Commit
·
0d5a46e
verified
·
0
Parent(s):
Duplicate from unsloth/aya-vision-8b
Browse filesCo-authored-by: Daniel Han-Chen <[email protected]>
- .gitattributes +36 -0
- README.md +176 -0
- chat_template.json +3 -0
- config.json +61 -0
- generation_config.json +8 -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 +708 -0
- preprocessor_config.json +27 -0
- processor_config.json +13 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +392 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: CohereForAI/aya-vision-8b
|
| 3 |
+
inference: false
|
| 4 |
+
library_name: transformers
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
- fr
|
| 8 |
+
- de
|
| 9 |
+
- es
|
| 10 |
+
- it
|
| 11 |
+
- pt
|
| 12 |
+
- ja
|
| 13 |
+
- ko
|
| 14 |
+
- zh
|
| 15 |
+
- ar
|
| 16 |
+
- el
|
| 17 |
+
- fa
|
| 18 |
+
- pl
|
| 19 |
+
- id
|
| 20 |
+
- cs
|
| 21 |
+
- he
|
| 22 |
+
- hi
|
| 23 |
+
- nl
|
| 24 |
+
- ro
|
| 25 |
+
- ru
|
| 26 |
+
- tr
|
| 27 |
+
- uk
|
| 28 |
+
- vi
|
| 29 |
+
license: cc-by-nc-4.0
|
| 30 |
+
extra_gated_prompt: >-
|
| 31 |
+
By submitting this form, you agree to the [License
|
| 32 |
+
Agreement](https://cohere.com/c4ai-cc-by-nc-license) and acknowledge that the
|
| 33 |
+
information you provide will be collected, used, and shared in accordance with
|
| 34 |
+
Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll receive email
|
| 35 |
+
updates about C4AI and Cohere research, events, products and services. You can
|
| 36 |
+
unsubscribe at any time.
|
| 37 |
+
extra_gated_fields:
|
| 38 |
+
Name: text
|
| 39 |
+
Affiliation: text
|
| 40 |
+
Country: country
|
| 41 |
+
I agree to use this model for non-commercial use ONLY: checkbox
|
| 42 |
+
pipeline_tag: image-text-to-text
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
+
# Model Card for Aya Vision 8B
|
| 46 |
+
|
| 47 |
+
<img src="aya-vision-8B.png" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 48 |
+
|
| 49 |
+
**C4AI Aya Vision 8B** is an open weights research release of an 8-billion parameter model with advanced capabilities optimized for a variety of vision-language use cases, including OCR, captioning, visual reasoning, summarization, question answering, code, and more.
|
| 50 |
+
It is a multilingual model trained to excel in 23 languages in vision and language.
|
| 51 |
+
|
| 52 |
+
This model card corresponds to the 8-billion version of the Aya Vision model. We also released a 32-billion version which you can find [here](https://huggingface.co/CohereForAI/aya-vision-32B).
|
| 53 |
+
|
| 54 |
+
- Developed by: [Cohere For AI](https://cohere.for.ai/)
|
| 55 |
+
- Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/)
|
| 56 |
+
- License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy)
|
| 57 |
+
- Model: c4ai-aya-vision-8b
|
| 58 |
+
- Model Size: 8 billion parameters
|
| 59 |
+
- Context length: 16K
|
| 60 |
+
|
| 61 |
+
## Try it: Aya Vision in Action
|
| 62 |
+
|
| 63 |
+
Before downloading the weights, you can try Aya Vision chat in the [Cohere playground](https://dashboard.cohere.com/playground/chat) or our dedicated [Hugging Face Space](https://huggingface.co/spaces/CohereForAI/aya_expanse) for interactive exploration.
|
| 64 |
+
|
| 65 |
+
## WhatsApp Integration
|
| 66 |
+
|
| 67 |
+
You can also talk to Aya Vision through the popular messaging service WhatsApp. Use this [link](https://wa.me/14313028498) to open a WhatsApp chatbox with Aya Vision.
|
| 68 |
+
|
| 69 |
+
If you don’t have WhatsApp downloaded on your machine you might need to do that, or, if you have it on your phone, you can follow the on-screen instructions to link your phone and WhatsApp Web.
|
| 70 |
+
By the end, you should see a text window which you can use to chat with the model.
|
| 71 |
+
More details about our WhatsApp integration are available [here](https://docs.cohere.com/v2/docs/aya#aya-expanse-integration-with-whatsapp).
