初始化项目，由ModelHub XC社区提供模型
Model: kulibinai/cadreasoner 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
|
||||
51
README.md
Normal file
51
README.md
Normal file
@@ -0,0 +1,51 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- vision-language
|
||||
- image-to-cad
|
||||
- cad
|
||||
- cadquery
|
||||
- qwen2-vl
|
||||
- 3d
|
||||
---
|
||||
# CADReasoner
|
||||
|
||||
CADReasoner is a vision–language model for **iterative CAD reverse engineering**. It generates a **runnable CadQuery program** and refines it over multiple iterations using geometric feedback from the discrepancy between the target and the current prediction.
|
||||
|
||||
**Accepted to CVPR 2026 Findings Track**
|
||||
**Paper:** https://arxiv.org/abs/2603.29847
|
||||
**Code:** https://github.com/zhemdi/CADReasoner
|
||||
**HF paper page:** https://huggingface.co/papers/2603.29847
|
||||
|
||||
## Overview
|
||||
|
||||
Unlike single-pass Image2CAD methods, CADReasoner performs iterative program editing. At each step, it uses multi-view geometric inputs together with the previous prediction to improve reconstruction quality.
|
||||
|
||||
|
||||
|
||||
## Usage
|
||||
|
||||
Please use the inference and evaluation scripts from the repository.
|
||||
|
||||
Example:
|
||||
```bash
|
||||
python3 test.py --dataset <test_dataset> --checkpoint kulibinai/CADReasoner --n_iters <n_iters> --outdir <outdir>
|
||||
```
|
||||
<test_dataset> can be one of:
|
||||
|
||||
* maksimko123/deepcad_test_mesh
|
||||
* maksimko123/fusion360_test_mesh
|
||||
* kulibinai/mcb_test
|
||||
* kulibinai/deepcad_test_scan
|
||||
* kulibinai/fusion360_test_scan
|
||||
* kulibinai/mcb_test_scan
|
||||
*
|
||||
### Citation
|
||||
```bibtex
|
||||
@article{kabisov2026cadreasoner,
|
||||
title={CADReasoner: Iterative Program Editing for CAD Reverse Engineering},
|
||||
author={Kabisov, Soslan and Kirichuk, Vsevolod and Volkov, Andrey and Savrasov, Gennadii and Barannikov, Marina and Konushin, Anton and Kuznetsov, Andrey and Zhemchuzhnikov, Dmitrii},
|
||||
journal={arXiv preprint arXiv:2603.29847},
|
||||
year={2026}
|
||||
}
|
||||
```
|
||||
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
|
||||
}
|
||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -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 %}
|
||||
57
config.json
Normal file
57
config.json
Normal file
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"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,
|
||||
"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": "4.50.3",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"embed_dim": 1280,
|
||||
"hidden_act": "quick_gelu",
|
||||
"hidden_size": 1536,
|
||||
"in_channels": 3,
|
||||
"in_chans": 3,
|
||||
"mlp_ratio": 4,
|
||||
"model_type": "qwen2_vl",
|
||||
"num_heads": 16,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"torch_dtype": "bfloat16"
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"attn_implementation": "flash_attention_2",
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.01,
|
||||
"top_k": 1,
|
||||
"top_p": 0.001,
|
||||
"transformers_version": "4.56.0.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:b9a090fb70289b9be14c6e615387aedf045ac8ade7877951bcaa3259126bd8ab
|
||||
size 4418050848
|
||||
37
preprocessor_config.json
Normal file
37
preprocessor_config.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"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": "<|endoftext|>",
|
||||
"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 sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
|
||||
size 11420538
|
||||
150
tokenizer_config.json
Normal file
150
tokenizer_config.json
Normal file
@@ -0,0 +1,150 @@
|
||||
{
|
||||
"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,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"max_length": null,
|
||||
"model_max_length": 32768,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"processor_class": "Qwen2VLProcessor",
|
||||
"resized_height": 952,
|
||||
"resized_width": 476,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"use_fast": true
|
||||
}
|
||||
45
video_preprocessor_config.json
Normal file
45
video_preprocessor_config.json
Normal file
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"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_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"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": "Qwen2VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"size_divisor": null,
|
||||
"temporal_patch_size": 2,
|
||||
"video_metadata": null,
|
||||
"video_processor_type": "Qwen2VLVideoProcessor"
|
||||
}
|
||||
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