prithivMLmods/Omni-Reasoner-2B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: prithivMLmods/Omni-Reasoner-2B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-31 14:44:14 +08:00
commit c666ed54aa
15 changed files with 152661 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
.gitattributes vendored Normal file
View File

@@ -0,0 +1,37 @@
*.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
model.safetensors filter=lfs diff=lfs merge=lfs -text

569
Omni-R/omni-r.ipynb Normal file
View File

@@ -0,0 +1,569 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "-b4-SW1aGOcF"
},
"source": [
"# **Omni-Reasoner**\n",
"\n",
"Qwen2VLForConditionalGeneration"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "oDmd1ZObGSel",
"outputId": "83835185-bd5e-4251-a5bd-9dea119b62bc"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting gradio\n",
" Downloading gradio-5.12.0-py3-none-any.whl.metadata (16 kB)\n",
"Collecting spaces\n",
" Downloading spaces-0.32.0-py3-none-any.whl.metadata (1.0 kB)\n",
"Requirement already satisfied: transformers in /usr/local/lib/python3.11/dist-packages (4.47.1)\n",
"Requirement already satisfied: accelerate in /usr/local/lib/python3.11/dist-packages (1.2.1)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (1.26.4)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (2.32.3)\n",
"Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (2.5.1+cu121)\n",
"Requirement already satisfied: torchvision in /usr/local/lib/python3.11/dist-packages (0.20.1+cu121)\n",
"Collecting qwen-vl-utils\n",
" Downloading qwen_vl_utils-0.0.8-py3-none-any.whl.metadata (3.6 kB)\n",
"Collecting av\n",
" Downloading av-14.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.5 kB)\n",
"Requirement already satisfied: ipython in /usr/local/lib/python3.11/dist-packages (7.34.0)\n",
"Collecting reportlab\n",
" Downloading reportlab-4.2.5-py3-none-any.whl.metadata (1.5 kB)\n",
"Collecting fpdf\n",
" Downloading fpdf-1.7.2.tar.gz (39 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting python-docx\n",
" Downloading python_docx-1.1.2-py3-none-any.whl.metadata (2.0 kB)\n",
"Requirement already satisfied: pillow in /usr/local/lib/python3.11/dist-packages (11.1.0)\n",
"Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/dist-packages (0.27.1)\n",
"Collecting aiofiles<24.0,>=22.0 (from gradio)\n",
" Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)\n",
"Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.7.1)\n",
"Collecting fastapi<1.0,>=0.115.2 (from gradio)\n",
" Downloading fastapi-0.115.6-py3-none-any.whl.metadata (27 kB)\n",
"Collecting ffmpy (from gradio)\n",
" Downloading ffmpy-0.5.0-py3-none-any.whl.metadata (3.0 kB)\n",
"Collecting gradio-client==1.5.4 (from gradio)\n",
" Downloading gradio_client-1.5.4-py3-none-any.whl.metadata (7.1 kB)\n",
"Requirement already satisfied: httpx>=0.24.1 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.28.1)\n",
"Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.1.5)\n",
"Collecting markupsafe~=2.0 (from gradio)\n",
" Downloading MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.0 kB)\n",
"Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.10.14)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from gradio) (24.2)\n",
"Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.2.2)\n",
"Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.10.5)\n",
"Collecting pydub (from gradio)\n",
" Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
"Collecting python-multipart>=0.0.18 (from gradio)\n",
" Downloading python_multipart-0.0.20-py3-none-any.whl.metadata (1.8 kB)\n",
"Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (6.0.2)\n",
"Collecting ruff>=0.2.2 (from gradio)\n",
" Downloading ruff-0.9.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (25 kB)\n",
"Collecting safehttpx<0.2.0,>=0.1.6 (from gradio)\n",
" Downloading safehttpx-0.1.6-py3-none-any.whl.metadata (4.2 kB)\n",
"Collecting semantic-version~=2.0 (from gradio)\n",
" Downloading semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
"Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
" Downloading starlette-0.45.2-py3-none-any.whl.metadata (6.3 kB)\n",
"Collecting tomlkit<0.14.0,>=0.12.0 (from gradio)\n",
" Downloading tomlkit-0.13.2-py3-none-any.whl.metadata (2.7 kB)\n",
"Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.15.1)\n",
"Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (4.12.2)\n",
"Collecting uvicorn>=0.14.0 (from gradio)\n",
" Downloading uvicorn-0.34.0-py3-none-any.whl.metadata (6.5 kB)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from gradio-client==1.5.4->gradio) (2024.10.0)\n",
"Requirement already satisfied: websockets<15.0,>=10.0 in /usr/local/lib/python3.11/dist-packages (from gradio-client==1.5.4->gradio) (14.1)\n",
