454 |
+
num_groups[i],
|
| 455 |
+
drop_path_rate=dpr[depth_offset + j * 2 + 1],
|
| 456 |
+
qkv_bias=qkv_bias,
|
| 457 |
+
mlp_ratio=mlp_ratio,
|
| 458 |
+
conv_at_attn=conv_at_attn,
|
| 459 |
+
conv_at_ffn=conv_at_ffn,
|
| 460 |
+
),
|
| 461 |
+
),
|
| 462 |
+
]
|
| 463 |
+
)
|
| 464 |
+
)
|
| 465 |
+
for j in range(depths[i])
|
| 466 |
+
]
|
| 467 |
+
)
|
| 468 |
+
blocks.append(block)
|
| 469 |
+
depth_offset += depths[i] * 2
|
| 470 |
+
|
| 471 |
+
self.convs = nn.ModuleList(convs)
|
| 472 |
+
self.blocks = nn.ModuleList(blocks)
|
| 473 |
+
|
| 474 |
+
self.norms = norm_layer(self.embed_dims[-1])
|
| 475 |
+
self.avgpool = nn.AdaptiveAvgPool1d(1)
|
| 476 |
+
self.head = (
|
| 477 |
+
nn.Linear(self.embed_dims[-1], num_classes)
|
| 478 |
+
if num_classes > 0
|
| 479 |
+
else nn.Identity()
|
| 480 |
+
)
|
| 481 |
+
|
| 482 |
+
# self.apply(self._init_weights)
|
| 483 |
+
|
| 484 |
+
@property
|
| 485 |
+
def dim_out(self):
|
| 486 |
+
return self.embed_dims[-1]
|
| 487 |
+
|
| 488 |
+
def _init_weights(self, m):
|
| 489 |
+
if isinstance(m, nn.Linear):
|
| 490 |
+
trunc_normal_(m.weight, std=0.02)
|
| 491 |
+
if m.bias is not None:
|
| 492 |
+
nn.init.constant_(m.bias, 0)
|
| 493 |
+
elif isinstance(m, nn.Conv2d):
|
| 494 |
+
nn.init.normal_(m.weight, std=0.02)
|
| 495 |
+
for name, _ in m.named_parameters():
|
| 496 |
+
if name in ["bias"]:
|
| 497 |
+
nn.init.constant_(m.bias, 0)
|
| 498 |
+
elif isinstance(m, nn.LayerNorm):
|
| 499 |
+
nn.init.constant_(m.weight, 1.0)
|
| 500 |
+
nn.init.constant_(m.bias, 0)
|
| 501 |
+
elif isinstance(m, nn.BatchNorm2d):
|
| 502 |
+
nn.init.constant_(m.weight, 1.0)
|
| 503 |
+
nn.init.constant_(m.bias, 0)
|
| 504 |
+
|
| 505 |
+
def forward_features_unpool(self, x):
|
| 506 |
+
"""
|
| 507 |
+
forward until avg pooling
|
| 508 |
+
Args:
|
| 509 |
+
x (_type_): input image tensor
|
| 510 |
+
"""
|
| 511 |
+
input_size = (x.size(2), x.size(3))
|
| 512 |
+
for conv, block in zip(self.convs, self.blocks):
|
| 513 |
+
x, input_size = conv(x, input_size)
|
| 514 |
+
if self.enable_checkpoint:
|
| 515 |
+
x, input_size = checkpoint.checkpoint(block, x, input_size)
|
| 516 |
+
else:
|
| 517 |
+
x, input_size = block(x, input_size)
|
| 518 |
+
return x
|
| 519 |
+
|
| 520 |
+
def forward_features(self, x):
|
| 521 |
+
x = self.forward_features_unpool(x)
|
| 522 |
+
|
| 523 |
+
# (batch_size, num_tokens, token_dim)
|
| 524 |
+
x = self.avgpool(x.transpose(1, 2))
|
| 525 |
+
# (batch_size, 1, num_tokens)
|
| 526 |
+
x = torch.flatten(x, 1)
|
| 527 |
+
x = self.norms(x)
|
| 528 |
+
|
| 529 |
+
return x
|
| 530 |
+
|
| 531 |
+
def forward(self, x):
|
| 532 |
+
x = self.forward_features(x)
|
| 533 |
+
x = self.head(x)
|
| 534 |
+
return x
|
| 535 |
+
|
| 536 |
+
@classmethod
|
| 537 |
+
def from_config(cls, config):
|
| 538 |
+
return cls(
|
| 539 |
+
depths=config.depths,
|
| 540 |
+
embed_dims=config.dim_embed,
|
| 541 |
+
num_heads=config.num_heads,
|
| 542 |
+
num_groups=config.num_groups,
|
| 543 |
+
patch_size=config.patch_size,
|
| 544 |
+
patch_stride=config.patch_stride,
|
| 545 |
+
patch_padding=config.patch_padding,
|
| 546 |
+
patch_prenorm=config.patch_prenorm,
|
| 547 |
+
drop_path_rate=config.drop_path_rate,
|
| 548 |
+
window_size=config.window_size,
|
| 549 |
+
)
|
| 550 |
+
|
| 551 |
+
|
| 552 |
+
class DaViTVisionTower(nn.Module):
|
| 553 |
+
def __init__(self, vision_tower, args, delay_load=False):
|
| 554 |
+
super().__init__()
|
| 555 |
+
|
| 556 |
+
self.is_loaded = False
|
| 557 |
+
self.image_size = getattr(args, "size", 768)
|
| 558 |
+
self.vision_tower_name = vision_tower
|
| 559 |
+
self.select_layer = args.mm_vision_select_layer
|
| 560 |
+
self.select_feature = getattr(args, "mm_vision_select_feature", "patch")
|
| 561 |
+
self.config = AutoConfig.from_pretrained(
|
| 562 |
+
self.vision_tower_name, trust_remote_code=True
|
| 563 |
+
).vision_config
|
| 564 |
+
