Upload folder using huggingface_hub

.gitattributes

@@ -32,4 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz 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
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
+base_model:
+  - lmsys/vicuna-7b-v1.5
+base_model_relation: merge
+tags:
+  - llava
+  - vision
+  - ocr
+  - custom_code
+---
+
+This repository contains the PIIP-LLaVA_ConvNeXt-B_CLIP-L_1024-336_7B model, based on vicuna-7b-v1.5.
+
+Please refer to our [**paper**](https://huggingface.co/papers/2501.07783) and [**GitHub repository**](https://github.com/OpenGVLab/PIIP/tree/main/llava) for introduction and usage.
+
+
+
+## Citation
+
+If you find this project useful in your research, please consider citing:
+
+```BibTeX
+@article{piip,
+  title={Parameter-Inverted Image Pyramid Networks},
+  author={Zhu, Xizhou and Yang, Xue and Wang, Zhaokai and Li, Hao and Dou, Wenhan and Ge, Junqi and Lu, Lewei and Qiao, Yu and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2406.04330},
+  year={2024}
+}
+
+@article{piip_v2,
+  title={Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding},
+  author={Wang, Zhaokai and Zhu, Xizhou and Yang, Xue and Luo, Gen and Li, Hao and Tian, Changyao and Dou, Wenhan and Ge, Junqi and Lu, Lewei and Qiao, Yu and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2501.07783},
+  year={2025}
+}
+```
+

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "PIIP-LLaVA_ConvNeXt-B_CLIP-L_1024-336_7B",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_feature_multiply": 1.0,
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "configs/piip-llava_convnext-b_clip-l_1024-336_7B.py",
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_vision_tower": true,
+  "tune_vit_pos_embedding": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vision_tower_name": "configs/piip-llava_convnext-b_clip-l_1024-336_7B.py",
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0ace3335a90b4c873a49770a489b8d62c59d29c963032a49ea7f10116c8a71
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b925603156c8cc30a3f0be185d4bd422bffa12f1b5e14a042eefd2f61f9cb1
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90b5cb5faf6ed2dc163e9a0feab293d76b409df0bb68e05cc99de31b6fab9cb
+size 4537322856

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f38f0ccb14a790e00de0e4a312257b5074b9f4c83325dec7fe1e9d43f7ad6f
+size 6331