初始化项目，由ModelHub XC社区提供模型
Model: prithivMLmods/Hoags-2B-Exp Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -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
|
||||||
131
README.md
Normal file
131
README.md
Normal file
@@ -0,0 +1,131 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- zh
|
||||||
|
base_model:
|
||||||
|
- prithivMLmods/Qwen2-VL-OCR-2B-Instruct
|
||||||
|
pipeline_tag: image-text-to-text
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
- Qwen
|
||||||
|
- Hoags
|
||||||
|
---
|
||||||
|
|
||||||
|
|
||||||
|
> [!WARNING]
|
||||||
|
> **Note:** This model contains artifacts and may perform poorly in some cases.
|
||||||
|
|
||||||
|
# **Hoags-2B-Exp**
|
||||||
|
|
||||||
|
The **Hoags-2B-Exp** model is a fine-tuned version of Qwen2-VL-2B-Instruct, specifically designed for reasoning tasks, context reasoning, and multi-modal understanding. If you ask for an image description, it will automatically describe the image and answer the question in a conversational manner.
|
||||||
|
|
||||||
|
# **Key Enhancements**
|
||||||
|
|
||||||
|
* **Advanced Contextual Reasoning**: Hoags-2B-Exp achieves state-of-the-art performance in reasoning tasks by enhancing logical inference and decision-making.
|
||||||
|
|
||||||
|
* **Understanding images of various resolution & ratio**: The model excels at visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.
|
||||||
|
|
||||||
|
* **Long-Context Video Understanding**: Capable of processing and reasoning over videos of 20 minutes or more for high-quality video-based question answering, content creation, and dialogue.
|
||||||
|
|
||||||
|
* **Device Integration**: With strong reasoning and decision-making abilities, the model can be integrated into mobile devices, robots, and automation systems for real-time operation based on both visual and textual input.
|
||||||
|
|
||||||
|
* **Multilingual Support**: Supports text understanding in various languages within images, including English, Chinese, Japanese, Korean, Arabic, most European languages, and Vietnamese.
|
||||||
|
|
||||||
|
# **Demo Inference**
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# **How to Use**
|
||||||
|
|
||||||
|
```python
|
||||||
|
instruction = "Analyze the image and generate a clear, concise description of the scene, objects, and actions. Respond to user queries with accurate, relevant details derived from the visual content. Maintain a natural conversational flow and ensure logical consistency. Summarize or clarify as needed for understanding."
|
||||||
|
```
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
||||||
|
from qwen_vl_utils import process_vision_info
|
||||||
|
|
||||||
|
# Load the model with automatic device placement
|
||||||
|
model = Qwen2VLForConditionalGeneration.from_pretrained(
|
||||||
|
"prithivMLmods/Hoags-2B-Exp", torch_dtype="auto", device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Recommended: Enable flash_attention_2 for better performance in multi-image and video tasks
|
||||||
|
# model = Qwen2VLForConditionalGeneration.from_pretrained(
|
||||||
|
# "prithivMLmods/Hoags-2B-Exp",
|
||||||
|
# torch_dtype=torch.bfloat16,
|
||||||
|
# attn_implementation="flash_attention_2",
|
||||||
|
# device_map="auto",
|
||||||
|
# )
|
||||||
|
|
||||||
|
# Load processor
|
||||||
|
processor = AutoProcessor.from_pretrained("prithivMLmods/Hoags-2B-Exp")
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": [
|
||||||
|
{
|
||||||
|
"type": "image",
|
||||||
|
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
||||||
|
},
|
||||||
|
{"type": "text", "text": "Analyze the context of this image."},
|
||||||
|
],
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
||||||
|
# Prepare input
|
||||||
|
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")
|
||||||
|
|
||||||
|
# Inference
|
||||||
|
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)
|
||||||
|
```
|
||||||
|
|
||||||
|
# **Buffer Handling**
|
||||||
|
```python
|
||||||
|
buffer = ""
|
||||||
|
for new_text in streamer:
|
||||||
|
buffer += new_text
|
||||||
|
buffer = buffer.replace("<|im_end|>", "")
|
||||||
|
yield buffer
|
||||||
|
```
|
||||||
|
|
||||||
|
# **Key Features**
|
||||||
|
|
||||||
|
1. **Advanced Contextual Reasoning:**
|
||||||
|
- Optimized for **context-aware problem-solving** and **logical inference**.