if not delay_load:
|
| 565 |
+
self.load_model()
|
| 566 |
+
elif getattr(args, "unfreeze_mm_vision_tower", False):
|
| 567 |
+
self.load_model()
|
| 568 |
+
else:
|
| 569 |
+
self.cfg_only = self.config
|
| 570 |
+
|
| 571 |
+
def load_model(self, device_map=None):
|
| 572 |
+
if self.is_loaded:
|
| 573 |
+
print(
|
| 574 |
+
"{} is already loaded, `load_model` called again, skipping.".format(
|
| 575 |
+
self.vision_tower_name
|
| 576 |
+
)
|
| 577 |
+
)
|
| 578 |
+
return
|
| 579 |
+
self.vision_tower = DaViT.from_config(config=self.config)
|
| 580 |
+
del self.vision_tower.head
|
| 581 |
+
del self.vision_tower.norms
|
| 582 |
+
self.image_processor = CLIPImageProcessor.from_pretrained(
|
| 583 |
+
self.vision_tower_name
|
| 584 |
+
)
|
| 585 |
+
self.vision_tower.requires_grad_(False)
|
| 586 |
+
self.is_loaded = True
|
| 587 |
+
|
| 588 |
+
def feature_select(self, image_forward_outs):
|
| 589 |
+
image_features = image_forward_outs
|
| 590 |
+
if self.select_feature == "patch":
|
| 591 |
+
image_features = image_features[:, 1:]
|
| 592 |
+
elif self.select_feature == "cls_patch":
|
| 593 |
+
image_features = image_features
|
| 594 |
+
else:
|
| 595 |
+
raise ValueError(f"Unexpected select feature: {self.select_feature}")
|
| 596 |
+
return image_features
|
| 597 |
+
|
| 598 |
+
@torch.no_grad()
|
| 599 |
+
def forward(self, images):
|
| 600 |
+
if type(images) is list:
|
| 601 |
+
image_features = []
|
| 602 |
+
for image in images:
|
| 603 |
+
image_forward_out = self.vision_tower.forward_features_unpool(
|
| 604 |
+
image.to(device=self.device, dtype=self.dtype).unsqueeze(0)
|
| 605 |
+
)
|
| 606 |
+
image_feature = self.feature_select(image_forward_out).to(image.dtype)
|
| 607 |
+
image_features.append(image_forward_out)
|
| 608 |
+
else:
|
| 609 |
+
image_forward_outs = self.vision_tower.forward_features_unpool(
|
| 610 |
+
images.to(device=self.device, dtype=self.dtype)
|
| 611 |
+
)
|
| 612 |
+
image_features = self.feature_select(image_forward_outs).to(images.dtype)
|
| 613 |
+
return image_features
|
| 614 |
+
|
| 615 |
+
@property
|
| 616 |
+
def dummy_feature(self):
|
| 617 |
+
return torch.zeros(1, self.hidden_size, device=self.device, dtype=self.dtype)
|
| 618 |
+
|
| 619 |
+
@property
|
| 620 |
+
def dtype(self):
|
| 621 |
+
for n, p in self.vision_tower.named_parameters():
|
| 622 |
+
dtype = p.dtype
|
| 623 |
+
break
|
| 624 |
+
return dtype
|
| 625 |
+
|
| 626 |
+
@property
|
| 627 |
+
def device(self):
|
| 628 |
+
for n, p in self.vision_tower.named_parameters():
|
| 629 |
+
device = p.device
|
| 630 |
+
break
|
| 631 |
+
return device
|
| 632 |
+
|
| 633 |
+
@property
|
| 634 |
+
def hidden_size(self):
|
| 635 |
+
return self.config.dim_embed[-1]
|
| 636 |
+
|
| 637 |
+
@property
|
| 638 |
+
def num_patches_per_side(self):
|
| 639 |
+
return self.config.image_size // self.config.patch_size
|
| 640 |
+
|
| 641 |
+
@property
|
| 642 |
+
def num_patches(self):
|
| 643 |
+
return (self.config.image_size // self.config.patch_size) ** 2
|
| 644 |
+
|
| 645 |
+
|
| 646 |
+
from abc import ABC, abstractmethod
|
| 647 |
+
|
| 648 |
+
|
| 649 |
+
IGNORE_INDEX = -100
|
| 650 |
+
IMAGE_TOKEN_INDEX = -200
|
| 651 |
+
DEFAULT_IMAGE_PATCH_TOKEN = "<im_patch>"
|
| 652 |
+
DEFAULT_IM_START_TOKEN = "<im_start>"
|
| 653 |
+
DEFAULT_IM_END_TOKEN = "<im_end>"
|
| 654 |
+
|
| 655 |
+
|
| 656 |
+
def build_vision_tower(vision_tower_cfg, **kwargs):
|
| 657 |
+
vision_tower = getattr(
|
| 658 |
+
vision_tower_cfg,
|
| 659 |
+
"mm_vision_tower",
|
| 660 |
+
getattr(vision_tower_cfg, "vision_tower", None),
|
| 661 |
+
)
|
| 662 |
+
return DaViTVisionTower(vision_tower, args=vision_tower_cfg, **kwargs)
|
| 663 |
+
|
| 664 |
+
|
| 665 |
+
import re
|
| 666 |
+
def build_vision_projector(config, delay_load=False, **kwargs):
|
| 667 |
+
projector_type = getattr(config, "mm_projector_type", "linear")
|
| 668 |
+
|
| 669 |
+
