Upload folder using huggingface_hub

checkpoints/DrvtFTPP_G_projectors/A/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cdd907f3f521c1c67d5bc159ff8c1cf52302d8650061103982fd3a2e53867e0
+size 10545547

checkpoints/DrvtFTPP_G_projectors/AT/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337f7af1ac4d3614875186a0f37d4e750a45b26d4339deac7b134479f880bcca
+size 10545547

checkpoints/DrvtFTPP_G_projectors/AV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b68c599e0f294c0c18887ba07ec6b5e0e5b8bc267ab63478bc85f77aeda7cf
+size 10545547

checkpoints/DrvtFTPP_G_projectors/T/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1245490845c3791afa5fb4a1e94f0552930fc62bb1ec8c029bef3d188eba3800
+size 10545547

checkpoints/DrvtFTPP_G_projectors/TV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07804fc20484736479a6dff15f56b7ac7aa4dd4390db8791ba382ccba53541cb
+size 10545547

checkpoints/DrvtFTPP_G_projectors/V/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abc3db3f0e140926ea8cc191133649cf1bf80a13af8056c67a17783658a76e9
+size 10545547

checkpoints/DrvtFTPP_G_projectors/mix/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88abd54902a0ea226ea9a40dd6f48e0d8fac9d8c5fe5f0803280f0e950193c4d
+size 10545547

checkpoints/DrvtFTPP_M_projectors/A/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cad30b7e2e96c8faeaf5b7444f58554d29103562b1457ccc8fe17e4044c4514
+size 10545547

checkpoints/DrvtFTPP_M_projectors/AT/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9083b09b55752511aa063ae8ca65f7cf4c229ad6cec128c88b48d41aa9afaaa9
+size 10545547

checkpoints/DrvtFTPP_M_projectors/AV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c11d366946d3910ecfe82544479018f03021a11706247e9a1f2eb29feddb656
+size 10545547

checkpoints/DrvtFTPP_M_projectors/T/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351510cf2ab34afef47c520a7b333c523dae419902c135f703f4d3d7bf65c580
+size 10545547

checkpoints/DrvtFTPP_M_projectors/TV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353282f8329555203cffd6609c7a525ecd4ab05fd304ace739a13ede3ffeea8d
+size 10545547

checkpoints/DrvtFTPP_M_projectors/V/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3edbbcbfedff32adaf7780437b994a40a0cba8790364b3236923f4b046cfee5d
+size 10545547

checkpoints/DrvtFTPP_M_projectors/mix/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06dfc8d6f8213cb88c2893da3b0eb7692ab519b10a19c712fb4f8f2600ab3aa9
+size 10545547

checkpoints/DrvtFT_audio_with_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92eed730638818bc3a30303890157c4261c34b55ed5b7629d543744dfb0db3a3
+size 448190294

checkpoints/Drvt_projectors/A/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef16fc2c4ada977d51114bd7965e622a01a6048e84bfa8929d71fc494171f46
+size 23137715

checkpoints/Drvt_projectors/AT/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6a1a3c302cfad5eaf522789969d640890a0a8a0b66769791064c72d3ecf766
+size 23137715

checkpoints/Drvt_projectors/AV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b50cae8217774821a206fc08e323ccf6c6eb64b9dbcd9e77e4014dd6d2da4530
+size 23137715

checkpoints/Drvt_projectors/T/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01a024f4b919a665967b9e10db02765710453df297c74401243c25aacdee9c5
+size 23137715

checkpoints/Drvt_projectors/TV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42aec0545ea9e67a94449d1f1d5e378bc989a3f95f0ab506e39dfeb67c549aa4
+size 23137715

checkpoints/Drvt_projectors/V/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060286c55b887bc0906b27da771565a109de8a0c55c317389ca698c715ba594f
+size 23137715

checkpoints/Drvt_projectors/mix/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b817758bbf078bad9c0753988860e976c969c1e91516aafc015d0c66f10e8417
+size 23137715

checkpoints/Drvt_projectors_mini/A/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585a6c5093e6fe0ef79c147f741b262667623d018f9b4ac05b79b21a32ef3ef7
+size 14739851

checkpoints/Drvt_projectors_mini/AT/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e72e12d0bf3f4c54139b2d0fa463f2c8a9a19d45feb879029713a4833c7e5ce6
+size 14739851

checkpoints/Drvt_projectors_mini/AV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17122f541cacc387bd42e17d837a3cc92d1480090c73e5680482639164c401e7
+size 14739851

checkpoints/Drvt_projectors_mini/T/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc41b0abb0438b7d9f4ea310a8c1c8377025c81717bcb5282fbc907416614e8
+size 14739851

checkpoints/Drvt_projectors_mini/TV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a6333df4c641f428c37c5d8fe4518d9793988c5fddd2293e2df57d09b9de18
+size 14739851

checkpoints/Drvt_projectors_mini/V/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c7785c2f204b5245a4c59bdf7e14ba18a2126430a74da4124eea7bc76cc255
+size 14739851

