Uploading checkpoints, tokenizers, and license

Dockerfile

@@ -0,0 +1,14 @@
+FROM nvcr.io/nvidia/pytorch:23.09-py3
+
+RUN pip install transformers==4.39.3
+
+RUN pip install accelerate==0.34.2
+
+RUN pip install datasets==2.18.0
+
+RUN pip install timm==1.0.9
+
+RUN pip install anls==0.0.2
+
+RUN pip install pycocoevalcap==1.2
+

README.md

@@ -0,0 +1,275 @@
+---
+license: cc-by-nc-4.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- nvidia
+- NVLM
+- pytorch
+- multimodal
+- conversational
+---
+
+
+## Model Details
+
+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.
+
+## Other Resources
+[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)
+
+## Benchmark Results
+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.
+We observe numerical differences between the Megatron and Huggingface codebases, which are within the expected range of variation. 
+We provide the results from both the Huggingface codebase and the Megatron codebase for reproducibility and comparison with other models.
+
+Results (as of September 17th, 2024) in the multimodal benchmarks are as follows:
+
+| Benchmark                    | MMMU (val / test) | MathVista | OCRBench | AI2D | ChartQA | DocVQA | TextVQA | RealWorldQA | VQAv2 |
+|------------------------------|-------------------|-----------|----------|------|---------|--------|---------|-------------|-------|
+| 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  |
+| 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  |
+| Llama 3.2 90B                | 60.3 / -          | 57.3      | -        | 92.3 | 85.5    | 90.1   | -       | -           | 78.1  |
+| Llama 3-V 70B                | 60.6 / -          | -         | -        | 93.0 | 83.2    | 92.2   | 83.4    | -           | 79.1  |
+| Llama 3-V 405B               | 64.5 / -          | -         | -        | 94.1 | 85.8    | 92.6   | 84.8    | -           | 80.2  |
+| InternVL2-Llama3-76B         | 55.2 / -          | 65.5      | 839      | 94.8 | 88.4    | 94.1   | 84.4    | 72.2        | -     |
+| GPT-4V                       | 56.8 / 55.7       | 49.9      | 645      | 78.2 | 78.5    | 88.4   | 78.0    | 61.4        | 77.2  |
+| GPT-4o                       | 69.1 / -          | 63.8      | 736      | 94.2 | 85.7    | 92.8   | -       | -           | -     |
+| Claude 3.5 Sonnet            | 68.3 / -          | 67.7      | 788      | 94.7 | 90.8    | 95.2   | -       | -           | -     |
+| Gemini 1.5 Pro (Aug 2024)    | 62.2 / -          | 63.9      | 754      | 94.4 | 87.2    | 93.1   | 78.7    | 70.4        | 80.2  |
+
+
+
+## How to use
+
+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)]().
+
+### Prepare the environment
+
+We provide a docker build file in the [Dockerfile](Dockerfile) for reproduction. 
+
+The docker image is based on `nvcr.io/nvidia/pytorch:23.09-py3`. 
+
+*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.*
+
+### Model loading
+
+```python
+import torch
+from transformers import AutoModel
+
+path = "nvidia/NVLM-D-72B"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    use_flash_attn=False,
+    trust_remote_code=True).eval()
+```
+
+### Multiple GPUs
+
+The model can be loaded on multiple GPUs as follows:
+
+```python
+import torch
+import math
+from transformers import AutoModel
+
+def split_model():
+    device_map = {}
+    world_size = torch.cuda.device_count()
+    num_layers = 80
+    # Since the first GPU will be used for ViT, treat it as half a GPU.
+    num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
+    num_layers_per_gpu = [num_layers_per_gpu] * world_size
+    num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
+    layer_cnt = 0
+    for i, num_layer in enumerate(num_layers_per_gpu):
+        for j in range(num_layer):
+            device_map[f'language_model.model.layers.{layer_cnt}'] = i
+            layer_cnt += 1
+    device_map['vision_model'] = 0
+    device_map['mlp1'] = 0
+    device_map['language_model.model.tok_embeddings'] = 0
+    device_map['language_model.model.embed_tokens'] = 0
+    device_map['language_model.output'] = 0
+    device_map['language_model.model.norm'] = 0
+    device_map['language_model.lm_head'] = 0
+    device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
+
+    return device_map
+
+path = "nvidia/NVLM-D-72B"
+device_map = split_model()
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    use_flash_attn=False,
+    trust_remote_code=True,
+    device_map=device_map).eval()
+```
+
+
+### Inference
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModel
+import math
+from PIL import Image
+import torchvision.transforms as T
+from torchvision.transforms.functional import InterpolationMode
+
+
+def split_model():
+    device_map = {}
+    world_size = torch.cuda.device_count()
+    num_layers = 80
+    # Since the first GPU will be used for ViT, treat it as half a GPU.
+    num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