|
| 72 |
+
|
| 73 |
+
## Example Notebook
|
| 74 |
+
|
| 75 |
+
You can also check out the following [notebook](https://colab.research.google.com/github/cohere-ai/cohere-developer-experience/blob/main/notebooks/guides/aya_vision_intro.ipynb) to understand how to use Aya Vision for different use cases.
|
| 76 |
+
|
| 77 |
+
## How to Use Aya Vision
|
| 78 |
+
|
| 79 |
+
Please install `transformers` from the source repository that includes the necessary changes for this model:
|
| 80 |
+
|
| 81 |
+
```python
|
| 82 |
+
# pip install 'git+https://github.com/huggingface/[email protected]'
|
| 83 |
+
from transformers import AutoProcessor, AutoModelForImageTextToText
|
| 84 |
+
import torch
|
| 85 |
+
|
| 86 |
+
model_id = "CohereForAI/aya-vision-8b"
|
| 87 |
+
|
| 88 |
+
processor = AutoProcessor.from_pretrained(model_id)
|
| 89 |
+
model = AutoModelForImageTextToText.from_pretrained(
|
| 90 |
+
model_id, device_map="auto", torch_dtype=torch.float16
|
| 91 |
+
)
|
| 92 |
+
|
| 93 |
+
# Format message with the aya-vision chat template
|
| 94 |
+
messages = [
|
| 95 |
+
{"role": "user",
|
| 96 |
+
"content": [
|
| 97 |
+
{"type": "image", "url": "https://pbs.twimg.com/media/Fx7YvfQWYAIp6rZ?format=jpg&name=medium"},
|
| 98 |
+
{"type": "text", "text": "चित्र में लिखा पाठ क्या कहता है?"},
|
| 99 |
+
]},
|
| 100 |
+
]
|
| 101 |
+
|
| 102 |
+
inputs = processor.apply_chat_template(
|
| 103 |
+
messages, padding=True, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt"
|
| 104 |
+
).to(model.device)
|
| 105 |
+
|
| 106 |
+
gen_tokens = model.generate(
|
| 107 |
+
**inputs,
|
| 108 |
+
max_new_tokens=300,
|
| 109 |
+
do_sample=True,
|
| 110 |
+
temperature=0.3,
|
| 111 |
+
)
|
| 112 |
+
|
| 113 |
+
print(processor.tokenizer.decode(gen_tokens[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
| 114 |
+
```
|
| 115 |
+
|
| 116 |
+
|
| 117 |
+
You can also use the model directly using transformers `pipeline` abstraction:
|
| 118 |
+
|
| 119 |
+
```python
|
| 120 |
+
from transformers import pipeline
|
| 121 |
+
|
| 122 |
+
pipe = pipeline(model="CohereForAI/aya-vision-8b", task="image-text-to-text", device_map="auto")
|
| 123 |
+
|
| 124 |
+
# Format message with the aya-vision chat template
|
| 125 |
+
messages = [
|
| 126 |
+
{"role": "user",
|
| 127 |
+
"content": [
|
| 128 |
+
{"type": "image", "url": "https://media.istockphoto.com/id/458012057/photo/istanbul-turkey.jpg?s=612x612&w=0&k=20&c=qogAOVvkpfUyqLUMr_XJQyq-HkACXyYUSZbKhBlPrxo="},
|
| 129 |
+
{"type": "text", "text": "Bu resimde hangi anıt gösterilmektedir?"},
|
| 130 |
+
]},
|
| 131 |
+
]
|
| 132 |
+
outputs = pipe(text=messages, max_new_tokens=300, return_full_text=False)
|
| 133 |
+
|
| 134 |
+
print(outputs)
|
| 135 |
+
```
|
| 136 |
+
|
| 137 |
+
## Model Details
|
| 138 |
+
|
| 139 |
+
**Input:** Model accepts input text and images.
|
| 140 |
+
|
| 141 |
+
**Output:** Model generates text.
|
| 142 |
+
|
| 143 |
+
**Model Architecture:** This is a vision-language model that uses a multilingual language model based on [C4AI Command R7B](https://huggingface.co/CohereForAI/c4ai-command-r7b-12-2024) and further post-trained with the [Aya Expanse recipe](https://arxiv.org/abs/2412.04261), paired with [SigLIP2-patch14-384](https://huggingface.co/google/siglip2-so400m-patch14-384) vision encoder through a multimodal adapter for vision-language understanding.