mlp_gelu_match = re.match(r"^mlp(\d+)x_gelu$", projector_type)
|
| 670 |
+
if mlp_gelu_match:
|
| 671 |
+
mlp_depth = int(mlp_gelu_match.group(1))
|
| 672 |
+
modules = [nn.Linear(config.mm_hidden_size, config.hidden_size)]
|
| 673 |
+
for _ in range(1, mlp_depth):
|
| 674 |
+
modules.append(nn.GELU())
|
| 675 |
+
modules.append(nn.Linear(config.hidden_size, config.hidden_size))
|
| 676 |
+
return nn.Sequential(*modules)
|
| 677 |
+
|
| 678 |
+
|
| 679 |
+
class MixsenseMetaModel:
|
| 680 |
+
|
| 681 |
+
def __init__(self, config):
|
| 682 |
+
super(MixsenseMetaModel, self).__init__(config)
|
| 683 |
+
|
| 684 |
+
if hasattr(config, "mm_vision_tower"):
|
| 685 |
+
self.vision_tower = build_vision_tower(config, delay_load=True)
|
| 686 |
+
self.mm_projector = build_vision_projector(config)
|
| 687 |
+
|
| 688 |
+
if "unpad" in getattr(config, "mm_patch_merge_type", ""):
|
| 689 |
+
self.image_newline = nn.Parameter(
|
| 690 |
+
torch.empty(config.hidden_size, dtype=self.dtype)
|
| 691 |
+
)
|
| 692 |
+
|
| 693 |
+
def get_vision_tower(self):
|
| 694 |
+
vision_tower = getattr(self, "vision_tower", None)
|
| 695 |
+
if type(vision_tower) is list:
|
| 696 |
+
vision_tower = vision_tower[0]
|
| 697 |
+
return vision_tower
|
| 698 |
+
|
| 699 |
+
def initialize_vision_modules(self, model_args, fsdp=None):
|
| 700 |
+
vision_tower = model_args.vision_tower
|
| 701 |
+
mm_vision_select_layer = model_args.mm_vision_select_layer
|
| 702 |
+
mm_vision_select_feature = model_args.mm_vision_select_feature
|
| 703 |
+
pretrain_mm_mlp_adapter = model_args.pretrain_mm_mlp_adapter
|
| 704 |
+
mm_patch_merge_type = model_args.mm_patch_merge_type
|
| 705 |
+
|
| 706 |
+
self.config.mm_vision_tower = vision_tower
|
| 707 |
+
|
| 708 |
+
if self.get_vision_tower() is None:
|
| 709 |
+
vision_tower = build_vision_tower(model_args)
|
| 710 |
+
|
| 711 |
+
if fsdp is not None and len(fsdp) > 0:
|
| 712 |
+
self.vision_tower = [vision_tower]
|
| 713 |
+
else:
|
| 714 |
+
self.vision_tower = vision_tower
|
| 715 |
+
else:
|
| 716 |
+
if fsdp is not None and len(fsdp) > 0:
|
| 717 |
+
vision_tower = self.vision_tower[0]
|
| 718 |
+
else:
|
| 719 |
+
vision_tower = self.vision_tower
|
| 720 |
+
vision_tower.load_model()
|
| 721 |
+
|
| 722 |
+
self.config.use_mm_proj = True
|
| 723 |
+
self.config.mm_projector_type = getattr(
|
| 724 |
+
model_args, "mm_projector_type", "linear"
|
| 725 |
+
)
|
| 726 |
+
self.config.mm_hidden_size = vision_tower.hidden_size
|
| 727 |
+
self.config.mm_vision_select_layer = mm_vision_select_layer
|
| 728 |
+
self.config.mm_vision_select_feature = mm_vision_select_feature
|
| 729 |
+
self.config.mm_patch_merge_type = mm_patch_merge_type
|
| 730 |
+
|
| 731 |
+
if getattr(self, "mm_projector", None) is None:
|
| 732 |
+
self.mm_projector = build_vision_projector(self.config)
|
| 733 |
+
|
| 734 |
+
if "unpad" in mm_patch_merge_type:
|
| 735 |
+
embed_std = 1 / torch.sqrt(
|
| 736 |
+
torch.tensor(self.config.hidden_size, dtype=self.dtype)
|
| 737 |
+
)
|
| 738 |
+
self.image_newline = nn.Parameter(
|
| 739 |
+
torch.randn(self.config.hidden_size, dtype=self.dtype) * embed_std
|
| 740 |
+
)
|
| 741 |
+
else:
|
| 742 |
+
# In case it is frozen by LoRA
|
| 743 |
+
for p in self.mm_projector.parameters():
|
| 744 |
+
p.requires_grad = True
|
| 745 |
+
|
| 746 |
+
if pretrain_mm_mlp_adapter is not None:
|
| 747 |
+
mm_projector_weights = torch.load(
|
| 748 |
+
pretrain_mm_mlp_adapter, map_location="cpu"
|
| 749 |
+
)
|
| 750 |
+
|
| 751 |
+
def get_w(weights, keyword):
|
| 752 |
+
return {
|
| 753 |
+
k.split(keyword + ".")[1]: v
|
| 754 |
+
for k, v in weights.items()
|
| 755 |
+
if keyword in k
|
| 756 |
+
}
|
| 757 |
+
|
| 758 |
+
self.mm_projector.load_state_dict(
|
| 759 |
+
get_w(mm_projector_weights, "mm_projector")
|
| 760 |
+
)
|
| 761 |
+
|
| 762 |
+
|
| 763 |
+
class MixsenseMetaForCausalLM(ABC):
|
| 764 |
+
|
| 765 |
+