+    num_layers_per_gpu = [num_layers_per_gpu] * world_size
+    num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
+    layer_cnt = 0
+    for i, num_layer in enumerate(num_layers_per_gpu):
+        for j in range(num_layer):
+            device_map[f'language_model.model.layers.{layer_cnt}'] = i
+            layer_cnt += 1
+    device_map['vision_model'] = 0
+    device_map['mlp1'] = 0
+    device_map['language_model.model.tok_embeddings'] = 0
+    device_map['language_model.model.embed_tokens'] = 0
+    device_map['language_model.output'] = 0
+    device_map['language_model.model.norm'] = 0
+    device_map['language_model.lm_head'] = 0
+    device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
+
+    return device_map
+
+
+IMAGENET_MEAN = (0.485, 0.456, 0.406)
+IMAGENET_STD = (0.229, 0.224, 0.225)
+
+
+def build_transform(input_size):
+    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
+    transform = T.Compose([
+        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
+        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
+        T.ToTensor(),
+        T.Normalize(mean=MEAN, std=STD)
+    ])
+    return transform
+
+
+def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
+    best_ratio_diff = float('inf')
+    best_ratio = (1, 1)
+    area = width * height
+    for ratio in target_ratios:
+        target_aspect_ratio = ratio[0] / ratio[1]
+        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
+        if ratio_diff < best_ratio_diff:
+            best_ratio_diff = ratio_diff
+            best_ratio = ratio
+        elif ratio_diff == best_ratio_diff:
+            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
+                best_ratio = ratio
+    return best_ratio
+
+
+def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
+    orig_width, orig_height = image.size
+    aspect_ratio = orig_width / orig_height
+
+    # calculate the existing image aspect ratio
+    target_ratios = set(
+        (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
+        i * j <= max_num and i * j >= min_num)
+    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
+
+    # find the closest aspect ratio to the target
+    target_aspect_ratio = find_closest_aspect_ratio(
+        aspect_ratio, target_ratios, orig_width, orig_height, image_size)
+
+    # calculate the target width and height
+    target_width = image_size * target_aspect_ratio[0]
+    target_height = image_size * target_aspect_ratio[1]
+    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
+
+    # resize the image
+    resized_img = image.resize((target_width, target_height))
+    processed_images = []
+    for i in range(blocks):
+        box = (
+            (i % (target_width // image_size)) * image_size,
+            (i // (target_width // image_size)) * image_size,
+            ((i % (target_width // image_size)) + 1) * image_size,
+            ((i // (target_width // image_size)) + 1) * image_size
+        )
+        # split the image
+        split_img = resized_img.crop(box)
+        processed_images.append(split_img)
+    assert len(processed_images) == blocks
+    if use_thumbnail and len(processed_images) != 1:
+        thumbnail_img = image.resize((image_size, image_size))
+        processed_images.append(thumbnail_img)
+    return processed_images
+
+
+def load_image(image_file, input_size=448, max_num=12):
+    image = Image.open(image_file).convert('RGB')
+    transform = build_transform(input_size=input_size)
+    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
+    pixel_values = [transform(image) for image in images]
+    pixel_values = torch.stack(pixel_values)
+    return pixel_values
+
+path = "nvidia/NVLM-D-72B"
+device_map = split_model()
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    use_flash_attn=False,
+    trust_remote_code=True,
+    device_map=device_map).eval()
+
+print(model)
+
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+
+# pure-text conversation
+question = 'Hello, who are you?'
+response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
+print(f'User: {question}\nAssistant: {response}')
+
+# single-image single-round conversation
+pixel_values = load_image('path/to/your/example/image.jpg', max_num=6).to(
+    torch.bfloat16)
+question = '<image>\nPlease describe the image shortly.'
+response = model.chat(tokenizer, pixel_values, question, generation_config)
+print(f'User: {question}\nAssistant: {response}')
+```
+
+
+## Correspondence to
+Wenliang Dai* ([email protected]), Nayeon Lee* ([email protected]), Boxin Wang* ([email protected]), Zhuolin Yang* ([email protected]), Wei Ping* ([email protected])
+
+*Equal contribution
+
+## Citation
+<pre>
+@article{nvlm2024,
+  title={NVLM: Open Frontier-Class Multimodal LLMs},
+  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},
+  journal={arXiv preprint},
+  year={2024}}
+</pre>
+
+
+## License
+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

