[email protected]
commited on
Commit
•
0e2e85d
1
Parent(s):
a9f1279
Uploading checkpoints, tokenizers, and license
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- Dockerfile +14 -0
- README.md +275 -0
- config.json +141 -0
- incl_licenses/LICENSE +21 -0
- incl_licenses/LICENSE_2 +201 -0
- merges.txt +0 -0
- preprocessor_config.json +19 -0
- pytorch_model-00001-of-00046.bin +3 -0
- pytorch_model-00002-of-00046.bin +3 -0
- pytorch_model-00003-of-00046.bin +3 -0
- pytorch_model-00004-of-00046.bin +3 -0
- pytorch_model-00005-of-00046.bin +3 -0
- pytorch_model-00006-of-00046.bin +3 -0
- pytorch_model-00007-of-00046.bin +3 -0
- pytorch_model-00008-of-00046.bin +3 -0
- pytorch_model-00009-of-00046.bin +3 -0
- pytorch_model-00010-of-00046.bin +3 -0
- pytorch_model-00011-of-00046.bin +3 -0
- pytorch_model-00012-of-00046.bin +3 -0
- pytorch_model-00013-of-00046.bin +3 -0
- pytorch_model-00014-of-00046.bin +3 -0
- pytorch_model-00015-of-00046.bin +3 -0
- pytorch_model-00016-of-00046.bin +3 -0
- pytorch_model-00017-of-00046.bin +3 -0
- pytorch_model-00018-of-00046.bin +3 -0
- pytorch_model-00019-of-00046.bin +3 -0
- pytorch_model-00020-of-00046.bin +3 -0
- pytorch_model-00021-of-00046.bin +3 -0
- pytorch_model-00022-of-00046.bin +3 -0
- pytorch_model-00023-of-00046.bin +3 -0
- pytorch_model-00024-of-00046.bin +3 -0
- pytorch_model-00025-of-00046.bin +3 -0
- pytorch_model-00026-of-00046.bin +3 -0
- pytorch_model-00027-of-00046.bin +3 -0
- pytorch_model-00028-of-00046.bin +3 -0
- pytorch_model-00029-of-00046.bin +3 -0
- pytorch_model-00030-of-00046.bin +3 -0
- pytorch_model-00031-of-00046.bin +3 -0
- pytorch_model-00032-of-00046.bin +3 -0
- pytorch_model-00033-of-00046.bin +3 -0
- pytorch_model-00034-of-00046.bin +3 -0
- pytorch_model-00035-of-00046.bin +3 -0
- pytorch_model-00036-of-00046.bin +3 -0
- pytorch_model-00037-of-00046.bin +3 -0
- pytorch_model-00038-of-00046.bin +3 -0
- pytorch_model-00039-of-00046.bin +3 -0
- pytorch_model-00040-of-00046.bin +3 -0
- pytorch_model-00041-of-00046.bin +3 -0
- pytorch_model-00042-of-00046.bin +3 -0
- pytorch_model-00043-of-00046.bin +3 -0
Dockerfile
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FROM nvcr.io/nvidia/pytorch:23.09-py3
|
2 |
+
|
3 |
+
RUN pip install transformers==4.39.3
|
4 |
+
|
5 |
+
RUN pip install accelerate==0.34.2
|
6 |
+
|
7 |
+
RUN pip install datasets==2.18.0
|
8 |
+
|
9 |
+
RUN pip install timm==1.0.9
|
10 |
+
|
11 |
+
RUN pip install anls==0.0.2
|
12 |
+
|
13 |
+
RUN pip install pycocoevalcap==1.2
|
14 |
+
|
README.md
ADDED
@@ -0,0 +1,275 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
tags:
|
7 |
+
- nvidia
|
8 |
+
- NVLM
|
9 |
+
- pytorch
|
10 |
+
- multimodal
|
11 |
+
- conversational
|
12 |
+
---
|
13 |
+
|
14 |
+
|
15 |
+
## Model Details
|
16 |
+
|
17 |
+
Today (September 17th, 2024), we introduce [NVLM 1.0](https://arxiv.org/abs/2409.11402), a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training. We are open-sourcing the model weights and code for the community.
|
18 |
+
|
19 |
+
## Other Resources
|
20 |
+
[Inference Code (HF)](https://huggingface.co/nvidia/NVLM-1.0-D-72B/tree/main)   [Training Code (Coming soon)]()   [Website](https://nvlm-project.github.io/)   [Paper](https://arxiv.org/abs/2409.11402)
|
21 |
+
|
22 |
+
## Benchmark Results
|
23 |
+
We train our model with legacy [Megatron-LM](https://github.com/NVIDIA/Megatron-LM/tree/main/megatron/legacy) and adapt the codebase to Huggingface for model hosting, reproducibility, and inference.
|
24 |
+
We observe numerical differences between the Megatron and Huggingface codebases, which are within the expected range of variation.
|
25 |
+
We provide the results from both the Huggingface codebase and the Megatron codebase for reproducibility and comparison with other models.