@abstractmethod
|
| 766 |
+
def get_model(self):
|
| 767 |
+
pass
|
| 768 |
+
|
| 769 |
+
def get_vision_tower(self):
|
| 770 |
+
return self.get_model().get_vision_tower()
|
| 771 |
+
|
| 772 |
+
def encode_images(self, images):
|
| 773 |
+
image_features = self.get_model().get_vision_tower()(images)
|
| 774 |
+
image_features = self.get_model().mm_projector(image_features)
|
| 775 |
+
return image_features
|
| 776 |
+
|
| 777 |
+
def prepare_inputs_labels_for_multimodal(
|
| 778 |
+
self,
|
| 779 |
+
input_ids,
|
| 780 |
+
position_ids,
|
| 781 |
+
attention_mask,
|
| 782 |
+
past_key_values,
|
| 783 |
+
labels,
|
| 784 |
+
images,
|
| 785 |
+
image_sizes=None,
|
| 786 |
+
):
|
| 787 |
+
vision_tower = self.get_vision_tower()
|
| 788 |
+
if vision_tower is None or images is None or input_ids.shape[1] == 1:
|
| 789 |
+
return (
|
| 790 |
+
input_ids,
|
| 791 |
+
position_ids,
|
| 792 |
+
attention_mask,
|
| 793 |
+
past_key_values,
|
| 794 |
+
None,
|
| 795 |
+
labels,
|
| 796 |
+
)
|
| 797 |
+
elif type(images) is list or images.ndim == 5:
|
| 798 |
+
if type(images) is list:
|
| 799 |
+
images = [x.unsqueeze(0) if x.ndim == 3 else x for x in images]
|
| 800 |
+
concat_images = torch.cat([image for image in images], dim=0)
|
| 801 |
+
image_features = self.encode_images(concat_images)
|
| 802 |
+
split_sizes = [image.shape[0] for image in images]
|
| 803 |
+
image_features = torch.split(image_features, split_sizes, dim=0)
|
| 804 |
+
mm_patch_merge_type = getattr(self.config, "mm_patch_merge_type", "flat")
|
| 805 |
+
image_aspect_ratio = getattr(self.config, "image_aspect_ratio", "square")
|
| 806 |
+
if mm_patch_merge_type == "flat":
|
| 807 |
+
image_features = [x.flatten(0, 1) for x in image_features]
|
| 808 |
+
else:
|
| 809 |
+
image_features = self.encode_images(images)
|
| 810 |
+
|
| 811 |
+
# TODO: image start / end is not implemented here to support pretraining.
|
| 812 |
+
if getattr(self.config, "tune_mm_mlp_adapter", False) and getattr(
|
| 813 |
+
self.config, "mm_use_im_start_end", False
|
| 814 |
+
):
|
| 815 |
+
raise NotImplementedError
|
| 816 |
+
|
| 817 |
+
# Let's just add dummy tensors if they do not exist,
|
| 818 |
+
# it is a headache to deal with None all the time.
|
| 819 |
+
# But it is not ideal, and if you have a better idea,
|
| 820 |
+
# please open an issue / submit a PR, thanks.
|
| 821 |
+
_labels = labels
|
| 822 |
+
_position_ids = position_ids
|
| 823 |
+
_attention_mask = attention_mask
|
| 824 |
+
if attention_mask is None:
|
| 825 |
+
attention_mask = torch.ones_like(input_ids, dtype=torch.bool)
|
| 826 |
+
else:
|
| 827 |
+
attention_mask = attention_mask.bool()
|
| 828 |
+
if position_ids is None:
|
| 829 |
+
position_ids = torch.arange(
|
| 830 |
+
0, input_ids.shape[1], dtype=torch.long, device=input_ids.device
|
| 831 |
+
)
|
| 832 |
+
if labels is None:
|
| 833 |
+
labels = torch.full_like(input_ids, IGNORE_INDEX)
|
| 834 |
+
|
| 835 |
+
# remove the padding using attention_mask -- FIXME
|
| 836 |
+
_input_ids = input_ids
|
| 837 |
+
input_ids = [
|
| 838 |
+
cur_input_ids[cur_attention_mask]
|
| 839 |
+
for cur_input_ids, cur_attention_mask in zip(input_ids, attention_mask)
|
| 840 |
+
]
|
| 841 |
+
labels = [
|
| 842 |
+
cur_labels[cur_attention_mask]
|
| 843 |
+
for cur_labels, cur_attention_mask in zip(labels, attention_mask)
|
| 844 |
+
]
|
| 845 |
+
|
| 846 |
+
new_input_embeds = []
|
| 847 |
+
new_labels = []
|
| 848 |
+
cur_image_idx = 0
|
| 849 |
+
for batch_idx, cur_input_ids in enumerate(input_ids):
|
| 850 |
+
num_images = (cur_input_ids == IMAGE_TOKEN_INDEX).sum()
|
| 851 |
+
if num_images == 0:
|
| 852 |
+
cur_image_features = image_features[cur_image_idx]
|
| 853 |
+
cur_input_embeds_1 = self.get_model().embed_tokens(cur_input_ids)
|
| 854 |
+
cur_input_embeds = torch.cat(
|
| 855 |
+
[cur_input_embeds_1, cur_image_features[0:0]], dim=0
|
| 856 |
+
)
|
| 857 |
+