@@ -0,0 +1,141 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "NVLM_D"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_nvlm_d.NVLM_D_Config",
+    "AutoModel": "modeling_nvlm_d.NVLM_D_Model",
+    "AutoModelForCausalLM": "modeling_nvlm_d.NVLM_D_Model"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "llm_config": {
+    "_name_or_path": "Qwen/Qwen2-72B-Instruct",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 151645,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 29568,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "min_length": 0,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 64,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "factor": 3.0,
+      "type": "dynamic"
+    },
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 1,
+    "top_p": 0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.39.3",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_cache": true,
+    "vocab_size": 152064
+  },
+  "max_dynamic_patch": 6,
+  "min_dynamic_patch": 1,
+  "model_type": "NVLM_D",
+  "ps_version": "v2",
+  "select_layer": -1,
+  "template": "chatml",
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_backbone_lora": 0,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "vision_config": {
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "drop_path_rate": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 3200,
+    "image_size": 448,
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 12800,
+    "layer_norm_eps": 1e-06,
+    "model_type": "intern_vit_6b",
+    "norm_type": "rms_norm",
+    "num_attention_heads": 25,
+    "num_channels": 3,
+    "num_hidden_layers": 45,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 14,
+    "qk_normalization": true,
+    "qkv_bias": false,
+    "return_dict": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.3",
+    "use_bfloat16": true,
+    "use_flash_attn": true
+  }
+}

incl_licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 OpenGVLab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

incl_licenses/LICENSE_2

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 448,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "size": 448
+}

pytorch_model-00001-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d7adb5a772be68592ad97edca1510b76f59ac11d5a3b608ebc9c62da585e29
+size 3732886635

pytorch_model-00002-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7497eac26dd8216cf0cec43d6b987b817a8b8b6e13466db8d432c4715d0a5d9a
+size 3846333146

pytorch_model-00003-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64a9b08b00f84f52dab4fbdc9d74c935ed3b92e4479868752554e12330c9b33
+size 3846333146

pytorch_model-00004-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02a5f68e3806c2b6ae3340afdab0c58c4c05ce192ec3769985cb5f306bf58ed
+size 3846333146

pytorch_model-00005-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d76a19b00bf3d19ea23cd3028e9159b803f9eebd9e8005d2c1310d5859b5ad5
+size 3846333146

pytorch_model-00006-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d26e426d781e3c064b566e8603d7a2ac9f21884edfd1e07a13a8b0a0bacf6d
+size 3846333146

pytorch_model-00007-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24809be438789fa12e0086f2e322a90fc2cb2366e839bbd2a30f68db997e1a21
+size 3846333210

pytorch_model-00008-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d1887020232d33fe96693cb844fce415612ad6c55c1c1613dbc57de29fdd2a
+size 3846333210

pytorch_model-00009-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95baf7daff6af4dad8d54cc9f82bb86ee182b647cf720d23175626b360da6081
+size 3846333210

pytorch_model-00010-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b61d4fee7f4e01006ecac309b65b9ac9a68012e1b275d053d7b84858db3a1c
+size 3846333210

pytorch_model-00011-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e809fe0737d2275578c1946be10cd582b7175feb1fd99beb6f8595662551fc5
+size 3846333210

pytorch_model-00012-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9ac5bf8b075bd5da4f27c26f06ab8b9c2ca6d07fb99d0bec4bf9aac166da0c
+size 3846333210

pytorch_model-00013-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7ac534453874d58451f3287dab57c7b064058ae590ef7b4df61c9d84140b65
+size 3846333210

pytorch_model-00014-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3086a774259da607e85340f00b9d90fb7da305bbf4291c14bec0e78bd544d7
+size 3846333210

pytorch_model-00015-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e86b1a3af51947ffa37179546f68a30c013fed87a1b593f09ca7dd5108bd6e8
+size 3846333210