|
||||||
|
|
||||||
|
2. **Optical Character Recognition (OCR):**
|
||||||
|
- Extracts and processes text from images with exceptional accuracy.
|
||||||
|
|
||||||
|
3. **Mathematical and Logical Problem Solving:**
|
||||||
|
- Supports complex reasoning and outputs equations in **LaTeX format**.
|
||||||
|
|
||||||
|
4. **Conversational and Multi-Turn Interaction:**
|
||||||
|
- Handles **multi-turn dialogue** with enhanced memory retention and response coherence.
|
||||||
|
|
||||||
|
5. **Multi-Modal Inputs & Outputs:**
|
||||||
|
- Processes images, text, and combined inputs to generate insightful analyses.
|
||||||
|
|
||||||
|
6. **Secure and Efficient Model Loading:**
|
||||||
|
- Uses **Safetensors** for faster and more secure model weight handling.
|
||||||
16
added_tokens.json
Normal file
16
added_tokens.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
{
|
||||||
|
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||||
|
}
|
||||||
50
config.json
Normal file
50
config.json
Normal file
@@ -0,0 +1,50 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "prithivMLmods/Hoags-2B-Exp",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"image_token_id": 151655,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2_vl",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151654,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"rope_type": "default",
|
||||||
|
"type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.49.0.dev0",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"vision_config": {
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"in_chans": 3,
|
||||||
|
"model_type": "qwen2_vl",
|
||||||
|
"spatial_patch_size": 14,
|
||||||
|
"torch_dtype": "float16"
|
||||||
|
},
|
||||||
|
"vision_end_token_id": 151653,
|
||||||
|
"vision_start_token_id": 151652,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "visual-question-answering", "allow_remote": true}
|
||||||
343
demonstration/exp.ipynb
Normal file
343
demonstration/exp.ipynb
Normal file
@@ -0,0 +1,343 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"id": "-b4-SW1aGOcF"
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"**Hoags-2B-Exp**\n",
|
||||||
|
"\n",
|
||||||
|
"Qwen2VLForConditionalGeneration"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"id": "oDmd1ZObGSel"
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"!pip install gradio spaces transformers accelerate numpy requests torch torchvision qwen-vl-utils av ipython reportlab fpdf python-docx pillow huggingface_hub"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"id": "ovBSsRFhGbs2"
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# Authenticate with Hugging Face\n",
|
||||||
|
"from huggingface_hub import login\n",
|
||||||
|
"\n",
|
||||||
|
"# Log in to Hugging Face using the provided token\n",
|
||||||
|
"hf_token = '---xxxx-xxx-xxx---'\n",
|
||||||
|
"login(hf_token)\n",
|
||||||
|
"\n",
|
||||||
|
"#Demo\n",
|
||||||
|
"import gradio as gr\n",
|
||||||
|
"import spaces\n",
|
||||||
|
"from transformers import Qwen2VLForConditionalGeneration, AutoProcessor, TextIteratorStreamer\n",
|
||||||
|
"from qwen_vl_utils import process_vision_info\n",
|
||||||
|
"import torch\n",
|
||||||
|
"from PIL import Image\n",
|
||||||
|
"import os\n",
|
||||||
|
"import uuid\n",
|
||||||
|
"import io\n",
|
||||||
|
"from threading import Thread\n",
|
||||||
|
"from reportlab.lib.pagesizes import A4\n",
|
||||||
|
"from reportlab.lib.styles import getSampleStyleSheet\n",
