Commit
·
59c5a66
verified
·
0
Parent(s):
Duplicate from llava-hf/LLaVA-NeXT-Video-7B-hf
Browse filesCo-authored-by: Raushan Turganbay <[email protected]>
- .gitattributes +35 -0
- README.md +260 -0
- added_tokens.json +4 -0
- chat_template.json +3 -0
- config.json +69 -0
- demo.png +0 -0
- generation_config.json +7 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +694 -0
- preprocessor_config.json +51 -0
- processor_config.json +8 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +66 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
README.md
ADDED
|
@@ -0,0 +1,260 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: llama2
|
| 5 |
+
pipeline_tag: video-text-to-text
|
| 6 |
+
datasets:
|
| 7 |
+
- lmms-lab/VideoChatGPT
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# LLaVA-NeXT-Video Model Card
|
| 11 |
+
|
| 12 |
+
Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance: [](https://colab.research.google.com/drive/1CZggLHrjxMReG-FNOmqSOdi4z7NPq6SO?usp=sharing)
|
| 13 |
+
|
| 14 |
+
Disclaimer: The team releasing LLaVa-NeXT-Video did not write a model card for this model so this model card has been written by the Hugging Face team.
|
| 15 |
+
|
| 16 |
+
## 📄 Model details
|
| 17 |
+
|
| 18 |
+
**Model type:**
|
| 19 |
+
LLaVA-Next-Video is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. The model is buit on top of LLaVa-NeXT by tuning on a mix of video and image data to achieve better video understanding capabilities. The videos were sampled uniformly to be 32 frames per clip.
|
| 20 |
+
The model is a current SOTA among open-source models on [VideoMME bench](https://arxiv.org/abs/2405.21075).
|
| 21 |
+
Base LLM: [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
**Model date:**
|
| 27 |
+
LLaVA-Next-Video-7B was trained in April 2024.
|
| 28 |
+
|
| 29 |
+
**Paper or resources for more information:** https://github.com/LLaVA-VL/LLaVA-NeXT
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
## 📚 Training dataset
|
| 33 |
+
|
| 34 |
+
### Image
|
| 35 |
+
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
|
| 36 |
+
- 158K GPT-generated multimodal instruction-following data.
|
| 37 |
+
- 500K academic-task-oriented VQA data mixture.
|
| 38 |
+
- 50K GPT-4V data mixture.
|
| 39 |
+
- 40K ShareGPT data.
|
| 40 |
+
|
| 41 |
+
### Video
|
| 42 |
+
- 100K VideoChatGPT-Instruct.
|
| 43 |
+
|
| 44 |
+
## 📊 Evaluation dataset
|
| 45 |
+
A collection of 4 benchmarks, including 3 academic VQA benchmarks and 1 captioning benchmark.
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
## 🚀 How to use the model
|
| 50 |
+
|
| 51 |
+
First, make sure to have `transformers >= 4.42.0`.
|
| 52 |
+
The model supports multi-visual and multi-prompt generation. Meaning that you can pass multiple images/videos in your prompt. Make sure also to follow the correct prompt template (`USER: xxx\nASSISTANT:`) and add the token `<image>` or `<video>` to the location where you want to query images/videos:
|
| 53 |
+
|
| 54 |
+
Below is an example script to run generation in `float16` precision on a GPU device:
|
| 55 |
+
|
| 56 |
+
```python
|
| 57 |
+
import av
|
| 58 |
+
import torch
|
| 59 |
+
import numpy as np
|
| 60 |
+
from huggingface_hub import hf_hub_download
|
| 61 |
+
from transformers import LlavaNextVideoProcessor, LlavaNextVideoForConditionalGeneration
|
| 62 |
+
|
| 63 |
+
model_id = "llava-hf/LLaVA-NeXT-Video-7B-hf"
|
| 64 |
+
|
| 65 |
+
model = LlavaNextVideoForConditionalGeneration.from_pretrained(
|
| 66 |
+
model_id,
|
| 67 |
+
torch_dtype=torch.float16,
|
| 68 |
+
low_cpu_mem_usage=True,
|
| 69 |
+
).to(0)
|
| 70 |
+
|
| 71 |
+
processor = LlavaNextVideoProcessor.from_pretrained(model_id)
|
| 72 |
+
|
| 73 |
+
def read_video_pyav(container, indices):
|
| 74 |
+
'''
|
| 75 |
+
Decode the video with PyAV decoder.
