thanks to Lin-Chen ❤

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+license: apache-2.0
+inference: false
+---
+
+<br>
+<br>
+
+# ShareGPT4V Model Card
+
+## Model details
+
+**Model type:**
+This is the vision tower of ShareGPT4V-7B fine-tuned with our [ShareGPT4V dataset](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V).
+
+**Model date:**
+This vision tower was trained in Nov 2023.
+
+**Paper or resources for more information:**
+[[Project](https://ShareGPT4V.github.io/)] [[Paper](https://huggingface.co/papers/2311.12793)] [[Code](https://github.com/InternLM/InternLM-XComposer/tree/main/projects/ShareGPT4V)]
+
+## License
+Llama 2 is licensed under the LLAMA 2 Community License, 
+Copyright (c) Meta Platforms, Inc. All Rights Reserved.
+
+## Intended use
+**Primary intended uses:**
+The primary use of this vision tower is research on large multimodal models and chatbots.
+
+**Primary intended users:**
+The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
+
+## Training dataset
+- 1.2M high-quality image-text pairs

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "ShareGPT4V-7B_Pretrained_vit-large336-l12",
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 336,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 14,
+  "projection_dim": 768,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0"
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a8a6740e800e3583e7ff04cceeb0a1a601fa3194d98e652e190922d4b8e309
+size 607160538