new_input_embeds.append(cur_input_embeds)
|
| 858 |
+
new_labels.append(labels[batch_idx])
|
| 859 |
+
cur_image_idx += 1
|
| 860 |
+
continue
|
| 861 |
+
|
| 862 |
+
image_token_indices = (
|
| 863 |
+
[-1]
|
| 864 |
+
+ torch.where(cur_input_ids == IMAGE_TOKEN_INDEX)[0].tolist()
|
| 865 |
+
+ [cur_input_ids.shape[0]]
|
| 866 |
+
)
|
| 867 |
+
cur_input_ids_noim = []
|
| 868 |
+
cur_labels = labels[batch_idx]
|
| 869 |
+
cur_labels_noim = []
|
| 870 |
+
for i in range(len(image_token_indices) - 1):
|
| 871 |
+
cur_input_ids_noim.append(
|
| 872 |
+
cur_input_ids[
|
| 873 |
+
image_token_indices[i] + 1 : image_token_indices[i + 1]
|
| 874 |
+
]
|
| 875 |
+
)
|
| 876 |
+
cur_labels_noim.append(
|
| 877 |
+
cur_labels[image_token_indices[i] + 1 : image_token_indices[i + 1]]
|
| 878 |
+
)
|
| 879 |
+
split_sizes = [x.shape[0] for x in cur_labels_noim]
|
| 880 |
+
cur_input_embeds = self.get_model().embed_tokens(
|
| 881 |
+
torch.cat(cur_input_ids_noim)
|
| 882 |
+
)
|
| 883 |
+
|
| 884 |
+
cur_input_embeds_no_im = torch.split(cur_input_embeds, split_sizes, dim=0)
|
| 885 |
+
cur_new_input_embeds = []
|
| 886 |
+
cur_new_labels = []
|
| 887 |
+
|
| 888 |
+
for i in range(num_images + 1):
|
| 889 |
+
cur_new_input_embeds.append(cur_input_embeds_no_im[i])
|
| 890 |
+
cur_new_labels.append(cur_labels_noim[i])
|
| 891 |
+
if i < num_images:
|
| 892 |
+
cur_image_features = image_features[cur_image_idx]
|
| 893 |
+
cur_image_idx += 1
|
| 894 |
+
cur_new_input_embeds.append(cur_image_features)
|
| 895 |
+
cur_new_labels.append(
|
| 896 |
+
torch.full(
|
| 897 |
+
(cur_image_features.shape[0],),
|
| 898 |
+
IGNORE_INDEX,
|
| 899 |
+
device=cur_labels.device,
|
| 900 |
+
dtype=cur_labels.dtype,
|
| 901 |
+
)
|
| 902 |
+
)
|
| 903 |
+
|
| 904 |
+
cur_new_input_embeds = [x.to(self.device) for x in cur_new_input_embeds]
|
| 905 |
+
|
| 906 |
+
cur_new_input_embeds = torch.cat(cur_new_input_embeds)
|
| 907 |
+
cur_new_labels = torch.cat(cur_new_labels)
|
| 908 |
+
|
| 909 |
+
new_input_embeds.append(cur_new_input_embeds)
|
| 910 |
+
new_labels.append(cur_new_labels)
|
| 911 |
+
|
| 912 |
+
# Truncate sequences to max length as image embeddings can make the sequence longer
|
| 913 |
+
tokenizer_model_max_length = getattr(
|
| 914 |
+
self.config, "tokenizer_model_max_length", None
|
| 915 |
+
)
|
| 916 |
+
if tokenizer_model_max_length is not None:
|
| 917 |
+
new_input_embeds = [
|
| 918 |
+
x[:tokenizer_model_max_length] for x in new_input_embeds
|
| 919 |
+
]
|
| 920 |
+
new_labels = [x[:tokenizer_model_max_length] for x in new_labels]
|
| 921 |
+
|
| 922 |
+
# Combine them
|
| 923 |
+
max_len = max(x.shape[0] for x in new_input_embeds)
|
| 924 |
+
batch_size = len(new_input_embeds)
|
| 925 |
+
|
| 926 |
+
new_input_embeds_padded = []
|
| 927 |
+
new_labels_padded = torch.full(
|
| 928 |
+
(batch_size, max_len),
|
| 929 |
+
IGNORE_INDEX,
|
| 930 |
+
dtype=new_labels[0].dtype,
|
| 931 |
+
device=new_labels[0].device,
|
| 932 |
+
)
|
| 933 |
+
attention_mask = torch.zeros(
|
| 934 |
+
(batch_size, max_len),
|
| 935 |
+
dtype=attention_mask.dtype,
|
| 936 |
+
device=attention_mask.device,
|
| 937 |
+
)
|
| 938 |
+
position_ids = torch.zeros(
|
| 939 |
+
(batch_size, max_len), dtype=position_ids.dtype, device=position_ids.device
|
| 940 |
+
)
|
| 941 |
+
|
| 942 |
+
for i, (cur_new_embed, cur_new_labels) in enumerate(
|
| 943 |
+
zip(new_input_embeds, new_labels)
|
| 944 |
+
):
|
| 945 |
+
cur_len = cur_new_embed.shape[0]
|
| 946 |
+
if getattr(self.config, "tokenizer_padding_side", "right") == "left":
|
| 947 |
+
new_input_embeds_padded.append(
|
| 948 |
+
torch.cat(
|
| 949 |
+
(
|
| 950 |
+
torch.zeros(
|
| 951 |
+
(max_len - cur_len, cur_new_embed.shape[1]),
|
| 952 |
+
dtype=cur_new_embed.dtype,
|
| 953 |
+
device=cur_new_embed.device,
|
| 954 |
+
),
|
| 955 |
+
cur_new_embed,
|
| 956 |
+
),
|
| 957 |
+
dim=0,
|
| 958 |
+
)
|
| 959 |
+