|
26 |
+
|
27 |
+
Results (as of September 17th, 2024) in the multimodal benchmarks are as follows:
|
28 |
+
|
29 |
+
| Benchmark | MMMU (val / test) | MathVista | OCRBench | AI2D | ChartQA | DocVQA | TextVQA | RealWorldQA | VQAv2 |
|
30 |
+
|------------------------------|-------------------|-----------|----------|------|---------|--------|---------|-------------|-------|
|
31 |
+
| NVLM-D 1.0 72B (Huggingface) | 58.7 / 54.9 | 65.2 | 852 | 94.2 | 86.0 | 92.6 | 82.6 | 69.5 | 85.4 |
|
32 |
+
| NVLM-D 1.0 72B (Megatron) | 59.7 / 54.6 | 65.2 | 853 | 94.2 | 86.0 | 92.6 | 82.1 | 69.7 | 85.4 |
|
33 |
+
| Llama 3.2 90B | 60.3 / - | 57.3 | - | 92.3 | 85.5 | 90.1 | - | - | 78.1 |
|
34 |
+
| Llama 3-V 70B | 60.6 / - | - | - | 93.0 | 83.2 | 92.2 | 83.4 | - | 79.1 |
|
35 |
+
| Llama 3-V 405B | 64.5 / - | - | - | 94.1 | 85.8 | 92.6 | 84.8 | - | 80.2 |
|
36 |
+
| InternVL2-Llama3-76B | 55.2 / - | 65.5 | 839 | 94.8 | 88.4 | 94.1 | 84.4 | 72.2 | - |
|
37 |
+
| GPT-4V | 56.8 / 55.7 | 49.9 | 645 | 78.2 | 78.5 | 88.4 | 78.0 | 61.4 | 77.2 |
|
38 |
+
| GPT-4o | 69.1 / - | 63.8 | 736 | 94.2 | 85.7 | 92.8 | - | - | - |
|
39 |
+
| Claude 3.5 Sonnet | 68.3 / - | 67.7 | 788 | 94.7 | 90.8 | 95.2 | - | - | - |
|
40 |
+
| Gemini 1.5 Pro (Aug 2024) | 62.2 / - | 63.9 | 754 | 94.4 | 87.2 | 93.1 | 78.7 | 70.4 | 80.2 |
|
41 |
+
|
42 |
+
|
43 |
+
|
44 |
+
## How to use
|
45 |
+
|
46 |
+
When converting Megatron checkpoint to Huggingface, we adapt [InternVL codebase](https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B) to support model loading and multi-GPU inference in HF. For training, please refer to [Megatron-LM (Coming soon)]().
|
47 |
+
|
48 |
+
### Prepare the environment
|
49 |
+
|
50 |
+
We provide a docker build file in the [Dockerfile](Dockerfile) for reproduction.
|
51 |
+
|
52 |
+
The docker image is based on `nvcr.io/nvidia/pytorch:23.09-py3`.
|
53 |
+
|
54 |
+
*Note: We observe that different transformer versions / CUDA versions / docker versions can lead to slight benchmark number differences. We recommend using the Dockerfile above for precise reproduction.*
|
55 |
+
|
56 |
+
### Model loading
|
57 |
+
|
58 |
+
```python
|
59 |
+
import torch
|
60 |
+
from transformers import AutoModel
|
61 |
+
|
62 |
+
path = "nvidia/NVLM-D-72B"
|
63 |
+
model = AutoModel.from_pretrained(
|
64 |
+
path,
|
65 |
+
torch_dtype=torch.bfloat16,
|
66 |
+
low_cpu_mem_usage=True,
|
67 |
+
use_flash_attn=False,
|
68 |
+
trust_remote_code=True).eval()
|
69 |
+
```
|
70 |
+
|
71 |
+
### Multiple GPUs
|
72 |
+
|
73 |
+
The model can be loaded on multiple GPUs as follows:
|
74 |
+
|
75 |
+
```python
|
76 |
+
import torch
|
77 |
+
import math
|
78 |
+
from transformers import AutoModel
|
79 |
+
|
80 |
+
def split_model():
|
81 |
+
device_map = {}
|
82 |
+
world_size = torch.cuda.device_count()
|
83 |
+
num_layers = 80
|
84 |
+
# Since the first GPU will be used for ViT, treat it as half a GPU.
|
85 |
+
num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
|
86 |
+
num_layers_per_gpu = [num_layers_per_gpu] * world_size
|
87 |
+
num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
|
88 |
+
layer_cnt = 0
|
89 |
+
for i, num_layer in enumerate(num_layers_per_gpu):
|
90 |
+
for j in range(num_layer):
|
91 |
+
device_map[f'language_model.model.layers.{layer_cnt}'] = i
|
92 |
+
layer_cnt += 1
|
93 |
+
device_map['vision_model'] = 0
|
94 |
+
device_map['mlp1'] = 0
|
95 |
+
device_map['language_model.model.tok_embeddings'] = 0
|
96 |
+
device_map['language_model.model.embed_tokens'] = 0
|
97 |
+
device_map['language_model.output'] = 0
|
98 |
+
device_map['language_model.model.norm'] = 0
|
99 |
+
device_map['language_model.lm_head'] = 0
|
100 |
+
device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
|
101 |
+
|
102 |
+
return device_map
|
103 |
+
|
104 |
+
path = "nvidia/NVLM-D-72B"
|
105 |
+
device_map = split_model()
|
106 |
+
model = AutoModel.from_pretrained(
|
107 |
+
path,
|
108 |
+
torch_dtype=torch.bfloat16,
|
109 |
+
low_cpu_mem_usage=True,
|
110 |
+
use_flash_attn=False,
|
111 |
+
trust_remote_code=True,
|
112 |
+
device_map=device_map).eval()
|
113 |
+
```
|
114 |
+
|
115 |
+
|
116 |
+
### Inference
|
117 |
+
|
118 |
+
```python
|
119 |
+
import torch
|
120 |
+
from transformers import AutoTokenizer, AutoModel
|
121 |
+
import math
|
122 |
+
from PIL import Image
|
123 |
+
import torchvision.transforms as T
|
124 |
+
from torchvision.transforms.functional import InterpolationMode
|
125 |
+
|
126 |
+
|
127 |
+
def split_model():
|
128 |
+
device_map = {}
|
129 |
+
world_size = torch.cuda.device_count()