|
||||||
|
"from reportlab.lib import colors\n",
|
||||||
|
"from reportlab.platypus import SimpleDocTemplate, Image as RLImage, Paragraph, Spacer\n",
|
||||||
|
"from reportlab.lib.units import inch\n",
|
||||||
|
"from reportlab.pdfbase import pdfmetrics\n",
|
||||||
|
"from reportlab.pdfbase.ttfonts import TTFont\n",
|
||||||
|
"import docx\n",
|
||||||
|
"from docx.enum.text import WD_ALIGN_PARAGRAPH\n",
|
||||||
|
"\n",
|
||||||
|
"# Define model options\n",
|
||||||
|
"MODEL_OPTIONS = {\n",
|
||||||
|
" \"Hoags\": \"prithivMLmods/Hoags-2B-Exp\",\n",
|
||||||
|
"}\n",
|
||||||
|
"\n",
|
||||||
|
"# Preload models and processors into CUDA\n",
|
||||||
|
"models = {}\n",
|
||||||
|
"processors = {}\n",
|
||||||
|
"for name, model_id in MODEL_OPTIONS.items():\n",
|
||||||
|
" print(f\"Loading {name}...\")\n",
|
||||||
|
" models[name] = Qwen2VLForConditionalGeneration.from_pretrained(\n",
|
||||||
|
" model_id,\n",
|
||||||
|
" trust_remote_code=True,\n",
|
||||||
|
" torch_dtype=torch.float16\n",
|
||||||
|
" ).to(\"cuda\").eval()\n",
|
||||||
|
" processors[name] = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)\n",
|
||||||
|
"\n",
|
||||||
|
"image_extensions = Image.registered_extensions()\n",
|
||||||
|
"\n",
|
||||||
|
"def identify_and_save_blob(blob_path):\n",
|
||||||
|
" \"\"\"Identifies if the blob is an image and saves it.\"\"\"\n",
|
||||||
|
" try:\n",
|
||||||
|
" with open(blob_path, 'rb') as file:\n",
|
||||||
|
" blob_content = file.read()\n",
|
||||||
|
" try:\n",
|
||||||
|
" Image.open(io.BytesIO(blob_content)).verify() # Check if it's a valid image\n",
|
||||||
|
" extension = \".png\" # Default to PNG for saving\n",
|
||||||
|
" media_type = \"image\"\n",
|
||||||
|
" except (IOError, SyntaxError):\n",
|
||||||
|
" raise ValueError(\"Unsupported media type. Please upload a valid image.\")\n",
|
||||||
|
"\n",
|
||||||
|
" filename = f\"temp_{uuid.uuid4()}_media{extension}\"\n",
|
||||||
|
" with open(filename, \"wb\") as f:\n",
|
||||||
|
" f.write(blob_content)\n",
|
||||||
|
"\n",
|
||||||
|
" return filename, media_type\n",
|
||||||
|
"\n",
|
||||||
|
" except FileNotFoundError:\n",
|
||||||
|
" raise ValueError(f\"The file {blob_path} was not found.\")\n",
|
||||||
|
" except Exception as e:\n",
|
||||||
|
" raise ValueError(f\"An error occurred while processing the file: {e}\")\n",
|
||||||
|
"\n",
|
||||||
|
"@spaces.GPU\n",
|
||||||
|
"def qwen_inference(model_name, media_input, text_input=None):\n",
|
||||||
|
" \"\"\"Handles inference for the selected model.\"\"\"\n",
|
||||||
|
" model = models[model_name]\n",
|
||||||
|
" processor = processors[model_name]\n",
|
||||||
|
"\n",
|
||||||
|
" if isinstance(media_input, str):\n",
|
||||||
|
" media_path = media_input\n",
|
||||||
|
" if media_path.endswith(tuple([i for i in image_extensions.keys()])):\n",
|
||||||
|
" media_type = \"image\"\n",
|
||||||
|
" else:\n",
|
||||||
|
" try:\n",
|
||||||
|
" media_path, media_type = identify_and_save_blob(media_input)\n",
|
||||||
|
" except Exception as e:\n",
|
||||||
|
" raise ValueError(\"Unsupported media type. Please upload a valid image.\")\n",
|
||||||
|
"\n",
|
||||||
|
" messages = [\n",
|
||||||
|
" {\n",
|
||||||
|
" \"role\": \"user\",\n",
|
||||||
|
" \"content\": [\n",
|
||||||
|
" {\n",
|
||||||
|
" \"type\": media_type,\n",
|
||||||
|
" media_type: media_path\n",
|
||||||
|
" },\n",
|
||||||
|
" {\"type\": \"text\", \"text\": text_input},\n",
|
||||||
|