)
|
| 960 |
+
if cur_len > 0:
|
| 961 |
+
new_labels_padded[i, -cur_len:] = cur_new_labels
|
| 962 |
+
attention_mask[i, -cur_len:] = True
|
| 963 |
+
position_ids[i, -cur_len:] = torch.arange(
|
| 964 |
+
0, cur_len, dtype=position_ids.dtype, device=position_ids.device
|
| 965 |
+
)
|
| 966 |
+
else:
|
| 967 |
+
new_input_embeds_padded.append(
|
| 968 |
+
torch.cat(
|
| 969 |
+
(
|
| 970 |
+
cur_new_embed,
|
| 971 |
+
torch.zeros(
|
| 972 |
+
(max_len - cur_len, cur_new_embed.shape[1]),
|
| 973 |
+
dtype=cur_new_embed.dtype,
|
| 974 |
+
device=cur_new_embed.device,
|
| 975 |
+
),
|
| 976 |
+
),
|
| 977 |
+
dim=0,
|
| 978 |
+
)
|
| 979 |
+
)
|
| 980 |
+
if cur_len > 0:
|
| 981 |
+
new_labels_padded[i, :cur_len] = cur_new_labels
|
| 982 |
+
attention_mask[i, :cur_len] = True
|
| 983 |
+
position_ids[i, :cur_len] = torch.arange(
|
| 984 |
+
0, cur_len, dtype=position_ids.dtype, device=position_ids.device
|
| 985 |
+
)
|
| 986 |
+
|
| 987 |
+
new_input_embeds = torch.stack(new_input_embeds_padded, dim=0)
|
| 988 |
+
|
| 989 |
+
if _labels is None:
|
| 990 |
+
new_labels = None
|
| 991 |
+
else:
|
| 992 |
+
new_labels = new_labels_padded
|
| 993 |
+
|
| 994 |
+
if _attention_mask is None:
|
| 995 |
+
attention_mask = None
|
| 996 |
+
else:
|
| 997 |
+
attention_mask = attention_mask.to(dtype=_attention_mask.dtype)
|
| 998 |
+
|
| 999 |
+
if _position_ids is None:
|
| 1000 |
+
position_ids = None
|
| 1001 |
+
|
| 1002 |
+
return (
|
| 1003 |
+
None,
|
| 1004 |
+
position_ids,
|
| 1005 |
+
attention_mask,
|
| 1006 |
+
past_key_values,
|
| 1007 |
+
new_input_embeds,
|
| 1008 |
+
new_labels,
|
| 1009 |
+
)
|
| 1010 |
+
|
| 1011 |
+
def initialize_vision_tokenizer(self, model_args, tokenizer):
|
| 1012 |
+
if model_args.mm_use_im_patch_token:
|
| 1013 |
+
tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True)
|
| 1014 |
+
self.resize_token_embeddings(len(tokenizer))
|
| 1015 |
+
|
| 1016 |
+
if model_args.mm_use_im_start_end:
|
| 1017 |
+
num_new_tokens = tokenizer.add_tokens(
|
| 1018 |
+
[DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True
|
| 1019 |
+
)
|
| 1020 |
+
self.resize_token_embeddings(len(tokenizer))
|
| 1021 |
+
|
| 1022 |
+
if num_new_tokens > 0:
|
| 1023 |
+
input_embeddings = self.get_input_embeddings().weight.data
|
| 1024 |
+
output_embeddings = self.get_output_embeddings().weight.data
|
| 1025 |
+
|
| 1026 |
+
input_embeddings_avg = input_embeddings[:-num_new_tokens].mean(
|
| 1027 |
+
dim=0, keepdim=True
|
| 1028 |
+
)
|
| 1029 |
+
output_embeddings_avg = output_embeddings[:-num_new_tokens].mean(
|
| 1030 |
+
dim=0, keepdim=True
|
| 1031 |
+
)
|
| 1032 |
+
|
| 1033 |
+
input_embeddings[-num_new_tokens:] = input_embeddings_avg
|
| 1034 |
+
output_embeddings[-num_new_tokens:] = output_embeddings_avg
|
| 1035 |
+
|
| 1036 |
+
if model_args.tune_mm_mlp_adapter:
|
| 1037 |
+
for p in self.get_input_embeddings().parameters():
|
| 1038 |
+
p.requires_grad = True
|
| 1039 |
+
for p in self.get_output_embeddings().parameters():
|
| 1040 |
+
p.requires_grad = False
|
| 1041 |
+
|
| 1042 |
+
if model_args.pretrain_mm_mlp_adapter:
|
| 1043 |
+
mm_projector_weights = torch.load(
|
| 1044 |
+
model_args.pretrain_mm_mlp_adapter, map_location="cpu"
|
| 1045 |
+
)
|
| 1046 |
+
embed_tokens_weight = mm_projector_weights["model.embed_tokens.weight"]
|
| 1047 |
+
assert num_new_tokens == 2
|
| 1048 |
+
if input_embeddings.shape == embed_tokens_weight.shape:
|
| 1049 |
+
input_embeddings[-num_new_tokens:] = embed_tokens_weight[
|
| 1050 |
+
-num_new_tokens:
|
| 1051 |
+
]
|
| 1052 |
+
elif embed_tokens_weight.shape[0] == num_new_tokens:
|
| 1053 |
+
input_embeddings[-num_new_tokens:] = embed_tokens_weight
|
| 1054 |
+
else:
|
| 1055 |
+
raise ValueError(
|
| 1056 |
+
f"Unexpected embed_tokens_weight shape. Pretrained: {embed_tokens_weight.shape}. Current: {input_embeddings.shape}. Numer of new tokens: {num_new_tokens}."