pytorch_model-00016-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7f7b1033229434579ee43fa52f31a02724eb30efbc8c1008fadcd769ace32f
+size 3846333210

pytorch_model-00017-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64a3db26926b8b833e24736781df164ef8e2bd6aa373c67d52ccce2ada2783b
+size 3846333210

pytorch_model-00018-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8ad0671d8deb55cbd23c88d066f336ddf394ec11f1ee53d286d6b5de7bf32c
+size 3846333210

pytorch_model-00019-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62cede7662ebc3418bba1a660ad9f061c6fe81c7d374ac38fa739c0553c2fce
+size 3846333210

pytorch_model-00020-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e5845f01413406edfc4ec28f71886a61e5c09915bef65ffc37336034dae7d0
+size 3846333210

pytorch_model-00021-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b3da31660e3b4abd6b4f6c5c55c118899e1511e6182e9c0d9a8c51c591227a
+size 3846333210

pytorch_model-00022-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5963f91078851e70cb3f5e6642c976f69670874e7dd2048f78b20a727ebb0bc
+size 3846333210

pytorch_model-00023-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6311fac9d7186a075c439d2f3eaed126e9e9460efd00264fe841d633e1eef383
+size 3846333210

pytorch_model-00024-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293a9b85ceab5f94f90b7a5a7343b0dd4994e68307055fd7be5e46714f7bc1e5
+size 3846333210

pytorch_model-00025-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6378e42370590b62407c6dc9549768aba6d8d02a8ac8379a2ab3f9bef794e6
+size 3846333210

pytorch_model-00026-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9716138dea98f9755c9654d219e2cb8e9076c12f869950791a21e1bf61dd5fae
+size 3846333210

pytorch_model-00027-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4805b2f377a77dfe20336350d78409db3d841fb5bda8e1a737f2f83e5dc43592
+size 3846333210

pytorch_model-00028-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29dfa3901c845ee5526ddcfdd98e8a1711d8bb00b08ce97a4ec82599f2347e6e
+size 3846333210

pytorch_model-00029-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af81554838908e52dc3a6c13d44a20acde7bf7f983a8d38c2f7d48adbf536dd
+size 3846333210

pytorch_model-00030-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c44a87014ac0de0df82c9d846316c831a11fc97233c0de7c03d848dba7e859f3
+size 3846333210

pytorch_model-00031-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4b8d18d8214c4761b46689bc245e669608aa43233e174476360674854c1ff2
+size 3846333210

pytorch_model-00032-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2e26602b09ec9e179a244d30c0edda94d2289bc086ad05d3aa8be785b8dbf8
+size 3846333210

pytorch_model-00033-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdce2cf88821141313e7a19b010bdd760a00228eb37053a19851dc9c4a380fa0
+size 3846333210

pytorch_model-00034-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f44d3c4d3a62d5b8113ff056f1b3085b7f731b1e38452db5fe3f49ce4acfa9c
+size 3846333210

pytorch_model-00035-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d52db37d9a87911181c1bcc4fdd4124c438fe7e188d10e8724b5d598e383bbd
+size 3846333210

pytorch_model-00036-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09ad964ee928715efd0456991c89c2b3608036abba785696ddef8121a32c74b
+size 3846333210

pytorch_model-00037-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3e5ae2bf830a5c77ae0a89a5dc0148c9601c25f7f44a356f36fffc1b9e4c19
+size 3846333210

pytorch_model-00038-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43878469fe151d44f5ed855c8f21e6fa587d61c2a1c38fce8d91d920249b307
+size 3846333210

pytorch_model-00039-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfcc6cb08a1ad868ddbbd211775c9c51fa0725644a8266be6fb333892ec71bcd
+size 3846333210

pytorch_model-00040-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3fc7b25b658a6545d6c361412f9b555135395c18b115a678418c7959f8e968
+size 3846333210

pytorch_model-00041-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e54e3cf2d5697d76405be4b0e1dc848c81b63b2cf1c060fb36dfedd78d14cc0
+size 3846316424

pytorch_model-00042-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce6c1061ab0b18a8c8eb5661ed6ef8b0e7693771e215e85f7a11465698b01f1
+size 3996393552

pytorch_model-00043-of-00046.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720628a087f8360aec910731bb23ddc03664de6664cffbb97a5d7cba8d6b5b1b
+size 3946320203