" ],\n",
|
||||||
|
" }\n",
|
||||||
|
" ]\n",
|
||||||
|
"\n",
|
||||||
|
" text = processor.apply_chat_template(\n",
|
||||||
|
" messages, tokenize=False, add_generation_prompt=True\n",
|
||||||
|
" )\n",
|
||||||
|
" image_inputs, _ = process_vision_info(messages)\n",
|
||||||
|
" inputs = processor(\n",
|
||||||
|
" text=[text],\n",
|
||||||
|
" images=image_inputs,\n",
|
||||||
|
" padding=True,\n",
|
||||||
|
" return_tensors=\"pt\",\n",
|
||||||
|
" ).to(\"cuda\")\n",
|
||||||
|
"\n",
|
||||||
|
" streamer = TextIteratorStreamer(\n",
|
||||||
|
" processor.tokenizer, skip_prompt=True, skip_special_tokens=True\n",
|
||||||
|
" )\n",
|
||||||
|
" generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)\n",
|
||||||
|
"\n",
|
||||||
|
" thread = Thread(target=model.generate, kwargs=generation_kwargs)\n",
|
||||||
|
" thread.start()\n",
|
||||||
|
"\n",
|
||||||
|
" buffer = \"\"\n",
|
||||||
|
" for new_text in streamer:\n",
|
||||||
|
" buffer += new_text\n",
|
||||||
|
" # Remove <|im_end|> or similar tokens from the output\n",
|
||||||
|
" buffer = buffer.replace(\"<|im_end|>\", \"\")\n",
|
||||||
|
" yield buffer\n",
|
||||||
|
"\n",
|
||||||
|
"def format_plain_text(output_text):\n",
|
||||||
|
" \"\"\"Formats the output text as plain text without LaTeX delimiters.\"\"\"\n",
|
||||||
|
" # Remove LaTeX delimiters and convert to plain text\n",
|
||||||
|
" plain_text = output_text.replace(\"\\\\(\", \"\").replace(\"\\\\)\", \"\").replace(\"\\\\[\", \"\").replace(\"\\\\]\", \"\")\n",
|
||||||
|
" return plain_text\n",
|
||||||
|
"\n",
|
||||||
|
"def generate_document(media_path, output_text, file_format, font_size, line_spacing, alignment, image_size):\n",
|
||||||
|
" \"\"\"Generates a document with the input image and plain text output.\"\"\"\n",
|
||||||
|
" plain_text = format_plain_text(output_text)\n",
|
||||||
|
" if file_format == \"pdf\":\n",
|
||||||
|
" return generate_pdf(media_path, plain_text, font_size, line_spacing, alignment, image_size)\n",
|
||||||
|
" elif file_format == \"docx\":\n",
|
||||||
|
" return generate_docx(media_path, plain_text, font_size, line_spacing, alignment, image_size)\n",
|
||||||
|
"\n",
|
||||||
|
"def generate_pdf(media_path, plain_text, font_size, line_spacing, alignment, image_size):\n",
|
||||||
|
" \"\"\"Generates a PDF document.\"\"\"\n",
|
||||||
|
" filename = f\"output_{uuid.uuid4()}.pdf\"\n",
|
||||||
|
" doc = SimpleDocTemplate(\n",
|
||||||
|
" filename,\n",
|
||||||
|
" pagesize=A4,\n",
|
||||||
|
" rightMargin=inch,\n",
|
||||||
|
" leftMargin=inch,\n",
|
||||||
|
" topMargin=inch,\n",
|
||||||
|
" bottomMargin=inch\n",
|
||||||
|
" )\n",
|
||||||
|
" styles = getSampleStyleSheet()\n",
|
||||||
|
" styles[\"Normal\"].fontSize = int(font_size)\n",
|
||||||
|
" styles[\"Normal\"].leading = int(font_size) * line_spacing\n",
|
||||||
|
" styles[\"Normal\"].alignment = {\n",
|
||||||
|
" \"Left\": 0,\n",
|
||||||
|
" \"Center\": 1,\n",
|
||||||
|
" \"Right\": 2,\n",
|
||||||
|
" \"Justified\": 4\n",
|
||||||
|
" }[alignment]\n",
|
||||||
|
"\n",
|
||||||
|
" story = []\n",
|
||||||
|
"\n",
|
||||||
|
" # Add image with size adjustment\n",
|
||||||
|
" image_sizes = {\n",
|
||||||
|
" \"Small\": (200, 200),\n",
|
||||||
|
" \"Medium\": (400, 400),\n",
|
||||||
|
" \"Large\": (600, 600)\n",
|
||||||
|
" }\n",
|
||||||
|
" img = RLImage(media_path, width=image_sizes[image_size][0], height=image_sizes[image_size][1])\n",
|
||||||
|
" story.append(img)\n",
|