|
| 1057 |
+
)
|
| 1058 |
+
elif model_args.mm_use_im_patch_token:
|
| 1059 |
+
if model_args.tune_mm_mlp_adapter:
|
| 1060 |
+
for p in self.get_input_embeddings().parameters():
|
| 1061 |
+
p.requires_grad = False
|
| 1062 |
+
for p in self.get_output_embeddings().parameters():
|
| 1063 |
+
p.requires_grad = False
|
| 1064 |
+
|
| 1065 |
+
from typing import List, Optional, Tuple, Union
|
| 1066 |
+
from transformers import (
|
| 1067 |
+
AutoConfig,
|
| 1068 |
+
AutoModelForCausalLM,
|
| 1069 |
+
LlamaConfig,
|
| 1070 |
+
LlamaModel,
|
| 1071 |
+
LlamaForCausalLM,
|
| 1072 |
+
)
|
| 1073 |
+
from transformers.modeling_outputs import CausalLMOutputWithPast
|
| 1074 |
+
from transformers.generation.utils import GenerateOutput
|
| 1075 |
+
|
| 1076 |
+
|
| 1077 |
+
class MixsenseConfig(LlamaConfig):
|
| 1078 |
+
model_type = "mixsense_llama"
|
| 1079 |
+
|
| 1080 |
+
|
| 1081 |
+
class MixsenseLlamaModel(MixsenseMetaModel, LlamaModel):
|
| 1082 |
+
config_class = MixsenseConfig
|
| 1083 |
+
|
| 1084 |
+
def __init__(self, config: LlamaConfig):
|
| 1085 |
+
super(MixsenseLlamaModel, self).__init__(config)
|
| 1086 |
+
|
| 1087 |
+
|
| 1088 |
+
class MixsenseLlamaForCausalLM(LlamaForCausalLM, MixsenseMetaForCausalLM):
|
| 1089 |
+
config_class = MixsenseConfig
|
| 1090 |
+
|
| 1091 |
+
def __init__(self, config):
|
| 1092 |
+
super(LlamaForCausalLM, self).__init__(config)
|
| 1093 |
+
self.model = MixsenseLlamaModel(config)
|
| 1094 |
+
self.pretraining_tp = config.pretraining_tp
|
| 1095 |
+
self.vocab_size = config.vocab_size
|
| 1096 |
+
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
|
| 1097 |
+
|
| 1098 |
+
# Initialize weights and apply final processing
|
| 1099 |
+
self.post_init()
|
| 1100 |
+
|
| 1101 |
+
def get_model(self):
|
| 1102 |
+
return self.model
|
| 1103 |
+
|
| 1104 |
+
def forward(
|
| 1105 |
+
self,
|
| 1106 |
+
input_ids: torch.LongTensor = None,
|
| 1107 |
+
attention_mask: Optional[torch.Tensor] = None,
|
| 1108 |
+
position_ids: Optional[torch.LongTensor] = None,
|
| 1109 |
+
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
| 1110 |
+
inputs_embeds: Optional[torch.FloatTensor] = None,
|
| 1111 |
+
labels: Optional[torch.LongTensor] = None,
|
| 1112 |
+
use_cache: Optional[bool] = None,
|
| 1113 |
+
output_attentions: Optional[bool] = None,
|
| 1114 |
+
output_hidden_states: Optional[bool] = None,
|
| 1115 |
+
images: Optional[torch.FloatTensor] = None,
|
| 1116 |
+
image_sizes: Optional[List[List[int]]] = None,
|
| 1117 |
+
return_dict: Optional[bool] = None,
|
| 1118 |
+
) -> Union[Tuple, CausalLMOutputWithPast]:
|
| 1119 |
+
if inputs_embeds is None:
|
| 1120 |
+
(
|
| 1121 |
+
input_ids,
|
| 1122 |
+
position_ids,
|
| 1123 |
+
attention_mask,
|
| 1124 |
+
past_key_values,
|
| 1125 |
+
inputs_embeds,
|
| 1126 |
+
labels,
|
| 1127 |
+
) = self.prepare_inputs_labels_for_multimodal(
|
| 1128 |
+
input_ids,
|
| 1129 |
+
position_ids,
|
| 1130 |
+
attention_mask,
|
| 1131 |
+
past_key_values,
|
| 1132 |
+
labels,
|
| 1133 |
+
images,
|
| 1134 |
+
image_sizes,
|
| 1135 |
+
)
|
| 1136 |
+
return super().forward(
|
| 1137 |
+
input_ids=input_ids,
|
| 1138 |
+
attention_mask=attention_mask,
|
| 1139 |
+
position_ids=position_ids,
|
| 1140 |
+
past_key_values=past_key_values,
|
| 1141 |
+
inputs_embeds=inputs_embeds,
|
| 1142 |
+
labels=labels,
|
| 1143 |
+
use_cache=use_cache,
|
| 1144 |
+
output_attentions=output_attentions,
|
| 1145 |
+
output_hidden_states=output_hidden_states,
|
| 1146 |
+
return_dict=return_dict,
|
| 1147 |
+
)
|
| 1148 |
+
|
| 1149 |
+
@torch.no_grad()
|
| 1150 |
+
def generate(
|
| 1151 |
+
self,
|
| 1152 |
+
inputs: Optional[torch.Tensor] = None,
|
| 1153 |
+
images: Optional[torch.Tensor] = None,
|
| 1154 |
+
image_sizes: Optional[torch.Tensor] = None,
|
| 1155 |
+
**kwargs,
|
| 1156 |
+
) -> Union[GenerateOutput, torch.LongTensor]:
|
| 1157 |
+
position_ids = kwargs.pop("position_ids", None)
|
| 1158 |
+
attention_mask = kwargs.pop("attention_mask", None)
|
| 1159 |
+
if "inputs_embeds" in kwargs:
|
| 1160 |
+
raise NotImplementedError("`inputs_embeds` is not supported")
|
| 1161 |
+
if images is not None:
|
| 1162 |
+
(inputs, position_ids, attention_mask, _, inputs_embeds, _) = (
|
| 1163 |
+
self.prepare_inputs_labels_for_multimodal(
|
| 1164 |
+
inputs,
|
| 1165 |
+
position_ids,
|
| 1166 |
+
attention_mask,
|
| 1167 |
+
None,
|
| 1168 |
+
None,
|
| 1169 |
+
images,
|
| 1170 |
+
image_sizes=image_sizes,
|