|
| 144 |
+
|
| 145 |
+
**Image Processing:** We use **169 visual tokens** to encode an image tile with a resolution of **364x364 pixels**. Input images of arbitrary sizes are mapped to the nearest supported resolution based on the aspect ratio. Aya Vision uses up to 12 input tiles and a thumbnail (resized to 364x364) (2197 image tokens).
|
| 146 |
+
|
| 147 |
+
**Languages covered:** The model has been trained on 23 languages: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Chinese (Simplified and Traditional), Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, and Persian.
|
| 148 |
+
|
| 149 |
+
**Context length**: Aya Vision 8B supports a context length of 16K.
|
| 150 |
+
|
| 151 |
+
For more details about how the model was trained, check out [our blogpost](https://huggingface.co/blog/aya-vision).
|
| 152 |
+
|
| 153 |
+
|
| 154 |
+
## Evaluation
|
| 155 |
+
|
| 156 |
+
We evaluated Aya Vision 8B against [Pangea 7B](https://huggingface.co/neulab/Pangea-7B), [Llama-3.2 11B Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision), [Molmo-D 7B](https://huggingface.co/allenai/Molmo-7B-D-0924), [Qwen2.5-VL 7B](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct), [Pixtral 12B](https://huggingface.co/mistralai/Pixtral-12B-2409), and [Gemini Flash 1.5 8B](https://developers.googleblog.com/en/gemini-15-flash-8b-is-now-generally-available-for-use/) using [Aya Vision Benchmark](https://huggingface.co/datasets/CohereForAI/AyaVisionBench) and [m-WildVision](https://huggingface.co/datasets/CohereForAI/m-WildVision).
|
| 157 |
+
Win-rates were determined using claude-3-7-sonnet-20250219 as a judge, based on the superior judge performance compared to other models.
|
| 158 |
+
|
| 159 |
+
We also evaluated Aya Vision 8B’s performance for text-only input against the same models using [m-ArenaHard](https://huggingface.co/datasets/CohereForAI/m-ArenaHard), a challenging open-ended generation evaluation, measured using win-rates using gpt-4o-2024-11-20 as a judge.
|
| 160 |
+
|
| 161 |
+
<!-- <img src="Aya_Vision_8B_Combined_Win_Rates.png" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/> -->
|
| 162 |
+
<img src="AyaVision8BWinRates(AyaVisionBench).png" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 163 |
+
<img src="AyaVision8BWinRates(m-WildVision).png" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 164 |
+
<img src="Aya_Vision_8BvsPangea(AyaVisionBench).png" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 165 |
+
<img src="EfficiencyvsPerformance.png" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 166 |
+
|
| 167 |
+
|
| 168 |
+
### Model Card Contact
|
| 169 |
+
|
| 170 |
+
For errors or additional questions about details in this model card, contact [email protected].
|
| 171 |
+
|
| 172 |
+
### Terms of Use
|
| 173 |
+
|
| 174 |
+
We hope that the release of this model will make community-based research efforts more accessible by releasing the weights of a highly performant 8 billion parameter Vision-Language Model to researchers all over the world.
|
| 175 |
+
|
| 176 |
+
This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License with an acceptable use addendum, and also requires adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy).