|
| 76 |
+
Args:
|
| 77 |
+
container (`av.container.input.InputContainer`): PyAV container.
|
| 78 |
+
indices (`List[int]`): List of frame indices to decode.
|
| 79 |
+
Returns:
|
| 80 |
+
result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
|
| 81 |
+
'''
|
| 82 |
+
frames = []
|
| 83 |
+
container.seek(0)
|
| 84 |
+
start_index = indices[0]
|
| 85 |
+
end_index = indices[-1]
|
| 86 |
+
for i, frame in enumerate(container.decode(video=0)):
|
| 87 |
+
if i > end_index:
|
| 88 |
+
break
|
| 89 |
+
if i >= start_index and i in indices:
|
| 90 |
+
frames.append(frame)
|
| 91 |
+
return np.stack([x.to_ndarray(format="rgb24") for x in frames])
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
# define a chat history and use `apply_chat_template` to get correctly formatted prompt
|
| 95 |
+
# Each value in "content" has to be a list of dicts with types ("text", "image", "video")
|
| 96 |
+
conversation = [
|
| 97 |
+
{
|
| 98 |
+
|
| 99 |
+
"role": "user",
|
| 100 |
+
"content": [
|
| 101 |
+
{"type": "text", "text": "Why is this video funny?"},
|
| 102 |
+
{"type": "video"},
|
| 103 |
+
],
|
| 104 |
+
},
|
| 105 |
+
]
|
| 106 |
+
|
| 107 |
+
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
|
| 108 |
+
|
| 109 |
+
video_path = hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="sample_demo_1.mp4", repo_type="dataset")
|
| 110 |
+
container = av.open(video_path)
|
| 111 |
+
|
| 112 |
+
# sample uniformly 8 frames from the video, can sample more for longer videos
|
| 113 |
+
total_frames = container.streams.video[0].frames
|
| 114 |
+
indices = np.arange(0, total_frames, total_frames / 8).astype(int)
|
| 115 |
+
clip = read_video_pyav(container, indices)
|
| 116 |
+
inputs_video = processor(text=prompt, videos=clip, padding=True, return_tensors="pt").to(model.device)
|
| 117 |
+
|
| 118 |
+
output = model.generate(**inputs_video, max_new_tokens=100, do_sample=False)
|
| 119 |
+
print(processor.decode(output[0][2:], skip_special_tokens=True))
|
| 120 |
+
```
|
| 121 |
+
|
| 122 |
+
-----------
|
| 123 |
+
From transformers>=v4.48, you can also pass image/video url or local path to the conversation history, and let the chat template handle the rest.
|
| 124 |
+
For video you also need to indicate how many `num_frames` to sample from video, otherwise the whole video will be loaded.
|
| 125 |
+
Chat template will load the image/video for you and return inputs in `torch.Tensor` which you can pass directly to `model.generate()`.