|
130 |
+
num_layers = 80
|
131 |
+
# Since the first GPU will be used for ViT, treat it as half a GPU.
|
132 |
+
num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
|
133 |
+
num_layers_per_gpu = [num_layers_per_gpu] * world_size
|
134 |
+
num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
|
135 |
+
layer_cnt = 0
|
136 |
+
for i, num_layer in enumerate(num_layers_per_gpu):
|
137 |
+
for j in range(num_layer):
|
138 |
+
device_map[f'language_model.model.layers.{layer_cnt}'] = i
|
139 |
+
layer_cnt += 1
|
140 |
+
device_map['vision_model'] = 0
|
141 |
+
device_map['mlp1'] = 0
|
142 |
+
device_map['language_model.model.tok_embeddings'] = 0
|
143 |
+
device_map['language_model.model.embed_tokens'] = 0
|
144 |
+
device_map['language_model.output'] = 0
|
145 |
+
device_map['language_model.model.norm'] = 0
|
146 |
+
device_map['language_model.lm_head'] = 0
|
147 |
+
device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
|
148 |
+
|
149 |
+
return device_map
|
150 |
+
|
151 |
+
|
152 |
+
IMAGENET_MEAN = (0.485, 0.456, 0.406)
|
153 |
+
IMAGENET_STD = (0.229, 0.224, 0.225)
|
154 |
+
|
155 |
+
|
156 |
+
def build_transform(input_size):
|
157 |
+
MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
|
158 |
+
transform = T.Compose([
|
159 |
+
T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
|
160 |
+
T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
|
161 |
+
T.ToTensor(),
|
162 |
+
T.Normalize(mean=MEAN, std=STD)
|
163 |
+
])
|
164 |
+
return transform
|
165 |
+
|
166 |
+
|
167 |
+
def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
|
168 |
+
best_ratio_diff = float('inf')
|
169 |
+
best_ratio = (1, 1)
|
170 |
+
area = width * height
|
171 |
+
for ratio in target_ratios:
|
172 |
+
target_aspect_ratio = ratio[0] / ratio[1]
|
173 |
+
ratio_diff = abs(aspect_ratio - target_aspect_ratio)
|
174 |
+
if ratio_diff < best_ratio_diff:
|
175 |
+
best_ratio_diff = ratio_diff
|
176 |
+
best_ratio = ratio
|
177 |
+
elif ratio_diff == best_ratio_diff:
|
178 |
+
if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
|
179 |
+
best_ratio = ratio
|
180 |
+
return best_ratio
|
181 |
+
|
182 |
+
|
183 |
+
def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
|
184 |
+
orig_width, orig_height = image.size
|
185 |
+
aspect_ratio = orig_width / orig_height
|
186 |
+
|
187 |
+
# calculate the existing image aspect ratio
|
188 |
+
target_ratios = set(
|
189 |
+
(i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
|
190 |
+
i * j <= max_num and i * j >= min_num)
|
191 |
+
target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
|
192 |
+
|
193 |
+
# find the closest aspect ratio to the target
|
194 |
+
target_aspect_ratio = find_closest_aspect_ratio(
|
195 |
+
aspect_ratio, target_ratios, orig_width, orig_height, image_size)
|
196 |
+
|
197 |
+
# calculate the target width and height
|
198 |
+
target_width = image_size * target_aspect_ratio[0]
|
199 |
+
target_height = image_size * target_aspect_ratio[1]
|
200 |
+
blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
|
201 |
+
|
202 |
+
# resize the image
|
203 |
+
resized_img = image.resize((target_width, target_height))
|
204 |
+
processed_images = []
|
205 |
+
for i in range(blocks):
|
206 |
+
box = (
|
207 |
+
(i % (target_width // image_size)) * image_size,
|
208 |
+
(i // (target_width // image_size)) * image_size,
|
209 |
+
((i % (target_width // image_size)) + 1) * image_size,
|
210 |
+
((i // (target_width // image_size)) + 1) * image_size
|
211 |
+
)
|
212 |
+
# split the image
|
213 |
+
split_img = resized_img.crop(box)
|
214 |
+
processed_images.append(split_img)
|
215 |
+
assert len(processed_images) == blocks
|
216 |
+
if use_thumbnail and len(processed_images) != 1:
|
217 |
+
thumbnail_img = image.resize((image_size, image_size))
|
218 |
+
processed_images.append(thumbnail_img)
|
219 |
+
return processed_images
|
220 |
+
|
221 |
+
|
222 |
+
def load_image(image_file, input_size=448, max_num=12):
|
223 |
+
image = Image.open(image_file).convert('RGB')
|
224 |
+
transform = build_transform(input_size=input_size)
|
225 |
+
images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
|
226 |
+
pixel_values = [transform(image) for image in images]
|
227 |
+
pixel_values = torch.stack(pixel_values)
|
228 |
+
return pixel_values
|
229 |
+
|
230 |
+
path = "nvidia/NVLM-D-72B"
|
231 |
+
device_map = split_model()
|
232 |
+
model = AutoModel.from_pretrained(
|
233 |
+
path,
|
234 |
+
torch_dtype=torch.bfloat16,
|
235 |
+
low_cpu_mem_usage=True,
|
236 |
+
use_flash_attn=False,
|
237 |
+
trust_remote_code=True,
|
238 |
+
device_map=device_map).eval()
|
239 |
+
|
240 |
+
print(model)
|
241 |
+
|
242 |
+
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
|
243 |
+
generation_config = dict(max_new_tokens=1024, do_sample=False)
|
244 |
+
|
245 |
+
# pure-text conversation
|
246 |
+
question = 'Hello, who are you?'