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes. When analyzing images, carefully describe and interpret their content while avoiding any promotion of harm, misinformation, or bias.\n\nYou are Aya Vision, a vision-language model built by Cohere for AI. You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew. You are capable of interpreting images, including describing them, answering questions about their contents, extracting textual information, and analyzing visual context. Your responses must maintain the highest standards of quality, accuracy, and safety.\n\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Aya Vision.\n- You are a large language model built by Cohere for AI.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages -%}\n <|START_OF_TURN_TOKEN|>{{ message.role | replace(\"user\", \"<|USER_TOKEN|>\") | replace(\"assistant\", \"<|CHATBOT_TOKEN|><|START_RESPONSE|>\") | replace(\"system\", \"<|SYSTEM_TOKEN|>\") }}\n {%- if message.content is defined -%}\n {%- if message.content is string -%}\n{{ message.content }}\n {%- else -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- elif message.message is defined -%}\n {%- if message.message is string -%}\n{{ message.message }}\n {%- else -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {%- if message.role == \"assistant\" -%}\n<|END_RESPONSE|>\n {%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- endif -%}\n"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"adapter_layer_norm_eps": 1e-06,
|
| 3 |
+
"alignment_activation_fn": "swiglu",
|
| 4 |
+
"alignment_intermediate_size": 28672,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"AyaVisionForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"bos_token_id": 5,
|
| 9 |
+
"downsample_factor": 2,
|
| 10 |
+
"eos_token_id": 255001,
|
| 11 |
+
"image_token_index": 255036,
|
| 12 |
+
"max_splits_per_img": 12,
|
| 13 |
+
"model_type": "aya_vision",
|
| 14 |
+
"pad_token_id": 0,
|
| 15 |
+
"projector_hidden_act": "gelu",
|
| 16 |
+
"text_config": {
|
| 17 |
+
"attention_bias": false,
|
| 18 |
+
"attention_dropout": 0.0,
|
| 19 |
+
"cache_implementation": "hybrid",
|
| 20 |
+
"head_dim": 128,
|
| 21 |
+
"hidden_act": "silu",
|
| 22 |
+
"hidden_size": 4096,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 14336,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"logit_scale": 0.25,
|
| 27 |
+
"max_position_embeddings": 8192,
|
| 28 |
+
"model_type": "cohere2",
|
| 29 |
+
"num_attention_heads": 32,
|
| 30 |
+
"num_hidden_layers": 32,
|
| 31 |
+
"num_key_value_heads": 8,
|
| 32 |
+
"rope_scaling": null,
|
| 33 |
+
"rope_theta": 50000,
|
| 34 |
+
"sliding_window": 4096,
|
| 35 |
+
"sliding_window_pattern": 4,
|
| 36 |
+
"torch_dtype": "bfloat16",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"use_qk_norm": false,
|
| 39 |
+
"vocab_size": 256000
|
| 40 |
+
},
|
| 41 |
+
"torch_dtype": "bfloat16",
|
| 42 |
+
"transformers_version": "4.50.0.dev0",
|
| 43 |
+
"unsloth_fixed": true,
|
| 44 |
+
"vision_config": {
|
| 45 |
+
"attention_dropout": 0.0,
|
| 46 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 47 |
+
"hidden_size": 1152,
|
| 48 |
+
"image_size": 364,
|
| 49 |
+
"intermediate_size": 4304,
|
| 50 |
+
"layer_norm_eps": 1e-06,
|
| 51 |
+
"model_type": "siglip_vision_model",
|
| 52 |
+
"num_attention_heads": 16,
|
| 53 |
+
"num_channels": 3,
|
| 54 |
+
"num_hidden_layers": 27,
|
| 55 |
+
"patch_size": 14,
|
| 56 |
+
"torch_dtype": "bfloat16",
|
| 57 |
+
"vision_use_head": false
|
| 58 |
+
},
|
| 59 |
+
"vision_feature_layer": -1,
|
| 60 |
+
"vision_feature_select_strategy": "full"
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 5,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": 255001,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.50.0.dev0"
|
| 8 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78e3682a39ce7517c0a33a29af95ef125081fe0e7be1157122e4bed1df3e531f
|
| 3 |
+
size 4932249664
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c64a234efd018087325144ac98fbb16aef6b5f6ca3f373e10bd64d697320605
|
| 3 |
+
size 4999720952
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff94c2d618d5ad89ac57531b473fc81ba40a4464259ddd333f6b0c5a6356f62e
|
| 3 |
+
size 4915826080
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f24d25814cf9e560b614a47a574f3477b6da50181c2ef28e31ae700569538730
|
| 3 |
+
size 2415982184
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,708 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 17263684064
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 7 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 24 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 25 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 26 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 27 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 64 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 65 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 66 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 67 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 72 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 73 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 74 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 75 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 76 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 77 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 78 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 79 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 80 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 81 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 82 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 83 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 84 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 85 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 86 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 87 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 88 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 89 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 90 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 91 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 92 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 93 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 94 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 95 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 96 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 97 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 98 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 99 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 100 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 101 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 102 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 103 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 104 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 105 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 106 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 107 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 108 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 109 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 110 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 111 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 112 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 113 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 114 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 115 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 117 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 119 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 122 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 123 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 125 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 160 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 161 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 163 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 168 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 169 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 170 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 171 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 172 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 173 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 174 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 175 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 176 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 177 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 178 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 179 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 180 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 181 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 182 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 183 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 184 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 185 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 186 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 187 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 188 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 189 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 190 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 191 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 192 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 193 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 194 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 195 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 196 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 197 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 198 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 199 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 200 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 201 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 202 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 203 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 204 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 205 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 206 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 207 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 208 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 209 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 210 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 211 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 212 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 213 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 214 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 215 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 216 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 217 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 