|
| 126 |
+
|
| 127 |
+
```python
|
| 128 |
+
messages = [
|
| 129 |
+
{
|
| 130 |
+
"role": "user",
|
| 131 |
+
"content": [
|
| 132 |
+
{"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"}
|
| 133 |
+
{"type": "video", "path": "my_video.mp4"},
|
| 134 |
+
{"type": "text", "text": "What is shown in this image and video?"},
|
| 135 |
+
],
|
| 136 |
+
},
|
| 137 |
+
]
|
| 138 |
+
|
| 139 |
+
inputs = processor.apply_chat_template(messages, num_frames=8, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors"pt")
|
| 140 |
+
output = model.generate(**inputs, max_new_tokens=50)
|
| 141 |
+
```
|
| 142 |
+
|
| 143 |
+
|
| 144 |
+
### Inference with images as inputs
|
| 145 |
+
|
| 146 |
+
To generate from images use the below code after loading the model as shown above:
|
| 147 |
+
|
| 148 |
+
```python
|
| 149 |
+
import requests
|
| 150 |
+
from PIL import Image
|
| 151 |
+
|
| 152 |
+
conversation = [
|
| 153 |
+
{
|
| 154 |
+
"role": "user",
|
| 155 |
+
"content": [
|
| 156 |
+
{"type": "text", "text": "What are these?"},
|
| 157 |
+
{"type": "image"},
|
| 158 |
+
],
|
| 159 |
+
},
|
| 160 |
+
]
|
| 161 |
+
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
|
| 162 |
+
|
| 163 |
+
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
|
| 164 |
+
raw_image = Image.open(requests.get(image_file, stream=True).raw)
|
| 165 |
+
inputs_image = processor(text=prompt, images=raw_image, return_tensors='pt').to(0, torch.float16)
|
| 166 |
+
|
| 167 |
+
output = model.generate(**inputs_video, max_new_tokens=100, do_sample=False)
|
| 168 |
+
print(processor.decode(output[0][2:], skip_special_tokens=True))
|
| 169 |
+
```
|
| 170 |
+
|
| 171 |
+
### Inference with images and videos as inputs
|
| 172 |
+
|
| 173 |
+
To generate from images and videos in one generate use the below code after loading the model as shown above:
|
| 174 |
+
|
| 175 |
+
```python
|
| 176 |
+
conversation_1 = [
|
| 177 |
+
{
|
| 178 |
+
"role": "user",
|
| 179 |
+
"content": [
|
| 180 |
+
{"type": "text", "text": "What's the content of the image>"},
|
| 181 |
+
{"type": "image"},
|
| 182 |
+
],
|
| 183 |
+
}
|
| 184 |
+
]
|
| 185 |
+
conversation_2 = [
|
| 186 |
+
{
|
| 187 |
+
"role": "user",
|
| 188 |
+
"content": [
|
| 189 |
+
{"type": "text", "text": "Why is this video funny?"},
|
| 190 |
+
{"type": "video"},
|
| 191 |
+
],
|
| 192 |
+
},
|
| 193 |
+
]
|
| 194 |
+
prompt_1 = processor.apply_chat_template(conversation_1, add_generation_prompt=True)
|
| 195 |
+
prompt_2 = processor.apply_chat_template(conversation_2, add_generation_prompt=True)
|
| 196 |
+
|
| 197 |
+
s = processor(text=[prompt_1, prompt_2], images=image, videos=clip, padding=True, return_tensors="pt").to(model.device)
|
| 198 |
+
|
| 199 |
+
# Generate
|
| 200 |
+
generate_ids = model.generate(**inputs, max_new_tokens=100)
|
| 201 |
+
out = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
|
| 202 |
+
print(out)
|
| 203 |
+
```
|
| 204 |
+
|
| 205 |
+
### Model optimization
|
| 206 |
+
|
| 207 |
+
#### 4-bit quantization through `bitsandbytes` library
|
| 208 |
+
|
| 209 |
+
First make sure to install `bitsandbytes`, `pip install bitsandbytes` and make sure to have access to a CUDA compatible GPU device. Simply change the snippet above with:
|
| 210 |
+
|
| 211 |
+
```diff
|
| 212 |
+
model = LlavaNextVideoForConditionalGeneration.from_pretrained(
|
| 213 |
+
model_id,
|
| 214 |
+
torch_dtype=torch.float16,
|
| 215 |
+
low_cpu_mem_usage=True,
|
| 216 |
+
+ load_in_4bit=True
|
| 217 |
+
)
|
| 218 |
+
```
|
| 219 |
+
|
| 220 |
+
#### Use Flash-Attention 2 to further speed-up generation
|
| 221 |
+
|
| 222 |
+
First make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) regarding that package installation. Simply change the snippet above with:
|
| 223 |
+
|
| 224 |
+
```diff
|
| 225 |
+
model = LlavaNextVideoForConditionalGeneration.from_pretrained(
|
| 226 |
+
model_id,
|
| 227 |
+
torch_dtype=torch.float16,
|
| 228 |
+
low_cpu_mem_usage=True,
|
| 229 |
+
+ use_flash_attention_2=True
|
| 230 |
+
).to(0)
|
| 231 |
+
```
|
| 232 |
+
|
| 233 |
+
|
| 234 |
+
## 🔒 License
|
| 235 |
+
Llama 2 is licensed under the LLAMA 2 Community License,
|
| 236 |
+
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
|
| 237 |
+
|
| 238 |
+
|
| 239 |
+
## ✏️ Citation
|
| 240 |
+
If you find our paper and code useful in your research:
|
| 241 |
+
|
| 242 |
+
```BibTeX
|
| 243 |
+
@misc{zhang2024llavanextvideo,
|
| 244 |
+
title={LLaVA-NeXT: A Strong Zero-shot Video Understanding Model},
|
| 245 |
+
url={https://llava-vl.github.io/blog/2024-04-30-llava-next-video/},
|
| 246 |
+
author={Zhang, Yuanhan and Li, Bo and Liu, haotian and Lee, Yong jae and Gui, Liangke and Fu, Di and Feng, Jiashi and Liu, Ziwei and Li, Chunyuan},
|
| 247 |
+
month={April},
|
| 248 |
+
year={2024}
|
| 249 |
+
}
|
| 250 |
+
```
|
| 251 |
+
|
| 252 |
+
```BibTeX
|
| 253 |
+
@misc{liu2024llavanext,
|
| 254 |
+
title={LLaVA-NeXT: Improved reasoning, OCR, and world knowledge},
|
| 255 |
+
url={https://llava-vl.github.io/blog/2024-01-30-llava-next/},
|
| 256 |
+
author={Liu, Haotian and Li, Chunyuan and Li, Yuheng and Li, Bo and Zhang, Yuanhan and Shen, Sheng and Lee, Yong Jae},
|
| 257 |
+
month={January},
|
| 258 |
+
year={2024}
|
| 259 |
+
}
|
| 260 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image>": 32001,
|
| 3 |
+
"<video>": 32000
|
| 4 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlavaNextVideoForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"ignore_index": -100,
|
| 6 |
+
"image_grid_pinpoints": [
|
| 7 |
+
[
|
| 8 |
+
336,
|
| 9 |
+
672
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
672,
|
| 13 |
+
336
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
672,
|
| 17 |
+
672
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
1008,
|
| 21 |
+
336
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
336,
|
| 25 |
+
1008
|
| 26 |
+
]
|
| 27 |
+
],
|
| 28 |
+
"image_token_index": 32001,
|
| 29 |
+
"model_type": "llava_next_video",
|
| 30 |
+
"projector_hidden_act": "gelu",
|
| 31 |
+
"spatial_pool_mode": "average",
|
| 32 |
+
"spatial_pool_out_channels": 1024,
|
| 33 |
+
"spatial_pool_stride": 2,
|
| 34 |
+
"text_config": {
|
| 35 |
+
"_name_or_path": "lmsys/vicuna-7b-v1.5",
|
| 36 |
+
"architectures": [
|
| 37 |
+
"LlamaForCausalLM"
|
| 38 |
+
],
|
| 39 |
+
"rope_scaling" : {
|
| 40 |
+
"factor": 2.5,
|
| 41 |
+
"type": "linear"
|
| 42 |
+
},
|
| 43 |
+
"max_position_embeddings": 4096,
|
| 44 |
+
"model_type": "llama",
|
| 45 |
+
"pad_token_id": 0,
|
| 46 |
+
"rms_norm_eps": 1e-05,
|
| 47 |
+
"torch_dtype": "float16",
|
| 48 |
+
"type": "linear",
|
| 49 |
+
"vocab_size": 32064
|
| 50 |
+
},
|
| 51 |
+
"tie_word_embeddings": false,
|
| 52 |
+
"torch_dtype": "bfloat16",
|
| 53 |
+
"transformers_version": "4.42.0.dev0",
|
| 54 |
+
"use_image_newline_parameter": true,
|
| 55 |
+
"video_token_index": 32000,
|
| 56 |
+
"vision_config": {
|
| 57 |
+
"hidden_size": 1024,
|
| 58 |
+
"image_size": 336,
|
| 59 |
+
"intermediate_size": 4096,
|
| 60 |
+
"model_type": "clip_vision_model",
|
| 61 |
+
"num_attention_heads": 16,
|
| 62 |
+
"num_hidden_layers": 24,
|
| 63 |
+
"patch_size": 14,
|
| 64 |
+
"projection_dim": 768,
|
| 65 |
+
"vocab_size": 32000
|
| 66 |
+
},
|
| 67 |
+
"vision_feature_layer": -2,
|
| 68 |
+
"vision_feature_select_strategy": "default"
|
| 69 |
+
}
|
demo.png
ADDED
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.42.0.dev0"
|
| 7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc32753ce8e75e89748b95677d9349d2b47af998457b4ebe22d27dece7338a3d
|
| 3 |
+
size 4992938952
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c50112e9dffcb204f90a5be738d28e33b92cd14332cabde6e8f39171d999a1b
|
| 3 |
+
size 4957878552
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8022077b98e08236a07b999f1f51ab577bda9c8aa2dc66d12853b1b162731100
|
| 3 |
+
size 4176137496
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,694 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14126862336
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"image_newline": "model-00001-of-00003.safetensors",
|
| 7 |
+