|
247 |
+
response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
|
248 |
+
print(f'User: {question}\nAssistant: {response}')
|
249 |
+
|
250 |
+
# single-image single-round conversation
|
251 |
+
pixel_values = load_image('path/to/your/example/image.jpg', max_num=6).to(
|
252 |
+
torch.bfloat16)
|
253 |
+
question = '<image>\nPlease describe the image shortly.'
|
254 |
+
response = model.chat(tokenizer, pixel_values, question, generation_config)
|
255 |
+
print(f'User: {question}\nAssistant: {response}')
|
256 |
+
```
|
257 |
+
|
258 |
+
|
259 |
+
## Correspondence to
|
260 |
+
Wenliang Dai* ([email protected]), Nayeon Lee* ([email protected]), Boxin Wang* ([email protected]), Zhuolin Yang* ([email protected]), Wei Ping* ([email protected])
|
261 |
+
|
262 |
+
*Equal contribution
|
263 |
+
|
264 |
+
## Citation
|
265 |
+
<pre>
|
266 |
+
@article{nvlm2024,
|
267 |
+
title={NVLM: Open Frontier-Class Multimodal LLMs},
|
268 |
+
author={Dai, Wenliang and Lee, Nayeon and Wang, Boxin and Yang, Zhuolin and Liu, Zihan and Barker, Jon and Rintamaki, Tuomas and Shoeybi, Mohammad and Catanzaro, Bryan and Ping, Wei},
|
269 |
+
journal={arXiv preprint},
|
270 |
+
year={2024}}
|
271 |
+
</pre>
|
272 |
+
|
273 |
+
|
274 |
+
## License
|
275 |
+
The use of this model is governed by the [cc-by-nc-4.0](https://spdx.org/licenses/CC-BY-NC-4.0)
|
config.json
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": null,
|
3 |
+
"architectures": [
|
4 |
+
"NVLM_D"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "configuration_nvlm_d.NVLM_D_Config",
|
8 |
+
"AutoModel": "modeling_nvlm_d.NVLM_D_Model",
|
9 |
+
"AutoModelForCausalLM": "modeling_nvlm_d.NVLM_D_Model"
|
10 |
+
},
|
11 |
+
"downsample_ratio": 0.5,
|
12 |
+
"dynamic_image_size": true,
|
13 |
+
"force_image_size": 448,
|
14 |
+
"llm_config": {
|
15 |
+
"_name_or_path": "Qwen/Qwen2-72B-Instruct",
|
16 |
+
"add_cross_attention": false,
|
17 |
+
"architectures": [
|
18 |
+
"Qwen2ForCausalLM"
|
19 |
+
],
|
20 |
+
"attention_bias": true,
|
21 |
+
"attention_dropout": 0.0,
|
22 |
+
"bad_words_ids": null,
|
23 |
+
"begin_suppress_tokens": null,
|
24 |
+
"bos_token_id": 151643,
|
25 |
+
"chunk_size_feed_forward": 0,
|
26 |
+
"cross_attention_hidden_size": null,
|
27 |
+
"decoder_start_token_id": null,
|
28 |
+
"diversity_penalty": 0.0,
|
29 |
+
"do_sample": false,
|
30 |
+
"early_stopping": false,
|
31 |
+
"encoder_no_repeat_ngram_size": 0,
|
32 |
+
"eos_token_id": 151645,
|
33 |
+
"exponential_decay_length_penalty": null,
|
34 |
+
"finetuning_task": null,
|
35 |
+
"forced_bos_token_id": null,
|
36 |
+
"forced_eos_token_id": null,
|
37 |
+
"hidden_act": "silu",
|
38 |
+
"hidden_size": 8192,
|
39 |
+
"id2label": {
|
40 |
+
"0": "LABEL_0",
|
41 |
+
"1": "LABEL_1"
|
42 |
+
},
|
43 |
+
"initializer_range": 0.02,
|
44 |
+
"intermediate_size": 29568,
|
45 |
+
"is_decoder": false,
|
46 |
+
"is_encoder_decoder": false,
|
47 |
+
"label2id": {
|
48 |
+
"LABEL_0": 0,
|
49 |
+
"LABEL_1": 1
|
50 |
+
},
|
51 |
+
"length_penalty": 1.0,
|
52 |
+
"max_length": 20,
|
53 |
+
"max_position_embeddings": 32768,
|
54 |
+
"min_length": 0,
|
55 |
+
"mlp_bias": false,
|
56 |
+
"model_type": "llama",
|
57 |
+
"no_repeat_ngram_size": 0,
|
58 |
+
"num_attention_heads": 64,
|
59 |
+
"num_beam_groups": 1,
|
60 |
+
"num_beams": 1,
