commit 0dde139d3acff7481dc3cc9273d222b9a8c0f857 Author: ModelHub XC Date: Thu Jul 9 12:38:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/WR30a-Deep-7B-0711 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a610f62 --- /dev/null +++ b/README.md @@ -0,0 +1,129 @@ +--- +license: apache-2.0 +language: +- en +- zh +pipeline_tag: image-text-to-text +library_name: transformers +tags: +- trl +- text-generation-inference +- image-captioning +- optical-character-recognition +- intelligent-character-recognition +- caption +- ocr +- visual-understanding +- art +- icr +- image-to-text +- vlm +- math +- stem +base_model: +- prithivMLmods/VIREX-062225-exp +--- + +![1](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/WjTcq6bA8tjqCTnytgXVM.png) + +# **WR30a-Deep-7B-0711** + +> The **WR30a-Deep-7B-0711** model is a fine-tuned version of **Qwen2.5-VL-7B-Instruct**, optimized for **Image Captioning**, **Visual Analysis**, and **Image Reasoning**. Built on top of the Qwen2.5-VL architecture, this experimental model enhances visual comprehension capabilities with focused training on 1,500K image pairs for superior image understanding and reasoning tasks across all categories of images with variational dimensions. + +# Key Enhancements + +* **Superior Image Captioning**: Advanced capability for generating detailed, contextually accurate captions for diverse image types and content. + +* **Enhanced Visual Analysis**: Designed to efficiently analyze and interpret complex visual information across different image categories and formats. + +* **Advanced Image Reasoning**: Optimized for logical reasoning about visual content, understanding relationships, and making inferences from images. + +* **Multi-Category Image Support**: Specialized in handling all categories of images with variational dimensions, from simple objects to complex scenes. + +* **State-of-the-Art Performance**: Achieves competitive results on visual understanding benchmarks and real-world image analysis tasks. + +* **Dimensional Flexibility**: Supports images of various resolutions and aspect ratios for comprehensive visual processing. + +* **Cross-Domain Visual Understanding**: Enables robust performance across different visual domains and content types. + +# Quick Start with Transformers + +```python +from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor +from qwen_vl_utils import process_vision_info + +model = Qwen2_5_VLForConditionalGeneration.from_pretrained( + "prithivMLmods/WR30a-Deep-7B-0711", torch_dtype="auto", device_map="auto" +) + +processor = AutoProcessor.from_pretrained("prithivMLmods/WR30a-Deep-7B-0711") + +messages = [ + { + "role": "user", + "content": [ + { + "type": "image", + "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", + }, + {"type": "text", "text": "Describe this image in detail."}, + ], + } +] + +text = processor.apply_chat_template( + messages, tokenize=False, add_generation_prompt=True +) +image_inputs, video_inputs = process_vision_info(messages) +inputs = processor( + text=[text], + images=image_inputs, + videos=video_inputs, + padding=True, + return_tensors="pt", +) +inputs = inputs.to("cuda") + +generated_ids = model.generate(**inputs, max_new_tokens=128) +generated_ids_trimmed = [ + out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) +] +output_text = processor.batch_decode( + generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False +) +print(output_text) +``` + +# Intended Use + +This model is intended for: + +* High-quality image captioning across diverse visual content and categories. +* Comprehensive visual analysis and interpretation of complex imagery. +* Advanced image reasoning for educational, research, and commercial applications. +* Multi-dimensional image understanding regardless of resolution or aspect ratio. +* Visual question answering and image-based dialogue systems. +* Content moderation and automated image classification tasks. +* Creative applications requiring detailed visual understanding. +* Accessibility tools for image description and visual assistance. + +## Training Details + +| Parameter | Value | +|-------------------------|-----------------------------------------------------| +| **Dataset Size** | 1,500K image pairs | +| **Model Architecture** | `Qwen2_5_VLForConditionalGeneration` | +| **Total Disk Volume** | 400,000 MB | +| **Training Time** | approx. 9,612 seconds (~2.67 hours) | +| **Model Stage** | Experimental | +| **Hardware** | 2 × NVIDIA A40 (19 vCPUs) | +| **Precision** | bfloat16 | + +# Limitations + +* May show degraded performance on extremely low-quality or heavily corrupted images. +* Not optimized for real-time applications on low-resource or edge devices due to computational demands. +* Variable accuracy on highly specialized or domain-specific visual content. +* Performance may vary with unusual image compositions or artistic styles. +* Being in experimental stage, outputs should be validated for critical applications. +* May require fine-tuning for specific niche use cases or domains. \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..6c22663 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system +You are a helpful assistant.<|im_end|> +{% endif %}<|im_start|>{{ message['role'] }} +{% if message['content'] is string %}{{ message['content'] }}<|im_end|> +{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|> +{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant +{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3b5da20 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e22efa693673247c062603da4d2ee157fb89e4be4f5cbeab0c5f68fa0f798d2c +size 3245 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..4aef15d --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6b4420a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_length": 128000, + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 1e-06, + "transformers_version": "4.53.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..f49c0d1 --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dec2a6a42aa95ae6cbddb674fc00d106ab42d51419c53730f7670cea1b4d4dc +size 3900233256 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..2bce904 --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4973bfc67dc7021722ef95977ee22ccad792574a443e91906639d421f3e0ba14 +size 3864726320 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..c019d36 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ec917a78f0955ebe8a40e5d173b058932e7e4c11ab5754c5defd96f8b8eb9f +size 3864726424 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..eb87344 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf16eaa18d8aace0fc09de8202c246d066ccc5ff6ad8852b37b819fee22c597 +size 3864733680 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..cf27374 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c859795ad3a627a9b95bcb762e059d5b768a4a36fdd4affeff269d93fdecc67 +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..c505b4d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b333b0b16e5286ddba615d2caebcd495cf7e616f52eb217a81781393d79de9 +size 57619 diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..ee08cdd --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,29 @@ +{ + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "max_pixels": 12845056, + "merge_size": 2, + "min_pixels": 3136, + "patch_size": 14, + "processor_class": "Qwen2_5_VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "temporal_patch_size": 2 +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..a8c78a0 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04081d680d5bb294b2e57aea5b3aa1256d9e06263e907917fc241c5adc2fbe4 +size 11422163 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..4610ab0 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ab9b3df99c783a264eb7fd9847d17f2db28d9cc2f64b37e8bf4d60c81c8761 +size 4757 diff --git a/video_preprocessor_config.json b/video_preprocessor_config.json new file mode 100644 index 0000000..6662e15 --- /dev/null +++ b/video_preprocessor_config.json @@ -0,0 +1,43 @@ +{ + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": false, + "fps": null, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "input_data_format": null, + "max_frames": 768, + "max_pixels": 12845056, + "merge_size": 2, + "min_frames": 4, + "min_pixels": 3136, + "num_frames": null, + "patch_size": 14, + "processor_class": "Qwen2_5_VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "size_divisor": null, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen2VLVideoProcessor" +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833