"language_model.lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 29 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 31 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 33 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 41 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 126 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 145 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 147 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 149 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 155 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 159 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 161 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 179 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 181 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 183 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 225 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 243 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 247 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 249 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 261 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 275 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 277 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"language_model.model.norm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"multi_modal_projector.linear_1.bias": "model-00001-of-00003.safetensors",
|
| 299 |
+
"multi_modal_projector.linear_1.weight": "model-00001-of-00003.safetensors",
|
| 300 |
+
"multi_modal_projector.linear_2.bias": "model-00001-of-00003.safetensors",
|
| 301 |
+
"multi_modal_projector.linear_2.weight": "model-00001-of-00003.safetensors",
|
| 302 |
+
"vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00003.safetensors",
|
| 303 |
+
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
|
| 304 |
+
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
|
| 305 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 306 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 307 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 308 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 309 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 310 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 311 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 312 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 313 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 314 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 315 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 316 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 317 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 318 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 319 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 320 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 321 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 322 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 323 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 324 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 325 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 326 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 327 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 328 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 329 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 330 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 331 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 332 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 333 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 334 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 335 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 336 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 337 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 338 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 339 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 340 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 341 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 342 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 343 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 344 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 345 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 346 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 347 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 348 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 349 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 350 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 351 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 352 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 353 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 354 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 355 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 356 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 357 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 358 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 359 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 360 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 361 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 362 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 363 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 364 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 365 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 366 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 367 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 368 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 369 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 370 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 372 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 374 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 375 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 376 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 382 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 384 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 386 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 387 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 388 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 394 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 396 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 398 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 399 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 400 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 406 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 408 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 410 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 411 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 412 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 418 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 420 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 422 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 423 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 424 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 430 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 432 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 434 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 435 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 436 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 442 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 443 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 444 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 445 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 446 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 447 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 448 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 449 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 450 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 451 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 452 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 453 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 