"Requirement already satisfied: psutil<6,>=2 in /usr/local/lib/python3.11/dist-packages (from spaces) (5.9.5)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from transformers) (3.16.1)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (2024.11.6)\n",
"Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.21.0)\n",
"Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.5.2)\n",
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.11/dist-packages (from transformers) (4.67.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests) (3.4.1)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests) (2.3.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests) (2024.12.14)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch) (3.4.2)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.11/dist-packages (from torch) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.11/dist-packages (from torch) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.11/dist-packages (from torch) (12.1.105)\n",
"Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.11/dist-packages (from torch) (9.1.0.70)\n",
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.11/dist-packages (from torch) (12.1.3.1)\n",
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.11/dist-packages (from torch) (11.0.2.54)\n",
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.11/dist-packages (from torch) (10.3.2.106)\n",
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.11/dist-packages (from torch) (11.4.5.107)\n",
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.11/dist-packages (from torch) (12.1.0.106)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch) (2.21.5)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.11/dist-packages (from torch) (12.1.105)\n",
"Requirement already satisfied: triton==3.1.0 in /usr/local/lib/python3.11/dist-packages (from torch) (3.1.0)\n",
"Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch) (1.13.1)\n",
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.11/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch) (12.6.85)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch) (1.3.0)\n",
"Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.11/dist-packages (from ipython) (75.1.0)\n",
"Collecting jedi>=0.16 (from ipython)\n",
" Downloading jedi-0.19.2-py2.py3-none-any.whl.metadata (22 kB)\n",
"Requirement already satisfied: decorator in /usr/local/lib/python3.11/dist-packages (from ipython) (4.4.2)\n",
"Requirement already satisfied: pickleshare in /usr/local/lib/python3.11/dist-packages (from ipython) (0.7.5)\n",
"Requirement already satisfied: traitlets>=4.2 in /usr/local/lib/python3.11/dist-packages (from ipython) (5.7.1)\n",
"Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from ipython) (3.0.48)\n",
"Requirement already satisfied: pygments in /usr/local/lib/python3.11/dist-packages (from ipython) (2.18.0)\n",
"Requirement already satisfied: backcall in /usr/local/lib/python3.11/dist-packages (from ipython) (0.2.0)\n",
"Requirement already satisfied: matplotlib-inline in /usr/local/lib/python3.11/dist-packages (from ipython) (0.1.7)\n",
"Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.11/dist-packages (from ipython) (4.9.0)\n",
"Requirement already satisfied: chardet in /usr/local/lib/python3.11/dist-packages (from reportlab) (5.2.0)\n",
"Requirement already satisfied: lxml>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from python-docx) (5.3.0)\n",
"Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.11/dist-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
"Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
" Downloading starlette-0.41.3-py3-none-any.whl.metadata (6.0 kB)\n",
"Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/dist-packages (from httpx>=0.24.1->gradio) (1.0.7)\n",
"Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.11/dist-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
"Requirement already satisfied: parso<0.9.0,>=0.8.4 in /usr/local/lib/python3.11/dist-packages (from jedi>=0.16->ipython) (0.8.4)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
"Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.11/dist-packages (from pexpect>4.3->ipython) (0.7.0)\n",
"Requirement already satisfied: wcwidth in /usr/local/lib/python3.11/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython) (0.2.13)\n",
"Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.0->gradio) (0.7.0)\n",
"Requirement already satisfied: pydantic-core==2.27.2 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.0->gradio) (2.27.2)\n",
"Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.8)\n",
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (13.9.4)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.17.0)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