|
61 |
+
"num_hidden_layers": 80,
|
62 |
+
"num_key_value_heads": 8,
|
63 |
+
"num_return_sequences": 1,
|
64 |
+
"output_attentions": false,
|
65 |
+
"output_hidden_states": false,
|
66 |
+
"output_scores": false,
|
67 |
+
"pad_token_id": null,
|
68 |
+
"prefix": null,
|
69 |
+
"pretraining_tp": 1,
|
70 |
+
"problem_type": null,
|
71 |
+
"pruned_heads": {},
|
72 |
+
"remove_invalid_values": false,
|
73 |
+
"repetition_penalty": 1.0,
|
74 |
+
"return_dict": true,
|
75 |
+
"return_dict_in_generate": false,
|
76 |
+
"rms_norm_eps": 1e-06,
|
77 |
+
"rope_scaling": {
|
78 |
+
"factor": 3.0,
|
79 |
+
"type": "dynamic"
|
80 |
+
},
|
81 |
+
"rope_theta": 1000000.0,
|
82 |
+
"sep_token_id": null,
|
83 |
+
"suppress_tokens": null,
|
84 |
+
"task_specific_params": null,
|
85 |
+
"temperature": 1.0,
|
86 |
+
"tf_legacy_loss": false,
|
87 |
+
"tie_encoder_decoder": false,
|
88 |
+
"tie_word_embeddings": false,
|
89 |
+
"tokenizer_class": null,
|
90 |
+
"top_k": 1,
|
91 |
+
"top_p": 0,
|
92 |
+
"torch_dtype": "bfloat16",
|
93 |
+
"torchscript": false,
|
94 |
+
"transformers_version": "4.39.3",
|
95 |
+
"typical_p": 1.0,
|
96 |
+
"use_bfloat16": true,
|
97 |
+
"use_cache": true,
|
98 |
+
"vocab_size": 152064
|
99 |
+
},
|
100 |
+
"max_dynamic_patch": 6,
|
101 |
+
"min_dynamic_patch": 1,
|
102 |
+
"model_type": "NVLM_D",
|
103 |
+
"ps_version": "v2",
|
104 |
+
"select_layer": -1,
|
105 |
+
"template": "chatml",
|
106 |
+
"torch_dtype": "bfloat16",
|
107 |
+
"transformers_version": null,
|
108 |
+
"use_backbone_lora": 0,
|
109 |
+
"use_llm_lora": 0,
|
110 |
+
"use_thumbnail": true,
|
111 |
+
"vision_config": {
|
112 |
+
"architectures": [
|
113 |
+
"InternVisionModel"
|
114 |
+
],
|
115 |
+
"attention_dropout": 0.0,
|
116 |
+
"drop_path_rate": 0.0,
|
117 |
+
"dropout": 0.0,
|
118 |
+
"hidden_act": "gelu",
|
119 |
+
"hidden_size": 3200,
|
120 |
+
"image_size": 448,
|
121 |
+
"initializer_factor": 0.1,
|
122 |
+
"initializer_range": 1e-10,
|
123 |
+
"intermediate_size": 12800,
|
124 |
+
"layer_norm_eps": 1e-06,
|
125 |
+
"model_type": "intern_vit_6b",
|
126 |
+
"norm_type": "rms_norm",
|
127 |
+
"num_attention_heads": 25,
|
128 |
+
"num_channels": 3,
|
129 |
+
"num_hidden_layers": 45,
|
130 |
+
"output_attentions": false,
|
131 |
+
"output_hidden_states": false,
|
132 |
+
"patch_size": 14,
|
133 |
+
"qk_normalization": true,
|
134 |
+
"qkv_bias": false,
|
135 |
+
"return_dict": true,
|
136 |
+
"torch_dtype": "bfloat16",
|
137 |
+
"transformers_version": "4.39.3",
|
138 |
+
"use_bfloat16": true,
|
139 |
+
"use_flash_attn": true
|
140 |
+
}
|
141 |
+
}
|
incl_licenses/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
MIT License
|
2 |
+
|
3 |
+
Copyright (c) 2023 OpenGVLab
|
4 |
+
|
5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6 |
+
of this software and associated documentation files (the "Software"), to deal
|
7 |
+
in the Software without restriction, including without limitation the rights
|
8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9 |
+
copies of the Software, and to permit persons to whom the Software is
|
10 |
+
furnished to do so, subject to the following conditions:
|
11 |
+
|
12 |
+
The above copyright notice and this permission notice shall be included in all
|
13 |
+
copies or substantial portions of the Software.