454 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 455 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 456 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 457 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 458 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 459 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 460 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 461 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 462 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 463 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 464 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 465 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 466 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 467 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 468 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 469 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 470 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 471 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 472 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 473 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 474 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 475 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 476 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 477 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 478 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 479 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 480 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 481 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 482 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 483 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 484 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 485 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 486 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 487 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 488 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 489 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 490 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 491 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 492 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 493 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 494 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 495 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 496 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 497 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 498 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 499 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 500 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 501 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 502 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 503 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 504 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 505 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 506 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 507 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 508 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 509 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 510 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 511 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 512 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 513 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 514 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 515 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 516 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 517 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 518 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 519 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 520 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 521 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 522 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 523 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 524 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 525 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 526 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 527 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 528 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 529 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 530 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 531 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 532 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 533 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 534 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 535 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 536 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 537 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 538 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 539 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 540 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 541 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 542 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 543 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 544 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 545 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 546 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 547 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 548 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 549 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 550 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 551 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 552 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 553 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 554 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 555 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 556 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 557 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 558 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 559 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 560 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 561 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 562 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 563 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 564 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 565 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 566 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 567 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 568 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 569 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 570 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 571 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 572 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 573 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 574 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 575 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 576 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 577 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 578 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 579 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 580 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 581 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 582 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 583 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 584 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 585 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 586 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 587 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 588 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 589 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 590 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 591 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 592 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 593 