"Downloading gradio-5.12.0-py3-none-any.whl (57.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 MB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading gradio_client-1.5.4-py3-none-any.whl (321 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m321.4/321.4 kB\u001b[0m \u001b[31m25.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading spaces-0.32.0-py3-none-any.whl (29 kB)\n",
"Downloading qwen_vl_utils-0.0.8-py3-none-any.whl (5.9 kB)\n",
"Downloading av-14.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (33.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m33.8/33.8 MB\u001b[0m \u001b[31m27.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading reportlab-4.2.5-py3-none-any.whl (1.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.9/1.9 MB\u001b[0m \u001b[31m33.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading python_docx-1.1.2-py3-none-any.whl (244 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m244.3/244.3 kB\u001b[0m \u001b[31m10.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
"Downloading fastapi-0.115.6-py3-none-any.whl (94 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.8/94.8 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading jedi-0.19.2-py2.py3-none-any.whl (1.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m29.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (28 kB)\n",
"Downloading python_multipart-0.0.20-py3-none-any.whl (24 kB)\n",
"Downloading ruff-0.9.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.4/12.4 MB\u001b[0m \u001b[31m40.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading safehttpx-0.1.6-py3-none-any.whl (8.7 kB)\n",
"Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
"Downloading starlette-0.41.3-py3-none-any.whl (73 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.2/73.2 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading tomlkit-0.13.2-py3-none-any.whl (37 kB)\n",
"Downloading uvicorn-0.34.0-py3-none-any.whl (62 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.3/62.3 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading ffmpy-0.5.0-py3-none-any.whl (6.0 kB)\n",
"Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
"Building wheels for collected packages: fpdf\n",
" Building wheel for fpdf (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for fpdf: filename=fpdf-1.7.2-py2.py3-none-any.whl size=40704 sha256=30ea77e9b92cd500a9949be10d62f59d531839024746553304a480325794ec70\n",
" Stored in directory: /root/.cache/pip/wheels/65/4f/66/bbda9866da446a72e206d6484cd97381cbc7859a7068541c36\n",
"Successfully built fpdf\n",
"Installing collected packages: pydub, fpdf, uvicorn, tomlkit, semantic-version, ruff, reportlab, python-multipart, python-docx, markupsafe, jedi, ffmpy, av, aiofiles, starlette, qwen-vl-utils, safehttpx, gradio-client, fastapi, gradio, spaces\n",
" Attempting uninstall: markupsafe\n",
" Found existing installation: MarkupSafe 3.0.2\n",
" Uninstalling MarkupSafe-3.0.2:\n",
" Successfully uninstalled MarkupSafe-3.0.2\n",
"Successfully installed aiofiles-23.2.1 av-14.0.1 fastapi-0.115.6 ffmpy-0.5.0 fpdf-1.7.2 gradio-5.12.0 gradio-client-1.5.4 jedi-0.19.2 markupsafe-2.1.5 pydub-0.25.1 python-docx-1.1.2 python-multipart-0.0.20 qwen-vl-utils-0.0.8 reportlab-4.2.5 ruff-0.9.2 safehttpx-0.1.6 semantic-version-2.10.0 spaces-0.32.0 starlette-0.41.3 tomlkit-0.13.2 uvicorn-0.34.0\n"
]
}
],
"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": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 715
},
"id": "ovBSsRFhGbs2",
"outputId": "dac679b7-0850-4cb4-b67e-538b4b49cc11"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading Omni-Reasoner...\n",
"Running Gradio in a Colab notebook requires sharing enabled. Automatically setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
"\n",
"Colab notebook detected. This cell will run indefinitely so that you can see errors and logs. To turn off, set debug=False in launch().\n",
"* Running on public URL: https://f0e8ea5657a5c96892.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"https://f0e8ea5657a5c96892.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Keyboard interruption in main thread... closing server.\n",
"Killing tunnel 127.0.0.1:7860 <> https://f0e8ea5657a5c96892.gradio.live\n"
]
},
{
"data": {
"text/plain": []
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"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---'\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",
" \"Omni-Reasoner\": \"prithivMLmods/Omni-Reasoner-2B\",\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(\"# Omni-Reasoner\")\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=\"Omni-Reasoner\"\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
}