218 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 219 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 220 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 221 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 222 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 223 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 224 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 225 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 226 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 227 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 228 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 229 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 230 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 231 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 232 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 233 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 234 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 235 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 236 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 237 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 238 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 239 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 240 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 241 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 242 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 243 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 244 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 245 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 246 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 247 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 248 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 249 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 250 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 251 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 252 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 253 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 254 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 255 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 256 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 257 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 258 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 259 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 260 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 261 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 262 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 263 |
+
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
|
| 264 |
+
"multi_modal_projector.layernorm.bias": "model-00001-of-00004.safetensors",
|
| 265 |
+
"multi_modal_projector.layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
|
| 269 |
+
"multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
|
| 271 |
+
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 274 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 276 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 278 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 280 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 286 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 288 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 290 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 291 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 292 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 296 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 298 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 300 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 302 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 303 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 304 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 306 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 307 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 308 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 309 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 310 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 311 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 312 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 313 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 314 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 315 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 316 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 317 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 318 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 320 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 322 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 323 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 324 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 325 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 326 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 327 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 328 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 329 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 330 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 332 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 334 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 335 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 336 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 337 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 338 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 339 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 340 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 342 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 344 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 346 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 348 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 350 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 352 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 354 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 356 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 358 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 360 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 362 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 364 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 366 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 368 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 370 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 372 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 374 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 376 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 378 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 380 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 382 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 384 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 386 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 388 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 390 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 392 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 394 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 396 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 398 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 400 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 402 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 404 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 406 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 407 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 408 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 409 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 410 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 411 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 412 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 413 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 414 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 415 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 416 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 418 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 419 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 420 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 421 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 422 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 423 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 424 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 425 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 426 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 427 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 428 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 429 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 430 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 431 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 432 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 433 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 434 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 435 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 436 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 437 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 438 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 439 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 440 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 441 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 442 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 443 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 444 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 445 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 446 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 447 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 448 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 449 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 450 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 451 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 452 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 453 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 454 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 455 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 456 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 457 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 458 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 459 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 460 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 461 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 462 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 463 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 464 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 465 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 466 