checkpoints/Drvt_projectors_mini/mix/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223c95fbd7aa7b938b816fd74d15706ed315b8e538233b09facf2aa5526983fa
+size 14739851

checkpoints/IBPP_G_projectors/A/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8681003740d414c7d4296250fe5e007ad5564f7192e8c91e4e91a08267b0df8
+size 12647819

checkpoints/IBPP_G_projectors/AT/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bb18d3370f0bb4b990db334fa0ab20914ef0a1be11bf8ce0fa7e9b42f6b9c7
+size 12647819

checkpoints/IBPP_G_projectors/AV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71dc39ebdb6fc1dd7a6bc10e01d2d0f94d4202934ad293ba3d0c888a81e01c4
+size 12647819

checkpoints/IBPP_G_projectors/T/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7004adee9d2200cf8d03598b356477b85ac79afd78e5125fb21003f56c7c2f
+size 12647819

checkpoints/IBPP_G_projectors/TV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d180f7b38df7f9973e7baf06393c46c2fed23f74485a7b57ebf23f139cc406f7
+size 12647819

checkpoints/IBPP_G_projectors/V/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117ee65328706d7ab310a59a303656ff6114d23f822b97a86531b843fdf88976
+size 12647819

checkpoints/IBPP_G_projectors/mix/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf38dd5fe3e36ebfddc7f589738e6d3d4d7e983bdf7d3f2af2a7c4bbfb5edd60
+size 12647819

checkpoints/IBPP_M_projectors/A/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e262081db30edb8150051563b0e7da007a925eadb01fb94d4349572da80649
+size 12647819

checkpoints/IBPP_M_projectors/AT/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e765e8916f0ccffa9d0d0199ff4936135bd28c488e392b29237e0d6858203cca
+size 12647819

checkpoints/IBPP_M_projectors/AV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80860d133cfb7c50c2419481b8dee1d98ab28e604d56ea5d14e7dd6ec16784c
+size 12647819

checkpoints/IBPP_M_projectors/T/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2e5ee0ca99f0070ce6660c46e20829e615db8b2d3a0010ac64d1b830808951
+size 12647819

checkpoints/IBPP_M_projectors/TV/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5482c7a73ca56b9b16b746d61c03b20279cebf049a9c00403577b2ab0adebddb
+size 12647819

checkpoints/IBPP_M_projectors/V/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bb1c9bd9cc69db0447404482bba2fe7d5817db4b68cf5a5540e805563fd844
+size 12647819

checkpoints/IBPP_M_projectors/mix/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6e05d23288d534b5a8ee4eeedd27cfda6fb98cfd211848744fc38a12cb3ab4
+size 12647819