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 594 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 595 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 596 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 597 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 598 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 599 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 600 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 601 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 602 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 603 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 604 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 605 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 606 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 607 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 608 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 609 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 610 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 611 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 612 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 613 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 614 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 615 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 616 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 617 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 618 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 619 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 620 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 621 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 622 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 623 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 624 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 625 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 626 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 627 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 628 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 629 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 630 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 631 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 632 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 633 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 634 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 635 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 636 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 637 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 638 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 639 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 640 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 641 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 642 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 643 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 644 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 645 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 646 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 647 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 648 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 649 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 650 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 651 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 652 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 653 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 654 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 655 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 656 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 657 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 658 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 659 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 660 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 661 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 662 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 663 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 664 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 665 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 666 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 667 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 668 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 669 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 670 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 671 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 672 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 673 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
| 674 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
| 675 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
| 676 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
| 677 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
| 678 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
| 679 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
| 680 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
| 681 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 682 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 683 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 684 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 685 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 686 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 687 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 688 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 689 |
+
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
|
| 690 |
+
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 691 |
+
"vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00003.safetensors",
|
| 692 |
+
"vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00003.safetensors"
|
| 693 |
+
}
|
| 694 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 336,
|
| 4 |
+
"width": 336
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_pad": true,
|
| 10 |
+
"do_rescale": true,
|
| 11 |
+
"do_resize": true,
|
| 12 |
+
"image_grid_pinpoints": [
|
| 13 |
+
[
|
| 14 |
+
336,
|
| 15 |
+
672
|
| 16 |
+
],
|
| 17 |
+
[
|
| 18 |
+
672,
|
| 19 |
+
336
|
| 20 |
+
],
|
| 21 |
+
[
|
| 22 |
+
672,
|
| 23 |
+
672
|
| 24 |
+
],
|
| 25 |
+
[
|
| 26 |
+
1008,
|
| 27 |
+
336
|
| 28 |
+
],
|
| 29 |
+
[
|
| 30 |
+
336,
|
| 31 |
+
1008
|
| 32 |
+
]
|
| 33 |
+
],
|
| 34 |
+
"image_mean": [
|
| 35 |
+
0.48145466,
|
| 36 |
+
0.4578275,
|
| 37 |
+
0.40821073
|
| 38 |
+
],
|
| 39 |
+
"image_processor_type": "LlavaNextImageProcessor",
|
| 40 |
+
"image_std": [
|
| 41 |
+
0.26862954,
|
| 42 |
+
0.26130258,
|
| 43 |
+
0.27577711
|
| 44 |
+
],
|
| 45 |
+
"processor_class": "LlavaNextVideoProcessor",
|
| 46 |
+
"resample": 3,
|
| 47 |
+
"rescale_factor": 0.00392156862745098,
|
| 48 |
+
"size": {
|
| 49 |
+
"shortest_edge": 336
|
| 50 |
+
}
|
| 51 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_token": "<image>",
|
| 3 |
+
"video_token": "<video>",
|
| 4 |
+
"num_additional_image_tokens": 1,
|
| 5 |
+
"patch_size": 14,
|
| 6 |
+
"processor_class": "LlavaNextVideoProcessor",
|
| 7 |
+
"vision_feature_select_strategy": "default"
|
| 8 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<video>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<image>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"bos_token": "<s>",
|
| 48 |
+
"clean_up_tokenization_spaces": false,
|
| 49 |
+
"eos_token": "</s>",
|
| 50 |
+
"extra_special_tokens": {
|
| 51 |
+
"image_token": "<image>",
|
| 52 |
+
"video_token": "<video>"
|
| 53 |
+
},
|
| 54 |
+
"image_token": "<image>",
|
| 55 |
+
"legacy": false,
|
| 56 |
+
"model_max_length": 4096,
|
| 57 |
+
"pad_token": "<unk>",
|
| 58 |
+
"padding_side": "left",
|
| 59 |
+
"processor_class": "LlavaNextVideoProcessor",
|
| 60 |
+
"sp_model_kwargs": {},
|
| 61 |
+
"spaces_between_special_tokens": false,
|
| 62 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 63 |
+
"unk_token": "<unk>",
|
| 64 |
+
"use_default_system_prompt": false,
|
| 65 |
+
"video_token": "<video>"
|
| 66 |
+
}
|