||||||
|
" story.append(Spacer(1, 12))\n",
|
||||||
|
"\n",
|
||||||
|
" # Add plain text output\n",
|
||||||
|
" text = Paragraph(plain_text, styles[\"Normal\"])\n",
|
||||||
|
" story.append(text)\n",
|
||||||
|
"\n",
|
||||||
|
" doc.build(story)\n",
|
||||||
|
" return filename\n",
|
||||||
|
"\n",
|
||||||
|
"def generate_docx(media_path, plain_text, font_size, line_spacing, alignment, image_size):\n",
|
||||||
|
" \"\"\"Generates a DOCX document.\"\"\"\n",
|
||||||
|
" filename = f\"output_{uuid.uuid4()}.docx\"\n",
|
||||||
|
" doc = docx.Document()\n",
|
||||||
|
"\n",
|
||||||
|
" # Add image with size adjustment\n",
|
||||||
|
" image_sizes = {\n",
|
||||||
|
" \"Small\": docx.shared.Inches(2),\n",
|
||||||
|
" \"Medium\": docx.shared.Inches(4),\n",
|
||||||
|
" \"Large\": docx.shared.Inches(6)\n",
|
||||||
|
" }\n",
|
||||||
|
" doc.add_picture(media_path, width=image_sizes[image_size])\n",
|
||||||
|
" doc.add_paragraph()\n",
|
||||||
|
"\n",
|
||||||
|
" # Add plain text output\n",
|
||||||
|
" paragraph = doc.add_paragraph()\n",
|
||||||
|
" paragraph.paragraph_format.line_spacing = line_spacing\n",
|
||||||
|
" paragraph.paragraph_format.alignment = {\n",
|
||||||
|
" \"Left\": WD_ALIGN_PARAGRAPH.LEFT,\n",
|
||||||
|
" \"Center\": WD_ALIGN_PARAGRAPH.CENTER,\n",
|
||||||
|
" \"Right\": WD_ALIGN_PARAGRAPH.RIGHT,\n",
|
||||||
|
" \"Justified\": WD_ALIGN_PARAGRAPH.JUSTIFY\n",
|
||||||
|
" }[alignment]\n",
|
||||||
|
" run = paragraph.add_run(plain_text)\n",
|
||||||
|
" run.font.size = docx.shared.Pt(int(font_size))\n",
|
||||||
|
"\n",
|
||||||
|
" doc.save(filename)\n",
|
||||||
|
" return filename\n",
|
||||||
|
"\n",
|
||||||
|
"# CSS for output styling\n",
|
||||||
|
"css = \"\"\"\n",
|
||||||
|
" #output {\n",
|
||||||
|
" height: 500px;\n",
|
||||||
|
" overflow: auto;\n",
|
||||||
|
" border: 1px solid #ccc;\n",
|
||||||
|
" }\n",
|
||||||
|
".submit-btn {\n",
|
||||||
|
" background-color: #cf3434 !important;\n",
|
||||||
|
" color: white !important;\n",
|
||||||
|
"}\n",
|
||||||
|
".submit-btn:hover {\n",
|
||||||
|
" background-color: #ff2323 !important;\n",
|
||||||
|
"}\n",
|
||||||
|
".download-btn {\n",
|
||||||
|
" background-color: #35a6d6 !important;\n",
|
||||||
|
" color: white !important;\n",
|
||||||
|
"}\n",
|
||||||
|
".download-btn:hover {\n",
|
||||||
|
" background-color: #22bcff !important;\n",
|
||||||
|
"}\n",
|
||||||
|
"\"\"\"\n",
|
||||||
|
"\n",
|
||||||
|
"# Gradio app setup\n",
|
||||||
|
"with gr.Blocks(css=css) as demo:\n",
|
||||||
|
" gr.Markdown(\"# Hoags-2B-Exp\")\n",
|
||||||
|
"\n",
|
||||||
|
" with gr.Tab(label=\"Image Input\"):\n",
|
||||||
|
"\n",
|
||||||
|
" with gr.Row():\n",
|
||||||
|
" with gr.Column():\n",
|
||||||
|
" model_choice = gr.Dropdown(\n",
|
||||||
|
" label=\"Model Selection\",\n",
|
||||||
|
" choices=list(MODEL_OPTIONS.keys()),\n",
|
||||||
|
" value=\"Hoags\"\n",
|
||||||
|
" )\n",
|
||||||
|
" input_media = gr.File(\n",
|
||||||
|
" label=\"Upload Image\", type=\"filepath\"\n",
|
||||||
|
" )\n",
|
||||||
|
" text_input = gr.Textbox(label=\"Question\", placeholder=\"Ask a question about the image...\")\n",
|
||||||
|
" submit_btn = gr.Button(value=\"Submit\", elem_classes=\"submit-btn\")\n",
|
||||||
|
"\n",
|
||||||
|
" with gr.Column():\n",
|
||||||
|
" output_text = gr.Textbox(label=\"Output Text\", lines=10)\n",
|
||||||
|
" plain_text_output = gr.Textbox(label=\"Standardized Plain Text\", lines=10)\n",
|
||||||
|
"\n",
|
||||||
|