checkpoints/InternVL-14B-224px/README.md

@@ -0,0 +1,123 @@
+---
+license: mit
+datasets:
+- laion/laion2B-en
+- laion/laion-coco
+- laion/laion2B-multi
+- kakaobrain/coyo-700m
+- conceptual_captions
+- wanng/wukong100m
+---
+
+# Model Card for InternVL-14B-224px
+
+## What is InternVL?
+
+\[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\]
+
+InternVL scales up the ViT to _**6B parameters**_ and aligns it with LLM.
+
+It is _**the largest open-source vision/vision-language foundation model (14B)**_ to date, achieving _**32 state-of-the-art**_ performances on a wide range of tasks such as visual perception, cross-modal retrieval, multimodal dialogue, etc.
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/f1jTYvyxyYbHRalvgtKY2.png)
+
+
+## Model Details
+- **Model Type:** vision-language foundation model
+- **Model Stats:**
+  - Params: 14B
+  - Image size: 224 x 224
+- **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
+
+## Model Usage
+
+```python
+import torch
+from PIL import Image
+from transformers import AutoModel, CLIPImageProcessor
+from transformers import AutoTokenizer
+
+
+model = AutoModel.from_pretrained(
+    'OpenGVLab/InternVL-14B-224px',
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).cuda().eval()
+
+image_processor = CLIPImageProcessor.from_pretrained('OpenGVLab/InternVL-14B-224px')
+
+tokenizer = AutoTokenizer.from_pretrained(
+    'OpenGVLab/InternVL-14B-224px', use_fast=False, add_eos_token=True)
+tokenizer.pad_token_id = 0  # set pad_token_id to 0
+
+images = [
+    Image.open('./examples/image1.jpg').convert('RGB'),
+    Image.open('./examples/image2.jpg').convert('RGB'),
+    Image.open('./examples/image3.jpg').convert('RGB')
+]
+prefix = 'summarize:'
+texts = [
+    prefix + 'a photo of a red panda',  # English
+    prefix + '一张熊猫的照片',  # Chinese
+    prefix + '二匹の猫の写真'  # Japanese
+]
+
+pixel_values = image_processor(images=images, return_tensors='pt').pixel_values
+pixel_values = pixel_values.to(torch.bfloat16).cuda()
+input_ids = tokenizer(texts, return_tensors='pt', max_length=80,
+                      truncation=True, padding='max_length').input_ids.cuda()
+
+# InternVL-C
+logits_per_image, logits_per_text = model(
+    image=pixel_values, text=input_ids, mode='InternVL-C')
+probs = logits_per_image.softmax(dim=-1)
+# tensor([[9.9609e-01, 5.2185e-03, 6.0070e-08],
+#         [2.2949e-02, 9.7656e-01, 5.9903e-06],
+#         [3.2932e-06, 7.4863e-05, 1.0000e+00]], device='cuda:0',
+#        dtype=torch.bfloat16, grad_fn=<SoftmaxBackward0>)
+
+# InternVL-G
+logits_per_image, logits_per_text = model(
+    image=pixel_values, text=input_ids, mode='InternVL-G')
+probs = logits_per_image.softmax(dim=-1)
+# tensor([[9.9609e-01, 3.1738e-03, 3.6322e-08],
+#         [8.6060e-03, 9.9219e-01, 2.8759e-06],
+#         [1.7583e-06, 3.1233e-05, 1.0000e+00]], device='cuda:0',
+#        dtype=torch.bfloat16, grad_fn=<SoftmaxBackward0>)
+
+# please set add_eos_token to False for generation
+tokenizer.add_eos_token = False
+image = Image.open('./examples/image1.jpg').convert('RGB')
+pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
+pixel_values = pixel_values.to(torch.bfloat16).cuda()
+
+tokenized = tokenizer("English caption:", return_tensors='pt')
+pred = model.generate(
+    pixel_values=pixel_values,
+    input_ids=tokenized.input_ids.cuda(),
+    attention_mask=tokenized.attention_mask.cuda(),
+    num_beams=5,
+    min_new_tokens=8,
+)
+caption = tokenizer.decode(pred[0].cpu(), skip_special_tokens=True).strip()
+# English caption: a red panda sitting on top of a wooden platform
+```
+
+## Citation
+
+If you find this project useful in your research, please consider cite:
+
+```BibTeX
+@article{chen2023internvl,
+  title={InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks},
+  author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2312.14238},
+  year={2023}
+}
+```
+
+
+## Acknowledgement
+
+InternVL is built with reference to the code of the following projects: [OpenAI CLIP](https://github.com/openai/CLIP), [Open CLIP](https://github.com/mlfoundations/open_clip), [CLIP Benchmark](https://github.com/LAION-AI/CLIP_benchmark), [EVA](https://github.com/baaivision/EVA/tree/master), [InternImage](https://github.com/OpenGVLab/InternImage), [ViT-Adapter](https://github.com/czczup/ViT-Adapter), [MMSegmentation](https://github.com/open-mmlab/mmsegmentation), [Transformers](https://github.com/huggingface/transformers), [DINOv2](https://github.com/facebookresearch/dinov2), [BLIP-2](https://github.com/salesforce/LAVIS/tree/main/projects/blip2), [Qwen-VL](https://github.com/QwenLM/Qwen-VL/tree/master/eval_mm), and [LLaVA-1.5](https://github.com/haotian-liu/LLaVA). Thanks for their awesome work!