372
README.md Normal file
View File

@@ -0,0 +1,372 @@
---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen2-VL-2B-Instruct
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- text-generation-inference
- Omni
- Math
- Reasoner
- Qwen-Base
---
# **Omni-Reasoner-2B [VL/ Doc OCR]**
![ADS.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/GJGP5Qvo7ew-ZQbwb3Hp9.png)
*Omni-Reasoner-2B* is based on Qwen2VL and is designed for mathematical and content-based explanations. It excels in providing detailed reasoning about content and solving math problems with proper content formatting. This model integrates a conversational approach with visual and textual understanding to handle multi-modal tasks effectively.
# **Use it with Transformers**
*Before using, ensure that the required libraries are successfully installed in the environment.*
!pip install gradio spaces transformers accelerate numpy requests torch torchvision qwen-vl-utils av ipython reportlab fpdf python-docx pillow huggingface_hub
*ChemQwen With Inference Documentation, **Before using, make sure that the `hf_token` is provided in the login field in the code below.***
# **Sample Inference with Doc**
![omnip.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/53LkSMzAkIl1Yxc2yfLwb.png)
📒*Demo:* https://huggingface.co/prithivMLmods/Omni-Reasoner-2B/blob/main/Omni-R/omni-r.ipynb
```python
# Authenticate with Hugging Face
from huggingface_hub import login
# Log in to Hugging Face using the provided token
hf_token = '----xxxxx----'
login(hf_token)
# Demo
import gradio as gr
import spaces
from transformers import Qwen2VLForConditionalGeneration, AutoProcessor, TextIteratorStreamer
from qwen_vl_utils import process_vision_info
import torch
from PIL import Image
import os
import uuid
import io
from threading import Thread
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.lib import colors
from reportlab.platypus import SimpleDocTemplate, Image as RLImage, Paragraph, Spacer
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
import docx
from docx.enum.text import WD_ALIGN_PARAGRAPH
# Define model options
MODEL_OPTIONS = {
"Omni-Reasoner": "prithivMLmods/Omni-Reasoner-2B",
}
# Preload models and processors into CUDA
models = {}
processors = {}
for name, model_id in MODEL_OPTIONS.items():
print(f"Loading {name}...")
models[name] = Qwen2VLForConditionalGeneration.from_pretrained(
model_id,
trust_remote_code=True,
torch_dtype=torch.float16
).to("cuda").eval()
processors[name] = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
image_extensions = Image.registered_extensions()
def identify_and_save_blob(blob_path):
"""Identifies if the blob is an image and saves it."""
try:
with open(blob_path, 'rb') as file:
blob_content = file.read()
try:
Image.open(io.BytesIO(blob_content)).verify() # Check if it's a valid image
extension = ".png" # Default to PNG for saving
media_type = "image"
except (IOError, SyntaxError):
raise ValueError("Unsupported media type. Please upload a valid image.")
filename = f"temp_{uuid.uuid4()}_media{extension}"
with open(filename, "wb") as f:
f.write(blob_content)
return filename, media_type
except FileNotFoundError:
raise ValueError(f"The file {blob_path} was not found.")
except Exception as e:
raise ValueError(f"An error occurred while processing the file: {e}")
@spaces.GPU
def qwen_inference(model_name, media_input, text_input=None):
"""Handles inference for the selected model."""
model = models[model_name]
processor = processors[model_name]
if isinstance(media_input, str):
media_path = media_input
if media_path.endswith(tuple([i for i in image_extensions.keys()])):
media_type = "image"
else:
try:
media_path, media_type = identify_and_save_blob(media_input)
except Exception as e:
raise ValueError("Unsupported media type. Please upload a valid image.")
messages = [
{
"role": "user",
"content": [
{
"type": media_type,
media_type: media_path
},
{"type": "text", "text": text_input},
],
}
]
text = processor.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
image_inputs, _ = process_vision_info(messages)
inputs = processor(
text=[text],