" submit_btn.click(\n",
|
||||||
|
" qwen_inference, [model_choice, input_media, text_input], [output_text]\n",
|
||||||
|
" ).then(\n",
|
||||||
|
" lambda output_text: format_plain_text(output_text), [output_text], [plain_text_output]\n",
|
||||||
|
" )\n",
|
||||||
|
"\n",
|
||||||
|
" # Add examples directly usable by clicking\n",
|
||||||
|
" with gr.Row():\n",
|
||||||
|
" with gr.Column():\n",
|
||||||
|
" line_spacing = gr.Dropdown(\n",
|
||||||
|
" choices=[0.5, 1.0, 1.15, 1.5, 2.0, 2.5, 3.0],\n",
|
||||||
|
" value=1.5,\n",
|
||||||
|
" label=\"Line Spacing\"\n",
|
||||||
|
" )\n",
|
||||||
|
" font_size = gr.Dropdown(\n",
|
||||||
|
" choices=[\"8\", \"10\", \"12\", \"14\", \"16\", \"18\", \"20\", \"22\", \"24\"],\n",
|
||||||
|
" value=\"18\",\n",
|
||||||
|
" label=\"Font Size\"\n",
|
||||||
|
" )\n",
|
||||||
|
" alignment = gr.Dropdown(\n",
|
||||||
|
" choices=[\"Left\", \"Center\", \"Right\", \"Justified\"],\n",
|
||||||
|
" value=\"Justified\",\n",
|
||||||
|
" label=\"Text Alignment\"\n",
|
||||||
|
" )\n",
|
||||||
|
" image_size = gr.Dropdown(\n",
|
||||||
|
" choices=[\"Small\", \"Medium\", \"Large\"],\n",
|
||||||
|
" value=\"Small\",\n",
|
||||||
|
" label=\"Image Size\"\n",
|
||||||
|
" )\n",
|
||||||
|
" file_format = gr.Radio([\"pdf\", \"docx\"], label=\"File Format\", value=\"pdf\")\n",
|
||||||
|
" get_document_btn = gr.Button(value=\"Get Document\", elem_classes=\"download-btn\")\n",
|
||||||
|
"\n",
|
||||||
|
" get_document_btn.click(\n",
|
||||||
|
" generate_document, [input_media, output_text, file_format, font_size, line_spacing, alignment, image_size], gr.File(label=\"Download Document\")\n",
|
||||||
|
" )\n",
|
||||||
|
"\n",
|
||||||
|
"demo.launch(debug=True)"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"accelerator": "GPU",
|
||||||
|
"colab": {
|
||||||
|
"gpuType": "T4",
|
||||||
|
"provenance": []
|
||||||
|
},
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"name": "python"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 0
|
||||||
|
}
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"max_length": 32768,
|
||||||
|
"pad_token_id": 151654,
|
||||||
|
"temperature": 0.01,
|
||||||
|
"top_k": 1,
|
||||||
|
"top_p": 0.001,
|
||||||
|
"transformers_version": "4.49.0.dev0"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:feecafa106f20ec6d3f182b6f292f32b8b94c76dccf267ab1d38e721beb56619
|
||||||
|
size 4418049776
|
||||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -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": "Qwen2VLProcessor",
|
||||||
|
"resample": 3,
|
||||||
|
"rescale_factor": 0.00392156862745098,
|
||||||
|
"size": {
|
||||||
|
"longest_edge": 12845056,
|
||||||
|
"shortest_edge": 3136
|
||||||
|
},
|
||||||
|
"temporal_patch_size": 2
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -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": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:948c45c29a91dd2e6ae77d6f5a324a3d408bcca6ad443365b2e79986f1422771
|
||||||
|
size 11420540
|
||||||
145
tokenizer_config.json
Normal file
145
tokenizer_config.json
Normal file
@@ -0,0 +1,145 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"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|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 32768,
|
||||||
|
"pad_token": "<|vision_pad|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"processor_class": "Qwen2VLProcessor",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user