checkpoints/InternVL-14B-224px/__init__.py

@@ -0,0 +1,87 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2023 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+import torch
+import torch.nn as nn
+import torchvision.transforms as T
+from torchvision.transforms import InterpolationMode
+from transformers import LlamaTokenizer
+
+from .configuration_intern_vit import InternVisionConfig
+from .configuration_internvl import InternVLConfig
+from .modeling_intern_vit import InternVisionModel
+from .modeling_internvl import InternVL_C, InternVL_G, InternVLModel
+
+__all__ = ['InternVisionConfig', 'InternVisionModel', 'InternVLConfig',
+           'InternVLModel', 'InternVL_C', 'InternVL_G']
+
+
+# Prefix the text "summarize:"
+class InternVLTokenizer(nn.Module):
+    def __init__(self, model_path):
+        super(InternVLTokenizer, self).__init__()
+        self.tokenizer = LlamaTokenizer.from_pretrained(model_path)
+        self.tokenizer.pad_token = ' '  # allow padding
+        self.tokenizer.add_eos_token = True
+
+    def forward(self, text, prefix='summarize:'):
+        if type(text) == str:
+            text = prefix + text
+        elif type(text) == list:
+            text = [prefix + item for item in text]
+        text = self.tokenizer(text, return_tensors='pt', max_length=80, truncation=True, padding='max_length').input_ids
+        return text
+
+
+def build_transform(task, image_size=224, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]):
+    if task == 'retrieval':
+        transform = T.Compose([
+            T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
+            T.Resize((image_size, image_size), interpolation=InterpolationMode.BICUBIC),
+            T.ToTensor(),
+            T.Normalize(mean=mean, std=std)])
+    else:
+        transform = T.Compose([
+            T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
+            T.Resize(image_size, interpolation=InterpolationMode.BICUBIC),
+            T.CenterCrop(image_size),
+            T.ToTensor(),
+            T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
+    return transform
+
+
+def load_internvl_c_huggingface(ckpt_path, device, task):
+    model = InternVL_C.from_pretrained(ckpt_path, torch_dtype=torch.float16).to(device)
+    if model.config.use_backbone_lora:
+        model.vision_model.merge_and_unload()
+        model.vision_model = model.vision_model.model
+    if model.config.use_qllama_lora:
+        model.qllama.merge_and_unload()
+        model.qllama = model.qllama.model
+    if model.config.force_image_size is not None:
+        image_size = model.config.force_image_size
+    else:
+        image_size = model.config.vision_config.image_size
+    transform = build_transform(task, image_size)
+    tokenizer = InternVLTokenizer(ckpt_path)
+    return model, transform, tokenizer
+
+
+def load_internvl_g_huggingface(ckpt_path, device, task):
+    model = InternVL_G.from_pretrained(ckpt_path, torch_dtype=torch.float16).to(device)
+    if model.config.use_backbone_lora:
+        model.vision_model.merge_and_unload()
+        model.vision_model = model.vision_model.model
+    if model.config.use_qllama_lora:
+        model.qllama.merge_and_unload()
+        model.qllama = model.qllama.model
+    if model.config.force_image_size is not None:
+        image_size = model.config.force_image_size
+    else:
+        image_size = model.config.vision_config.image_size
+    transform = build_transform(task, image_size)
+    tokenizer = InternVLTokenizer(ckpt_path)
+    return model, transform, tokenizer

checkpoints/InternVL-14B-224px/config.json

@@ -0,0 +1,190 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "./",
+  "architectures": [
+    "InternVLModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_internvl.InternVLConfig",
+    "AutoModel": "modeling_internvl.InternVLModel"
+  },
+  "attn_pool_num_heads": 16,
+  "clip_embed_dim": 768,
+  "force_image_size": null,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "label_smoothing": 0.0,
+  "max_txt_len": 32,
+  "model_type": "internvl",
+  "num_query_token": 96,
+  "qllama_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_frequency": 2,
+    "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": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "max_sequence_length": 2048,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "num_query_token": 96,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "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": null,
+    "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": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float16",
+    "torchscript": false,
+    "transformers_version": "4.32.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "vocab_size": 49954
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_backbone_lora": 0,
+  "use_cache": false,
+  "use_decoder_only_language_model": true,
+  "use_qllama_lora": 0,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 3200,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 12800,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "intern_vit_6b",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 25,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 48,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qk_normalization": true,
+    "qkv_bias": false,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "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": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.32.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_flash_attn": true
+  }
+}

checkpoints/InternVL-14B-224px/configuration_intern_vit.py

@@ -0,0 +1,117 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2023 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+import os
+from typing import Union
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class InternVisionConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
+    instantiate a vision encoder according to the specified arguments, defining the model architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        num_channels (`int`, *optional*, defaults to 3):
+            Number of color channels in the input images (e.g., 3 for RGB).
+        patch_size (`int`, *optional*, defaults to 14):
+            The size (resolution) of each patch.
+        image_size (`int`, *optional*, defaults to 224):
+            The size (resolution) of each image.
+        qkv_bias (`bool`, *optional*, defaults to `False`):
+            Whether to add a bias to the queries and values in the self-attention layers.
+        hidden_size (`int`, *optional*, defaults to 3200):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_attention_heads (`int`, *optional*, defaults to 25):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (`int`, *optional*, defaults to 12800):
+            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        qk_normalization (`bool`, *optional*, defaults to `True`):
+            Whether to normalize the queries and keys in the self-attention layers.
+        num_hidden_layers (`int`, *optional*, defaults to 48):
+            Number of hidden layers in the Transformer encoder.
+        use_flash_attn (`bool`, *optional*, defaults to `True`):
+            Whether to use flash attention mechanism.
+        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
+        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+            The epsilon used by the layer normalization layers.
+        dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        drop_path_rate (`float`, *optional*, defaults to 0.0):
+            Dropout rate for stochastic depth.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        initializer_factor (`float`, *optional*, defaults to 0.1):
+            A factor for layer scale.
+    """
+
+    model_type = 'intern_vit_6b'
+
+    def __init__(
+            self,
+            num_channels=3,
+            patch_size=14,
+            image_size=224,
+            qkv_bias=False,
+            hidden_size=3200,
+            num_attention_heads=25,
+            intermediate_size=12800,
+            qk_normalization=True,
+            num_hidden_layers=48,
+            use_flash_attn=True,
+            hidden_act='gelu',
+            layer_norm_eps=1e-6,
+            dropout=0.0,
+            drop_path_rate=0.0,
+            attention_dropout=0.0,
+            initializer_range=0.02,
+            initializer_factor=0.1,
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.dropout = dropout
+        self.drop_path_rate = drop_path_rate
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_channels = num_channels
+        self.patch_size = patch_size
+        self.image_size = image_size
+        self.initializer_range = initializer_range
+        self.initializer_factor = initializer_factor
+        self.attention_dropout = attention_dropout
+        self.layer_norm_eps = layer_norm_eps
+        self.hidden_act = hidden_act
+        self.qkv_bias = qkv_bias
+        self.qk_normalization = qk_normalization
+        self.use_flash_attn = use_flash_attn
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
+
+        if 'vision_config' in config_dict:
+            config_dict = config_dict['vision_config']
+
+        if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
+            )
+
+        return cls.from_dict(config_dict, **kwargs)