images=image_inputs,
padding=True,
return_tensors="pt",
).to("cuda")
streamer = TextIteratorStreamer(
processor.tokenizer, skip_prompt=True, skip_special_tokens=True
)
generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)
thread = Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()
buffer = ""
for new_text in streamer:
buffer += new_text
# Remove <|im_end|> or similar tokens from the output
buffer = buffer.replace("<|im_end|>", "")
yield buffer
def format_plain_text(output_text):
"""Formats the output text as plain text without LaTeX delimiters."""
# Remove LaTeX delimiters and convert to plain text
plain_text = output_text.replace("\\(", "").replace("\\)", "").replace("\\[", "").replace("\\]", "")
return plain_text
def generate_document(media_path, output_text, file_format, font_size, line_spacing, alignment, image_size):
"""Generates a document with the input image and plain text output."""
plain_text = format_plain_text(output_text)
if file_format == "pdf":
return generate_pdf(media_path, plain_text, font_size, line_spacing, alignment, image_size)
elif file_format == "docx":
return generate_docx(media_path, plain_text, font_size, line_spacing, alignment, image_size)
def generate_pdf(media_path, plain_text, font_size, line_spacing, alignment, image_size):
"""Generates a PDF document."""
filename = f"output_{uuid.uuid4()}.pdf"
doc = SimpleDocTemplate(
filename,
pagesize=A4,
rightMargin=inch,
leftMargin=inch,
topMargin=inch,
bottomMargin=inch
)
styles = getSampleStyleSheet()
styles["Normal"].fontSize = int(font_size)
styles["Normal"].leading = int(font_size) * line_spacing
styles["Normal"].alignment = {
"Left": 0,
"Center": 1,
"Right": 2,
"Justified": 4
}[alignment]
story = []
# Add image with size adjustment
image_sizes = {
"Small": (200, 200),
"Medium": (400, 400),
"Large": (600, 600)
}
img = RLImage(media_path, width=image_sizes[image_size][0], height=image_sizes[image_size][1])
story.append(img)
story.append(Spacer(1, 12))
# Add plain text output
text = Paragraph(plain_text, styles["Normal"])
story.append(text)
doc.build(story)
return filename
def generate_docx(media_path, plain_text, font_size, line_spacing, alignment, image_size):
"""Generates a DOCX document."""
filename = f"output_{uuid.uuid4()}.docx"
doc = docx.Document()
# Add image with size adjustment
image_sizes = {
"Small": docx.shared.Inches(2),
"Medium": docx.shared.Inches(4),
"Large": docx.shared.Inches(6)
}
doc.add_picture(media_path, width=image_sizes[image_size])
doc.add_paragraph()
# Add plain text output
paragraph = doc.add_paragraph()
paragraph.paragraph_format.line_spacing = line_spacing
paragraph.paragraph_format.alignment = {
"Left": WD_ALIGN_PARAGRAPH.LEFT,
"Center": WD_ALIGN_PARAGRAPH.CENTER,
"Right": WD_ALIGN_PARAGRAPH.RIGHT,
"Justified": WD_ALIGN_PARAGRAPH.JUSTIFY
}[alignment]
run = paragraph.add_run(plain_text)
run.font.size = docx.shared.Pt(int(font_size))
doc.save(filename)
return filename
# CSS for output styling
css = """
#output {
height: 500px;
overflow: auto;
border: 1px solid #ccc;
}
.submit-btn {
background-color: #cf3434 !important;
color: white !important;
}
.submit-btn:hover {
background-color: #ff2323 !important;
}
.download-btn {
background-color: #35a6d6 !important;
color: white !important;
}
.download-btn:hover {
background-color: #22bcff !important;
}
"""
# Gradio app setup
with gr.Blocks(css=css) as demo:
gr.Markdown("# ChemQwen Chemical Identifier")
with gr.Tab(label="Image Input"):
with gr.Row():
with gr.Column():
model_choice = gr.Dropdown(
label="Model Selection",
choices=list(MODEL_OPTIONS.keys()),
value="Omni-Reasoner"
)
input_media = gr.File(
label="Upload Image", type="filepath"
)
text_input = gr.Textbox(label="Question", placeholder="Ask a question about the image...")
submit_btn = gr.Button(value="Submit", elem_classes="submit-btn")
with gr.Column():
output_text = gr.Textbox(label="Output Text", lines=10)
plain_text_output = gr.Textbox(label="Standardized Plain Text", lines=10)
submit_btn.click(
qwen_inference, [model_choice, input_media, text_input], [output_text]
).then(