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 467 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 468 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 469 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 470 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 471 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 472 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 473 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 474 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 475 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 476 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 477 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 478 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 479 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 480 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 481 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 482 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 483 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 484 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 485 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 486 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 487 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 488 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 489 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 490 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 491 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 492 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 493 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 494 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 495 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 496 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 497 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 498 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 499 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 500 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 501 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 502 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 503 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 504 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 505 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 506 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 507 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 508 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 509 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 510 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 511 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 512 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 514 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 515 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 516 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 517 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 518 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 519 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 520 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 521 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 522 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 523 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 524 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 525 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 526 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 527 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 528 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 529 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 530 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 531 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 532 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 533 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 534 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 535 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 536 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 537 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 538 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 539 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 540 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 541 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 542 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 543 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 544 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 545 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 546 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 547 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 548 |
+
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 549 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 550 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 551 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 552 |
+
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 553 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 554 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 555 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 556 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 557 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 558 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 559 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 560 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 561 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 562 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 563 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 564 |
+
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 565 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 566 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 567 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 568 |
+
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 569 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 570 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 571 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 572 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 573 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 574 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 575 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 576 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 577 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 578 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 579 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 580 |
+
"vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 581 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 582 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 583 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 584 |
+
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 586 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 587 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 588 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 589 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 590 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 591 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 592 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 593 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 594 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 596 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 598 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 599 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 600 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 601 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 602 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 603 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 604 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 605 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 606 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 608 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 610 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 611 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 612 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 613 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 614 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 615 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 616 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 617 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 618 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 620 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 622 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 623 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 624 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 625 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 626 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 627 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 628 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 629 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 630 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 631 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 632 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 634 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 635 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 636 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 637 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 638 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 639 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 640 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 641 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 642 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 644 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 645 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 646 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 647 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 648 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 649 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 650 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 651 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 652 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 653 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 654 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 656 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 658 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 659 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 660 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 661 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 662 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 663 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 664 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 665 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 666 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 668 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 670 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 671 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 672 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 673 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 674 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 675 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 676 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 677 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 678 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 679 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 680 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 681 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 682 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 683 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 684 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 685 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 686 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 687 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 688 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 689 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