checkpoints/InternVL-14B-224px/configuration_internvl.py

@@ -0,0 +1,108 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2023 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+import copy
+
+from transformers import LlamaConfig
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+from .configuration_intern_vit import InternVisionConfig
+
+logger = logging.get_logger(__name__)
+
+
+class InternVLConfig(PretrainedConfig):
+    r"""
+    [`InternVLConfig`] is the configuration class to store the configuration of a
+    [`InternVLModel`]. It is used to instantiate a InternVLModel according to the specified
+    arguments, defining the InternViT-6B and QLLaMA configs. Instantiating a configuration with
+    the defaults will yield a similar configuration to that of the InternVL architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        vision_config (`dict`, *optional*):
+            Dictionary of configuration options used to initialize [`InternVisionConfig`].
+        qllama_config (`dict`, *optional*):
+            Dictionary of configuration options used to initialize [`LLaMAConfig`].
+        clip_embed_dim (`int`, *optional*, defaults to 768):
+            Size of the embeddings from the CLIP model.
+        attn_pool_num_heads (`int`, *optional*, defaults to 16):
+            Number of attention heads used in the attention pooling layers.
+        num_query_token (`int`, *optional*, defaults to 96):
+            Number of query tokens used in the transformer.
+        label_smoothing (`float`, *optional*, defaults to 0.0):
+            The amount of label smoothing to apply.
+        cross_attention_frequency (`int`, *optional*, defaults to 2):
+            The frequency of cross-attention layers in the model.
+        use_backbone_lora (`int`, *optional*, defaults to 0):
+            If non-zero, indicates the use of LoRA in the backbone of the model.
+        use_qllama_lora (`int`, *optional*, defaults to 0):
+            If non-zero, indicates the use of LoRA in the QLLaMA of the model.
+        force_image_size (`int` or `None`, *optional*):
+            If not None, forces the model to use this specific image size.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        kwargs (*optional*):
+            Dictionary of additional keyword arguments.
+    """
+
+    model_type = 'internvl'
+    is_composition = True
+
+    def __init__(
+            self,
+            vision_config=None,
+            qllama_config=None,
+            clip_embed_dim=768,
+            attn_pool_num_heads=16,
+            num_query_token=96,
+            label_smoothing=0.0,
+            cross_attention_frequency=2,
+            use_backbone_lora=0,
+            use_qllama_lora=0,
+            force_image_size=None,
+            initializer_range=0.02,
+            **kwargs):
+        super().__init__(**kwargs)
+
+        if vision_config is None:
+            vision_config = {}
+            logger.info('vision_config is None. initializing the InternVisionConfig with default values.')
+
+        if qllama_config is None:
+            qllama_config = {}
+            logger.info(
+                'qllama_config is None. Initializing the InternTextConfig config with default values (`LlamaConfig`).')
+
+        self.vision_config = InternVisionConfig(**vision_config)
+        self.qllama_config = LlamaConfig(**qllama_config)
+        self.qllama_config.num_query_token = num_query_token
+        self.qllama_config.cross_attention_frequency = cross_attention_frequency
+        self.hidden_size = self.qllama_config.hidden_size
+
+        self.clip_embed_dim = clip_embed_dim
+        self.attn_pool_num_heads = attn_pool_num_heads
+        self.num_query_token = num_query_token
+        self.label_smoothing = label_smoothing
+        self.use_backbone_lora = use_backbone_lora
+        self.use_qllama_lora = use_qllama_lora
+        self.force_image_size = force_image_size
+        self.initializer_range = initializer_range
+
+    def to_dict(self):
+        """
+        Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
+
+        Returns:
+            `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
+        """
+        output = copy.deepcopy(self.__dict__)
+        output['vision_config'] = self.vision_config.to_dict()
+        output['qllama_config'] = self.qllama_config.to_dict()
+        output['model_type'] = self.__class__.model_type
+        return output