| 1171 |
+
)
|
| 1172 |
+
)
|
| 1173 |
+
else:
|
| 1174 |
+
inputs_embeds = self.get_model().embed_tokens(inputs)
|
| 1175 |
+
output = super().generate(
|
| 1176 |
+
position_ids=position_ids,
|
| 1177 |
+
attention_mask=attention_mask,
|
| 1178 |
+
inputs_embeds=inputs_embeds,
|
| 1179 |
+
**kwargs,
|
| 1180 |
+
)
|
| 1181 |
+
return output
|
| 1182 |
+
|
| 1183 |
+
def prepare_inputs_for_generation(
|
| 1184 |
+
self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs
|
| 1185 |
+
):
|
| 1186 |
+
images = kwargs.pop("images", None)
|
| 1187 |
+
image_sizes = kwargs.pop("image_sizes", None)
|
| 1188 |
+
inputs = super().prepare_inputs_for_generation(
|
| 1189 |
+
input_ids,
|
| 1190 |
+
past_key_values=past_key_values,
|
| 1191 |
+
inputs_embeds=inputs_embeds,
|
| 1192 |
+
**kwargs,
|
| 1193 |
+
)
|
| 1194 |
+
if images is not None:
|
| 1195 |
+
inputs["images"] = images
|
| 1196 |
+
if image_sizes is not None:
|
| 1197 |
+
inputs["image_sizes"] = image_sizes
|
| 1198 |
+
return inputs
|
| 1199 |
+
def image_process(self,images):
|
| 1200 |
+
vision_tower = self.get_vision_tower()
|
| 1201 |
+
if not vision_tower.is_loaded:
|
| 1202 |
+
vision_tower.load_model()
|
| 1203 |
+
processor = vision_tower.image_processor
|
| 1204 |
+
def expand2square(pil_img, background_color):
|
| 1205 |
+
from PIL import Image
|
| 1206 |
+
width, height = pil_img.size
|
| 1207 |
+
if width == height:
|
| 1208 |
+
return pil_img
|
| 1209 |
+
elif width > height:
|
| 1210 |
+
result = Image.new(pil_img.mode, (width, width), background_color)
|
| 1211 |
+
result.paste(pil_img, (0, (width - height) // 2))
|
| 1212 |
+
return result
|
| 1213 |
+
else:
|
| 1214 |
+
result = Image.new(pil_img.mode, (height, height), background_color)
|
| 1215 |
+
result.paste(pil_img, ((height - width) // 2, 0))
|
| 1216 |
+
return result
|
| 1217 |
+
processed_images=[]
|
| 1218 |
+
for image in images:
|
| 1219 |
+
image = expand2square(image, tuple(int(x*255) for x in processor.image_mean))
|
| 1220 |
+
image = processor.preprocess(image, return_tensors='pt')['pixel_values'][0]
|
| 1221 |
+
processed_images.append(image)
|
| 1222 |
+
if all(x.shape == processed_images[0].shape for x in processed_images):
|
| 1223 |
+
processed_images = torch.stack(processed_images, dim=0)
|
| 1224 |
+
return processed_images
|
| 1225 |
+
def text_process(self,text,tokenizer):
|
| 1226 |
+
prompt=f"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n<image>\n{text}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
|
| 1227 |
+
text_chunks = [tokenizer(chunk).input_ids for chunk in prompt.split('<image>')]
|
| 1228 |
+
input_ids = torch.tensor(text_chunks[0] + [-200] + text_chunks[1][1:], dtype=torch.long).unsqueeze(0)
|
| 1229 |
+
return input_ids
|
| 1230 |
+
|
| 1231 |
+
|
| 1232 |
+
AutoConfig.register("mixsense_llama", MixsenseConfig)
|
| 1233 |
+
AutoModelForCausalLM.register(MixsenseConfig, MixsenseLlamaForCausalLM)
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2071 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|reserved_special_token_2|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|reserved_special_token_4|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|reserved_special_token_5|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_6|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_7|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_8|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_9|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_10|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_11|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_12|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_13|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_14|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_15|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_16|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"128256": {
|
| 2052 |
+
"content": "<pad>",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
+
}
|
| 2059 |
+
},
|
| 2060 |
+
"bos_token": "<|begin_of_text|>",
|
| 2061 |
+
"clean_up_tokenization_spaces": true,
|
| 2062 |
+
"eos_token": "<|end_of_text|>",
|
| 2063 |
+
"model_input_names": [
|
| 2064 |
+
"input_ids",
|
| 2065 |
+
"attention_mask"
|
| 2066 |
+
],
|
| 2067 |
+
"model_max_length": 3072,
|
| 2068 |
+
"pad_token": "<pad>",
|
| 2069 |
+
"padding_side": "right",
|
| 2070 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2071 |
+
}
|