| 690 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
| 691 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
| 692 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
| 693 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 694 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 695 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 696 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 697 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 698 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 699 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 700 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 701 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 702 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 703 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 704 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 705 |
+
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
|
| 706 |
+
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
|
| 707 |
+
}
|
| 708 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_to_patches": false,
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "GotOcr2ImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"max_patches": 12,
|
| 19 |
+
"min_patches": 1,
|
| 20 |
+
"processor_class": "AyaVisionProcessor",
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"height": 364,
|
| 25 |
+
"width": 364
|
| 26 |
+
}
|
| 27 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"end_of_img_token": "<|END_OF_IMG|>",
|
| 3 |
+
"image_token": "<image>",
|
| 4 |
+
"img_line_break_token": "<|IMG_LINE_BREAK|>",
|
| 5 |
+
"img_patch_token": "<|IMG_PATCH|>",
|
| 6 |
+
"img_size": 364,
|
| 7 |
+
"patch_size": 28,
|
| 8 |
+
"processor_class": "AyaVisionProcessor",
|
| 9 |
+
"start_of_img_token": "<|START_OF_IMG|>",
|
| 10 |
+
"tile_global_token": "TILE_GLOBAL",
|
| 11 |
+
"tile_token": "TILE",
|
| 12 |
+
"vision_feature_select_strategy": "full"
|
| 13 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<BOS_TOKEN>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|END_OF_TURN_TOKEN|>",
|
| 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
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d896f76efd3c9d3e0541ec0a0396a5669281c5667a1ac1d82001117625720ff4
|
| 3 |
+
size 20125695
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<PAD>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<UNK>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "<CLS>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"3": {
|
| 31 |
+
"content": "<SEP>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"4": {
|
| 39 |
+
"content": "<MASK_TOKEN>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"5": {
|
| 47 |
+
"content": "<BOS_TOKEN>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"6": {
|
| 55 |
+
"content": "<EOS_TOKEN>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"7": {
|
| 63 |
+
"content": "<EOP_TOKEN>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"255000": {
|
| 71 |
+
"content": "<|START_OF_TURN_TOKEN|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"255001": {
|
| 79 |
+
"content": "<|END_OF_TURN_TOKEN|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"255002": {
|
| 87 |
+
"content": "<|YES_TOKEN|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"255003": {
|
| 95 |
+
"content": "<|NO_TOKEN|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"255004": {
|
| 103 |
+
"content": "<|GOOD_TOKEN|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"255005": {
|
| 111 |
+
"content": "<|BAD_TOKEN|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"255006": {
|
| 119 |
+
"content": "<|USER_TOKEN|>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"255007": {
|
| 127 |
+
"content": "<|CHATBOT_TOKEN|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"255008": {
|
| 135 |
+
"content": "<|SYSTEM_TOKEN|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"255009": {
|
| 143 |
+
"content": "<|USER_0_TOKEN|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"255010": {
|
| 151 |
+
"content": "<|USER_1_TOKEN|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"255011": {
|
| 159 |
+
"content": "<|USER_2_TOKEN|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"255012": {
|
| 167 |
+
"content": "<|USER_3_TOKEN|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"255013": {
|
| 175 |
+
"content": "<|USER_4_TOKEN|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"255014": {
|
| 183 |
+
"content": "<|USER_5_TOKEN|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"255015": {
|
| 191 |
+
"content": "<|USER_6_TOKEN|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"255016": {
|
| 199 |
+
"content": "<|USER_7_TOKEN|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"255017": {
|
| 207 |
+
"content": "<|USER_8_TOKEN|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"255018": {
|
| 215 |
+
"content": "<|USER_9_TOKEN|>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": false
|
| 221 |
+
},
|
| 222 |
+
"255019": {
|
| 223 |
+
"content": "<|START_THINKING|>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": false
|
| 229 |
+
},
|
| 230 |
+
"255020": {
|
| 231 |
+
"content": "<|END_THINKING|>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": false
|
| 237 |
+
},
|
| 238 |
+
"255021": {
|
| 239 |
+
"content": "<|START_RESPONSE|>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"255022": {
|
| 247 |
+
"content": "<|END_RESPONSE|>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"255023": {
|
| 255 |
+
"content": "<|START_ACTION|>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": false
|
| 261 |
+
},
|
| 262 |
+
"255024": {
|
| 263 |
+
"content": "<|END_ACTION|>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": false
|
| 269 |
+
},
|
| 270 |
+
"255025": {
|
| 271 |
+
"content": "<|START_TOOL_RESULT|>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": false
|
| 277 |
+
},
|
| 278 |
+
"255026": {
|
| 279 |
+
"content": "<|END_TOOL_RESULT|>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": false
|
| 285 |
+
},
|
| 286 |
+
"255027": {
|
| 287 |
+
"content": "<|EXTRA_8_TOKEN|>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": false
|
| 293 |
+
},
|
| 294 |
+
"255028": {
|
| 295 |
+
"content": "<|NEW_FILE|>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"255029": {
|
| 303 |
+
"content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": false
|
| 309 |
+
},
|
| 310 |
+
"255030": {
|
| 311 |
+
"content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": false
|
| 317 |
+
},
|
| 318 |
+
"255031": {
|
| 319 |
+
"content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": false
|
| 325 |
+
},
|
| 326 |
+
"255032": {
|
| 327 |
+
"content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": false
|
| 333 |
+
},
|
| 334 |
+
"255033": {
|
| 335 |
+
"content": "<|START_OF_IMG|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": false
|
| 341 |
+
},
|
| 342 |
+
"255034": {
|
| 343 |
+
"content": "<|END_OF_IMG|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": false
|
| 349 |
+
},
|
| 350 |
+
"255035": {
|
| 351 |
+
"content": "<|IMG_LINE_BREAK|>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": false
|
| 357 |
+
},
|
| 358 |
+
"255036": {
|
| 359 |
+
"content": "<|IMG_PATCH|>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": false
|
| 365 |
+
}
|
| 366 |
+
},
|
| 367 |
+
"bos_token": "<BOS_TOKEN>",
|
| 368 |
+
"chat_template": [
|
| 369 |
+
{
|
| 370 |
+
"name": "default",
|
| 371 |
+
"template": "{{ bos_token }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes. When analyzing images, carefully describe and interpret their content while avoiding any promotion of harm, misinformation, or bias.\n\nYou are Aya Vision, a vision-language model built by Cohere for AI. You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew. You are capable of interpreting images, including describing them, answering questions about their contents, extracting textual information, and analyzing visual context. Your responses must maintain the highest standards of quality, accuracy, and safety.\n\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Aya Vision.\n- You are a large language model built by Cohere for AI.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages -%}\n <|START_OF_TURN_TOKEN|>{{ message.role | replace(\"user\", \"<|USER_TOKEN|>\") | replace(\"assistant\", \"<|CHATBOT_TOKEN|><|START_RESPONSE|>\") | replace(\"system\", \"<|SYSTEM_TOKEN|>\") }}\n {%- if message.content is defined -%}\n {%- if message.content is string -%}\n{{ message.content }}\n {%- else -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- elif message.message is defined -%}\n {%- if message.message is string -%}\n{{ message.message }}\n {%- else -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {%- if message.role == \"assistant\" -%}\n<|END_RESPONSE|>\n {%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- endif -%}\n"
|
| 372 |
+
}
|
| 373 |
+
],
|
| 374 |
+
"clean_up_tokenization_spaces": false,
|
| 375 |
+
"eos_token": "<|END_OF_TURN_TOKEN|>",
|
| 376 |
+
"extra_special_tokens": {},
|
| 377 |
+
"legacy": true,
|
| 378 |
+
"max_length": null,
|
| 379 |
+
"merges_file": null,
|
| 380 |
+
"model_max_length": 16384,
|
| 381 |
+
"pad_to_multiple_of": null,
|
| 382 |
+
"pad_token": "<PAD>",
|
| 383 |
+
"pad_token_type_id": 0,
|
| 384 |
+
"padding_side": "left",
|
| 385 |
+
"processor_class": "AyaVisionProcessor",
|
| 386 |
+
"sp_model_kwargs": {},
|
| 387 |
+
"spaces_between_special_tokens": false,
|
| 388 |
+
"tokenizer_class": "CohereTokenizer",
|
| 389 |
+
"unk_token": null,
|
| 390 |
+
"use_default_system_prompt": false,
|
| 391 |
+
"vocab_file": null
|
| 392 |
+
}
|