checkpoints/InternVL-14B-224px/flash_attention.py

@@ -0,0 +1,76 @@
+# https://github.com/Dao-AILab/flash-attention/blob/v0.2.8/flash_attn/flash_attention.py
+import torch
+import torch.nn as nn
+from einops import rearrange
+
+try:  # v1
+    from flash_attn.flash_attn_interface import \
+        flash_attn_unpadded_qkvpacked_func
+except:  # v2
+    from flash_attn.flash_attn_interface import flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func
+
+from flash_attn.bert_padding import pad_input, unpad_input
+
+
+class FlashAttention(nn.Module):
+    """Implement the scaled dot product attention with softmax.
+    Arguments
+    ---------
+        softmax_scale: The temperature to use for the softmax attention.
+                      (default: 1/sqrt(d_keys) where d_keys is computed at
+                      runtime)
+        attention_dropout: The dropout rate to apply to the attention
+                           (default: 0.0)
+    """
+
+    def __init__(self, softmax_scale=None, attention_dropout=0.0, device=None, dtype=None):
+        super().__init__()
+        self.softmax_scale = softmax_scale
+        self.dropout_p = attention_dropout
+
+    def forward(self, qkv, key_padding_mask=None, causal=False, cu_seqlens=None,
+                max_s=None, need_weights=False):
+        """Implements the multihead softmax attention.
+        Arguments
+        ---------
+            qkv: The tensor containing the query, key, and value. (B, S, 3, H, D) if key_padding_mask is None
+                if unpadded: (nnz, 3, h, d)
+            key_padding_mask: a bool tensor of shape (B, S)
+        """
+        assert not need_weights
+        assert qkv.dtype in [torch.float16, torch.bfloat16]
+        assert qkv.is_cuda
+
+        if cu_seqlens is None:
+            batch_size = qkv.shape[0]
+            seqlen = qkv.shape[1]
+            if key_padding_mask is None:
+                qkv = rearrange(qkv, 'b s ... -> (b s) ...')
+                max_s = seqlen
+                cu_seqlens = torch.arange(0, (batch_size + 1) * seqlen, step=seqlen, dtype=torch.int32,
+                                          device=qkv.device)
+                output = flash_attn_unpadded_qkvpacked_func(
+                    qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                    softmax_scale=self.softmax_scale, causal=causal
+                )
+                output = rearrange(output, '(b s) ... -> b s ...', b=batch_size)
+            else:
+                nheads = qkv.shape[-2]
+                x = rearrange(qkv, 'b s three h d -> b s (three h d)')
+                x_unpad, indices, cu_seqlens, max_s = unpad_input(x, key_padding_mask)
+                x_unpad = rearrange(x_unpad, 'nnz (three h d) -> nnz three h d', three=3, h=nheads)
+                output_unpad = flash_attn_unpadded_qkvpacked_func(
+                    x_unpad, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                    softmax_scale=self.softmax_scale, causal=causal
+                )
+                output = rearrange(pad_input(rearrange(output_unpad, 'nnz h d -> nnz (h d)'),
+                                             indices, batch_size, seqlen),
+                                   'b s (h d) -> b s h d', h=nheads)
+        else:
+            assert max_s is not None
+            output = flash_attn_unpadded_qkvpacked_func(
+                qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                softmax_scale=self.softmax_scale, causal=causal
+            )
+
+        return output, None