|
14 |
+
|
15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
21 |
+
SOFTWARE.
|
incl_licenses/LICENSE_2
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Apache License
|
2 |
+
Version 2.0, January 2004
|
3 |
+
http://www.apache.org/licenses/
|
4 |
+
|
5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6 |
+
|
7 |
+
1. Definitions.
|
8 |
+
|
9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
11 |
+
|
12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13 |
+
the copyright owner that is granting the License.
|
14 |
+
|
15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
16 |
+
other entities that control, are controlled by, or are under common
|
17 |
+
control with that entity. For the purposes of this definition,
|
18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
19 |
+
direction or management of such entity, whether by contract or
|
20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22 |
+
|
23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24 |
+
exercising permissions granted by this License.
|
25 |
+
|
26 |
+
"Source" form shall mean the preferred form for making modifications,
|
27 |
+
including but not limited to software source code, documentation
|
28 |
+
source, and configuration files.
|
29 |
+
|
30 |
+
"Object" form shall mean any form resulting from mechanical
|
31 |
+
transformation or translation of a Source form, including but
|
32 |
+
not limited to compiled object code, generated documentation,
|
33 |
+
and conversions to other media types.
|
34 |
+
|
35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
36 |
+
Object form, made available under the License, as indicated by a
|
37 |
+
copyright notice that is included in or attached to the work
|
38 |
+
(an example is provided in the Appendix below).
|
39 |
+
|
40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41 |
+
form, that is based on (or derived from) the Work and for which the
|
42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
44 |
+
of this License, Derivative Works shall not include works that remain
|
45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46 |
+
the Work and Derivative Works thereof.
|
47 |
+
|
48 |
+
"Contribution" shall mean any work of authorship, including
|
49 |
+
the original version of the Work and any modifications or additions
|
50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
54 |
+
means any form of electronic, verbal, or written communication sent
|
55 |
+
to the Licensor or its representatives, including but not limited to
|
56 |
+
communication on electronic mailing lists, source code control systems,
|
57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
59 |
+
excluding communication that is conspicuously marked or otherwise
|
60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
61 |
+
|
62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
64 |
+
subsequently incorporated within the Work.
|
65 |
+
|
66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
71 |
+
Work and such Derivative Works in Source or Object form.
|
72 |
+
|
73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76 |
+
(except as stated in this section) patent license to make, have made,
|
77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78 |
+
where such license applies only to those patent claims licensable
|
79 |
+
by such Contributor that are necessarily infringed by their
|
80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
82 |
+
institute patent litigation against any entity (including a
|
83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84 |
+
or a Contribution incorporated within the Work constitutes direct
|
85 |
+
or contributory patent infringement, then any patent licenses
|
86 |
+
granted to You under this License for that Work shall terminate
|
87 |
+
as of the date such litigation is filed.
|
88 |
+
|
89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
90 |
+
Work or Derivative Works thereof in any medium, with or without
|
91 |
+
modifications, and in Source or Object form, provided that You
|
92 |
+
meet the following conditions:
|
93 |
+
|
94 |
+
(a) You must give any other recipients of the Work or
|
95 |
+
Derivative Works a copy of this License; and
|
96 |
+
|
97 |
+
(b) You must cause any modified files to carry prominent notices
|
98 |
+
stating that You changed the files; and
|
99 |
+
|
100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
101 |
+
that You distribute, all copyright, patent, trademark, and
|
102 |
+
attribution notices from the Source form of the Work,
|
103 |
+
excluding those notices that do not pertain to any part of
|
104 |
+
the Derivative Works; and
|
105 |
+
|
106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107 |
+
distribution, then any Derivative Works that You distribute must
|
108 |
+
include a readable copy of the attribution notices contained
|
109 |
+
within such NOTICE file, excluding those notices that do not
|
110 |
+
pertain to any part of the Derivative Works, in at least one
|
111 |
+
of the following places: within a NOTICE text file distributed
|
112 |
+
as part of the Derivative Works; within the Source form or
|
113 |
+
documentation, if provided along with the Derivative Works; or,
|
114 |
+
within a display generated by the Derivative Works, if and
|
115 |
+
wherever such third-party notices normally appear. The contents
|
116 |
+
of the NOTICE file are for informational purposes only and
|
117 |
+
do not modify the License. You may add Your own attribution
|
118 |
+
notices within Derivative Works that You distribute, alongside
|
119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
120 |
+
that such additional attribution notices cannot be construed
|
121 |
+
as modifying the License.
|
122 |
+
|
123 |
+
You may add Your own copyright statement to Your modifications and
|
124 |
+
may provide additional or different license terms and conditions
|
125 |
+
for use, reproduction, or distribution of Your modifications, or
|
126 |
+
for any such Derivative Works as a whole, provided Your use,
|
127 |
+
reproduction, and distribution of the Work otherwise complies with
|
128 |
+
the conditions stated in this License.
|
129 |
+
|
130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
132 |
+
by You to the Licensor shall be under the terms and conditions of
|
133 |
+
this License, without any additional terms or conditions.
|
134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135 |
+
the terms of any separate license agreement you may have executed
|
136 |
+
with Licensor regarding such Contributions.