lambda output_text: format_plain_text(output_text), [output_text], [plain_text_output]
)
# Add examples directly usable by clicking
with gr.Row():
with gr.Column():
line_spacing = gr.Dropdown(
choices=[0.5, 1.0, 1.15, 1.5, 2.0, 2.5, 3.0],
value=1.5,
label="Line Spacing"
)
font_size = gr.Dropdown(
choices=["8", "10", "12", "14", "16", "18", "20", "22", "24"],
value="18",
label="Font Size"
)
alignment = gr.Dropdown(
choices=["Left", "Center", "Right", "Justified"],
value="Justified",
label="Text Alignment"
)
image_size = gr.Dropdown(
choices=["Small", "Medium", "Large"],
value="Small",
label="Image Size"
)
file_format = gr.Radio(["pdf", "docx"], label="File Format", value="pdf")
get_document_btn = gr.Button(value="Get Document", elem_classes="download-btn")
get_document_btn.click(
generate_document, [input_media, output_text, file_format, font_size, line_spacing, alignment, image_size], gr.File(label="Download Document")
)
demo.launch(debug=True)
```
# **Key Enhancements**
1. **Advanced Reasoning Capabilities**:
- Enhanced ability to perform long-form reasoning for complex mathematical and content-based queries.
- Supports detailed step-by-step explanations for problem-solving and content formatting.
2. **Multi-Modal Integration**:
- Combines visual and textual understanding to interpret and analyze diverse input formats (images, text, and mathematical expressions).
3. **Conversational Workflow**:
- Offers a natural conversational interface for interactive problem-solving and explanations.
4. **Content Formatting**:
- Improves content presentation with structured formatting for better readability and understanding.
# **Intended Use**
1. **Educational Assistance**:
- Ideal for students and educators for solving mathematical problems, creating structured explanations, and formatting educational content.
2. **Research Support**:
- Assists researchers in generating in-depth explanations and interpreting complex visual and textual data.
3. **Content Creation**:
- Enhances the generation of well-formatted documents, reports, and presentations.
4. **General Purpose Assistance**:
- Useful for applications requiring long-form reasoning and conversational AI in domains like tutoring, customer support, and technical writing.
# **Limitations**
1. **Domain-Specific Expertise**:
- May struggle with niche or highly specialized topics outside its training domain.
2. **Error in Long-Chain Reasoning**:
- In rare cases, it might generate incorrect or inconsistent solutions for highly complex problems.
3. **Visual Data Limitations**:
- Performance may depend on the quality and clarity of visual inputs (e.g., low-resolution images may reduce accuracy).
4. **Formatting Constraints**:
- While effective, complex or heavily customized formatting tasks may require manual adjustments.
5. **Dependence on Context**:
- The model relies on well-structured input to produce accurate and coherent outputs; ambiguous or incomplete prompts may lead to suboptimal results.

16
added_tokens.json Normal file
View 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
View 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 %}"
}

49
config.json Normal file
View File

@@ -0,0 +1,49 @@
{
"_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
"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": "bfloat16",
"transformers_version": "4.47.1",
"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
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}

14
generation_config.json Normal file
View 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": "4.47.1"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a68fb3357544c1b5f122d9661a507596c4d52ee1c0106c20683a9578cd9150a2
size 4418050848

29
preprocessor_config.json Normal file
View 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
View 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
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
size 11420371

145
tokenizer_config.json Normal file
View 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
View File

File diff suppressed because one or more lines are too long