checkpoints/InternVL-14B-224px/modeling_intern_vit.py

@@ -0,0 +1,342 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2023 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+from typing import Optional, Tuple, Union
+
+import torch
+import torch.nn.functional as F
+import torch.utils.checkpoint
+from einops import rearrange
+from timm.models.layers import DropPath
+from torch import nn
+from transformers.activations import ACT2FN
+from transformers.modeling_outputs import (BaseModelOutput,
+                                           BaseModelOutputWithPooling)
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import logging
+
+from .configuration_intern_vit import InternVisionConfig
+
+try:
+    from .flash_attention import FlashAttention
+    has_flash_attn = True
+except:
+    print('FlashAttention is not installed.')
+    has_flash_attn = False
+
+
+logger = logging.get_logger(__name__)
+
+
+class InternRMSNorm(nn.Module):
+    def __init__(self, hidden_size, eps=1e-6):
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.variance_epsilon = eps
+
+    def forward(self, hidden_states):
+        input_dtype = hidden_states.dtype
+        hidden_states = hidden_states.to(torch.float32)
+        variance = hidden_states.pow(2).mean(-1, keepdim=True)
+        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
+        return self.weight * hidden_states.to(input_dtype)
+
+
+try:
+    from apex.normalization import FusedRMSNorm
+
+    InternRMSNorm = FusedRMSNorm  # noqa
+
+    logger.info('Discovered apex.normalization.FusedRMSNorm - will use it instead of InternRMSNorm')
+except ImportError:
+    # using the normal InternRMSNorm
+    pass
+except Exception:
+    logger.warning('discovered apex but it failed to load, falling back to InternRMSNorm')
+    pass
+
+
+class InternVisionEmbeddings(nn.Module):
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        self.embed_dim = config.hidden_size
+        self.image_size = config.image_size
+        self.patch_size = config.patch_size
+
+        self.class_embedding = nn.Parameter(
+            torch.randn(1, 1, self.embed_dim),
+        )
+
+        self.patch_embedding = nn.Conv2d(
+            in_channels=3, out_channels=self.embed_dim, kernel_size=self.patch_size, stride=self.patch_size
+        )
+
+        self.num_patches = (self.image_size // self.patch_size) ** 2
+        self.num_positions = self.num_patches + 1
+
+        self.position_embedding = nn.Parameter(torch.randn(1, self.num_positions, self.embed_dim))
+
+    def forward(self, pixel_values: torch.FloatTensor) -> torch.Tensor:
+        batch_size = pixel_values.shape[0]
+        target_dtype = self.patch_embedding.weight.dtype
+        patch_embeds = self.patch_embedding(pixel_values)  # shape = [*, width, grid, grid]
+        patch_embeds = patch_embeds.flatten(2).transpose(1, 2)
+        class_embeds = self.class_embedding.expand(batch_size, 1, -1).to(target_dtype)
+        embeddings = torch.cat([class_embeds, patch_embeds], dim=1)
+        embeddings = embeddings + self.position_embedding.to(target_dtype)
+        return embeddings
+
+
+class InternAttention(nn.Module):
+    """Multi-headed attention from 'Attention Is All You Need' paper"""
+
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        self.embed_dim = config.hidden_size
+        self.num_heads = config.num_attention_heads
+        self.use_flash_attn = config.use_flash_attn and has_flash_attn
+        if config.use_flash_attn and not has_flash_attn:
+            print('Warning: Flash Attention is not available, use_flash_attn is set to False.')
+        self.head_dim = self.embed_dim // self.num_heads
+        if self.head_dim * self.num_heads != self.embed_dim:
+            raise ValueError(
+                f'embed_dim must be divisible by num_heads (got `embed_dim`: {self.embed_dim} and `num_heads`:'
+                f' {self.num_heads}).'
+            )
+
+        self.scale = self.head_dim ** -0.5
+        self.qkv = nn.Linear(self.embed_dim, 3 * self.embed_dim, bias=config.qkv_bias)
+        self.attn_drop = nn.Dropout(config.attention_dropout)
+        self.proj_drop = nn.Dropout(config.dropout)
+
+        self.qk_normalization = config.qk_normalization
+
+        if self.qk_normalization:
+            self.q_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+            self.k_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+
+        if self.use_flash_attn:
+            self.inner_attn = FlashAttention(attention_dropout=config.attention_dropout)
+        self.proj = nn.Linear(self.embed_dim, self.embed_dim)
+
+    def _naive_attn(self, x):
+        B, N, C = x.shape
+        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv.unbind(0)  # make torchscript happy (cannot use tensor as tuple)
+
+        if self.qk_normalization:
+            B_, H_, N_, D_ = q.shape
+            q = self.q_norm(q.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
+            k = self.k_norm(k.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
+
+        attn = ((q * self.scale) @ k.transpose(-2, -1))
+        attn = attn.softmax(dim=-1)
+        attn = self.attn_drop(attn)
+
+        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+    def _flash_attn(self, x, key_padding_mask=None, need_weights=False):
+        qkv = self.qkv(x)
+        qkv = rearrange(qkv, 'b s (three h d) -> b s three h d', three=3, h=self.num_heads)
+
+        if self.qk_normalization:
+            q, k, v = qkv.unbind(2)
+            q = self.q_norm(q.flatten(-2, -1)).view(q.shape)
+            k = self.k_norm(k.flatten(-2, -1)).view(k.shape)
+            qkv = torch.stack([q, k, v], dim=2)
+
+        context, _ = self.inner_attn(
+            qkv, key_padding_mask=key_padding_mask, need_weights=need_weights, causal=False
+        )
+        outs = self.proj(rearrange(context, 'b s h d -> b s (h d)'))
+        outs = self.proj_drop(outs)
+        return outs
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        x = self._naive_attn(hidden_states) if not self.use_flash_attn else self._flash_attn(hidden_states)
+        return x
+
+
+class InternMLP(nn.Module):
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        self.act = ACT2FN[config.hidden_act]
+        self.fc1 = nn.Linear(config.hidden_size, config.intermediate_size)
+        self.fc2 = nn.Linear(config.intermediate_size, config.hidden_size)
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        hidden_states = self.fc1(hidden_states)