|
137 |
+
|
138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
140 |
+
except as required for reasonable and customary use in describing the
|
141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
142 |
+
|
143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144 |
+
agreed to in writing, Licensor provides the Work (and each
|
145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147 |
+
implied, including, without limitation, any warranties or conditions
|
148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150 |
+
appropriateness of using or redistributing the Work and assume any
|
151 |
+
risks associated with Your exercise of permissions under this License.
|
152 |
+
|
153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
154 |
+
whether in tort (including negligence), contract, or otherwise,
|
155 |
+
unless required by applicable law (such as deliberate and grossly
|
156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157 |
+
liable to You for damages, including any direct, indirect, special,
|
158 |
+
incidental, or consequential damages of any character arising as a
|
159 |
+
result of this License or out of the use or inability to use the
|
160 |
+
Work (including but not limited to damages for loss of goodwill,
|
161 |
+
work stoppage, computer failure or malfunction, or any and all
|
162 |
+
other commercial damages or losses), even if such Contributor
|
163 |
+
has been advised of the possibility of such damages.
|
164 |
+
|
165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168 |
+
or other liability obligations and/or rights consistent with this
|
169 |
+
License. However, in accepting such obligations, You may act only
|
170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171 |
+
of any other Contributor, and only if You agree to indemnify,
|
172 |
+
defend, and hold each Contributor harmless for any liability
|
173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
174 |
+
of your accepting any such warranty or additional liability.
|
175 |
+
|
176 |
+
END OF TERMS AND CONDITIONS
|
177 |
+
|
178 |
+
APPENDIX: How to apply the Apache License to your work.
|
179 |
+
|
180 |
+
To apply the Apache License to your work, attach the following
|
181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
182 |
+
replaced with your own identifying information. (Don't include
|
183 |
+
the brackets!) The text should be enclosed in the appropriate
|
184 |
+
comment syntax for the file format. We also recommend that a
|
185 |
+
file or class name and description of purpose be included on the
|
186 |
+
same "printed page" as the copyright notice for easier
|
187 |
+
identification within third-party archives.
|
188 |
+
|
189 |
+
Copyright [yyyy] [name of copyright owner]
|
190 |
+
|
191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192 |
+
you may not use this file except in compliance with the License.
|
193 |
+
You may obtain a copy of the License at
|
194 |
+
|
195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
196 |
+
|
197 |
+
Unless required by applicable law or agreed to in writing, software
|
198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200 |
+
See the License for the specific language governing permissions and
|
201 |
+
limitations under the License.
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": 448,
|
3 |
+
"do_center_crop": true,
|
4 |
+
"do_normalize": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
7 |
+
"image_mean": [
|
8 |
+
0.485,
|
9 |
+
0.456,
|
10 |
+
0.406
|
11 |
+
],
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"size": 448
|
19 |
+
}
|
pytorch_model-00001-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09d7adb5a772be68592ad97edca1510b76f59ac11d5a3b608ebc9c62da585e29
|
3 |
+
size 3732886635
|
pytorch_model-00002-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7497eac26dd8216cf0cec43d6b987b817a8b8b6e13466db8d432c4715d0a5d9a
|
3 |
+
size 3846333146
|
pytorch_model-00003-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c64a9b08b00f84f52dab4fbdc9d74c935ed3b92e4479868752554e12330c9b33
|
3 |
+
size 3846333146
|
pytorch_model-00004-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f02a5f68e3806c2b6ae3340afdab0c58c4c05ce192ec3769985cb5f306bf58ed
|
3 |
+
size 3846333146
|
pytorch_model-00005-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d76a19b00bf3d19ea23cd3028e9159b803f9eebd9e8005d2c1310d5859b5ad5
|
3 |
+
size 3846333146
|
pytorch_model-00006-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4d26e426d781e3c064b566e8603d7a2ac9f21884edfd1e07a13a8b0a0bacf6d
|
3 |
+
size 3846333146
|
pytorch_model-00007-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24809be438789fa12e0086f2e322a90fc2cb2366e839bbd2a30f68db997e1a21
|
3 |
+
size 3846333210
|
pytorch_model-00008-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77d1887020232d33fe96693cb844fce415612ad6c55c1c1613dbc57de29fdd2a
|
3 |
+
size 3846333210
|
pytorch_model-00009-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95baf7daff6af4dad8d54cc9f82bb86ee182b647cf720d23175626b360da6081
|
3 |
+
size 3846333210
|
pytorch_model-00010-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34b61d4fee7f4e01006ecac309b65b9ac9a68012e1b275d053d7b84858db3a1c
|
3 |
+
size 3846333210
|
pytorch_model-00011-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e809fe0737d2275578c1946be10cd582b7175feb1fd99beb6f8595662551fc5