+        hidden_states = self.act(hidden_states)
+        hidden_states = self.fc2(hidden_states)
+        return hidden_states
+
+
+class InternVisionEncoderLayer(nn.Module):
+    def __init__(self, config: InternVisionConfig, drop_path_rate: float):
+        super().__init__()
+        self.embed_dim = config.hidden_size
+        self.intermediate_size = config.intermediate_size
+
+        self.attn = InternAttention(config)
+        self.mlp = InternMLP(config)
+        self.norm1 = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+        self.norm2 = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+
+        self.ls1 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))
+        self.ls2 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))
+        self.drop_path1 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
+        self.drop_path2 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
+
+    def forward(
+            self,
+            hidden_states: torch.Tensor,
+    ) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor], Optional[Tuple[torch.FloatTensor]]]:
+        """
+        Args:
+            hidden_states (`Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]`): input to the layer of shape `(batch, seq_len, embed_dim)`
+        """
+        hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states)) * self.ls1)
+
+        hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states)) * self.ls2)
+
+        return hidden_states
+
+
+class InternVisionEncoder(nn.Module):
+    """
+    Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a
+    [`InternEncoderLayer`].
+
+    Args:
+        config (`InternConfig`):
+            The corresponding vision configuration for the `InternEncoder`.
+    """
+
+    def __init__(self, config: InternVisionConfig):
+        super().__init__()
+        self.config = config
+        # stochastic depth decay rule
+        dpr = [x.item() for x in torch.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
+        self.layers = nn.ModuleList([
+            InternVisionEncoderLayer(config, dpr[idx]) for idx in range(config.num_hidden_layers)])
+        self.gradient_checkpointing = True
+
+    def forward(
+            self,
+            inputs_embeds,
+            output_hidden_states: Optional[bool] = None,
+            return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutput]:
+        r"""
+        Args:
+            inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
+                Embedded representation of the inputs. Should be float, not int tokens.
+            output_hidden_states (`bool`, *optional*):
+                Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
+                for more detail.
+            return_dict (`bool`, *optional*):
+                Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
+        """
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        encoder_states = () if output_hidden_states else None
+        hidden_states = inputs_embeds
+
+        for idx, encoder_layer in enumerate(self.layers):
+            if output_hidden_states:
+                encoder_states = encoder_states + (hidden_states,)
+            if self.gradient_checkpointing and self.training:
+                layer_outputs = torch.utils.checkpoint.checkpoint(
+                    encoder_layer,
+                    hidden_states)
+            else:
+                layer_outputs = encoder_layer(
+                    hidden_states,
+                )
+            hidden_states = layer_outputs
+
+        if output_hidden_states:
+            encoder_states = encoder_states + (hidden_states,)
+
+        if not return_dict:
+            return tuple(v for v in [hidden_states, encoder_states] if v is not None)
+        return BaseModelOutput(
+            last_hidden_state=hidden_states, hidden_states=encoder_states
+        )
+
+
+class InternVisionModel(PreTrainedModel):
+    main_input_name = 'pixel_values'
+    config_class = InternVisionConfig
+
+    def __init__(self, config: InternVisionConfig):
+        super().__init__(config)
+        self.config = config
+
+        self.embeddings = InternVisionEmbeddings(config)
+        self.encoder = InternVisionEncoder(config)
+
+    def resize_pos_embeddings(self, old_size, new_size, patch_size):
+        pos_emb = self.embeddings.position_embedding
+        _, num_positions, embed_dim = pos_emb.shape
+        cls_emb = pos_emb[:, :1, :]
+        pos_emb = pos_emb[:, 1:, :].reshape(1, old_size // patch_size, old_size // patch_size, -1).permute(0, 3, 1, 2)
+        pos_emb = F.interpolate(pos_emb.float(), size=new_size // patch_size, mode='bicubic', align_corners=False)
+        pos_emb = pos_emb.to(cls_emb.dtype).reshape(1, embed_dim, -1).permute(0, 2, 1)
+        pos_emb = torch.cat([cls_emb, pos_emb], dim=1)
+        self.embeddings.position_embedding = nn.Parameter(pos_emb)
+        logger.info('Resized position embeddings from {} to {}'.format(old_size, new_size))
+
+    def get_input_embeddings(self):
+        return self.embeddings
+
+    def forward(
+            self,
+            pixel_values: Optional[torch.FloatTensor] = None,
+            output_hidden_states: Optional[bool] = None,
+            return_dict: Optional[bool] = None,
+            pixel_embeds: Optional[torch.FloatTensor] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPooling]:
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        if pixel_values is None and pixel_embeds is None:
+            raise ValueError('You have to specify pixel_values or pixel_embeds')
+
+        if pixel_embeds is not None:
+            hidden_states = pixel_embeds
+        else:
+            if len(pixel_values.shape) == 4:
+                hidden_states = self.embeddings(pixel_values)
+            else:
+                raise ValueError(f'wrong pixel_values size: {pixel_values.shape}')
+        encoder_outputs = self.encoder(
+            inputs_embeds=hidden_states,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+        last_hidden_state = encoder_outputs.last_hidden_state
+        pooled_output = last_hidden_state[:, 0, :]
+
+        if not return_dict:
+            return (last_hidden_state, pooled_output) + encoder_outputs[1:]
+
+        return BaseModelOutputWithPooling(
+            last_hidden_state=last_hidden_state,
+            pooler_output=pooled_output,
+            hidden_states=encoder_outputs.hidden_states,
+            attentions=encoder_outputs.attentions,
+        )