|
3 |
+
size 3846333210
|
pytorch_model-00012-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba9ac5bf8b075bd5da4f27c26f06ab8b9c2ca6d07fb99d0bec4bf9aac166da0c
|
3 |
+
size 3846333210
|
pytorch_model-00013-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c7ac534453874d58451f3287dab57c7b064058ae590ef7b4df61c9d84140b65
|
3 |
+
size 3846333210
|
pytorch_model-00014-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b3086a774259da607e85340f00b9d90fb7da305bbf4291c14bec0e78bd544d7
|
3 |
+
size 3846333210
|
pytorch_model-00015-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e86b1a3af51947ffa37179546f68a30c013fed87a1b593f09ca7dd5108bd6e8
|
3 |
+
size 3846333210
|
pytorch_model-00016-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef7f7b1033229434579ee43fa52f31a02724eb30efbc8c1008fadcd769ace32f
|
3 |
+
size 3846333210
|
pytorch_model-00017-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d64a3db26926b8b833e24736781df164ef8e2bd6aa373c67d52ccce2ada2783b
|
3 |
+
size 3846333210
|
pytorch_model-00018-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c8ad0671d8deb55cbd23c88d066f336ddf394ec11f1ee53d286d6b5de7bf32c
|
3 |
+
size 3846333210
|
pytorch_model-00019-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b62cede7662ebc3418bba1a660ad9f061c6fe81c7d374ac38fa739c0553c2fce
|
3 |
+
size 3846333210
|
pytorch_model-00020-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74e5845f01413406edfc4ec28f71886a61e5c09915bef65ffc37336034dae7d0
|
3 |
+
size 3846333210
|
pytorch_model-00021-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65b3da31660e3b4abd6b4f6c5c55c118899e1511e6182e9c0d9a8c51c591227a
|
3 |
+
size 3846333210
|
pytorch_model-00022-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5963f91078851e70cb3f5e6642c976f69670874e7dd2048f78b20a727ebb0bc
|
3 |
+
size 3846333210
|
pytorch_model-00023-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6311fac9d7186a075c439d2f3eaed126e9e9460efd00264fe841d633e1eef383
|
3 |
+
size 3846333210
|
pytorch_model-00024-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:293a9b85ceab5f94f90b7a5a7343b0dd4994e68307055fd7be5e46714f7bc1e5
|
3 |
+
size 3846333210
|
pytorch_model-00025-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df6378e42370590b62407c6dc9549768aba6d8d02a8ac8379a2ab3f9bef794e6
|
3 |
+
size 3846333210
|
pytorch_model-00026-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9716138dea98f9755c9654d219e2cb8e9076c12f869950791a21e1bf61dd5fae
|
3 |
+
size 3846333210
|
pytorch_model-00027-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4805b2f377a77dfe20336350d78409db3d841fb5bda8e1a737f2f83e5dc43592
|
3 |
+
size 3846333210
|
pytorch_model-00028-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29dfa3901c845ee5526ddcfdd98e8a1711d8bb00b08ce97a4ec82599f2347e6e
|
3 |
+
size 3846333210
|
pytorch_model-00029-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0af81554838908e52dc3a6c13d44a20acde7bf7f983a8d38c2f7d48adbf536dd
|
3 |
+
size 3846333210
|
pytorch_model-00030-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c44a87014ac0de0df82c9d846316c831a11fc97233c0de7c03d848dba7e859f3
|
3 |
+
size 3846333210
|
pytorch_model-00031-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf4b8d18d8214c4761b46689bc245e669608aa43233e174476360674854c1ff2
|
3 |
+
size 3846333210
|
pytorch_model-00032-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f2e26602b09ec9e179a244d30c0edda94d2289bc086ad05d3aa8be785b8dbf8
|
3 |
+
size 3846333210
|
pytorch_model-00033-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdce2cf88821141313e7a19b010bdd760a00228eb37053a19851dc9c4a380fa0
|
3 |
+
size 3846333210
|
pytorch_model-00034-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f44d3c4d3a62d5b8113ff056f1b3085b7f731b1e38452db5fe3f49ce4acfa9c
|
3 |
+
size 3846333210
|
pytorch_model-00035-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d52db37d9a87911181c1bcc4fdd4124c438fe7e188d10e8724b5d598e383bbd
|
3 |
+
size 3846333210
|
pytorch_model-00036-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b09ad964ee928715efd0456991c89c2b3608036abba785696ddef8121a32c74b
|
3 |
+
size 3846333210
|
pytorch_model-00037-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf3e5ae2bf830a5c77ae0a89a5dc0148c9601c25f7f44a356f36fffc1b9e4c19
|
3 |
+
size 3846333210
|
pytorch_model-00038-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f43878469fe151d44f5ed855c8f21e6fa587d61c2a1c38fce8d91d920249b307
|
3 |
+
size 3846333210
|
pytorch_model-00039-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfcc6cb08a1ad868ddbbd211775c9c51fa0725644a8266be6fb333892ec71bcd
|
3 |
+
size 3846333210
|
pytorch_model-00040-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe3fc7b25b658a6545d6c361412f9b555135395c18b115a678418c7959f8e968
|
3 |
+
size 3846333210
|
pytorch_model-00041-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e54e3cf2d5697d76405be4b0e1dc848c81b63b2cf1c060fb36dfedd78d14cc0
|
3 |
+
size 3846316424
|
pytorch_model-00042-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ce6c1061ab0b18a8c8eb5661ed6ef8b0e7693771e215e85f7a11465698b01f1
|
3 |
+
size 3996393552
|
pytorch_model-00043-of-00046.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:720628a087f8360aec910731bb23ddc03664de6664cffbb97a5d7cba8d6b5b1b
|
3 |
+
size 3946320203
|