Instructions to use xiaomoguhzz/VisionEncoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xiaomoguhzz/VisionEncoder with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("xiaomoguhzz/VisionEncoder", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Restructure repo into data/ + legacy/ (batch 6)
Browse filesThis view is limited to 50 files because it contains too many changes. Β See raw diff
- {vmllm_cached β data/vmllm_cached}/qwen3vit/image_10pct/train/data-00000-of-00001.arrow +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/image_10pct/train/dataset_info.json +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/image_10pct/train/state.json +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/data-00000-of-00002.arrow +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/data-00001-of-00002.arrow +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/dataset_info.json +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/state.json +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_10pct/train/data-00000-of-00001.arrow +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_10pct/train/dataset_info.json +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_10pct/train/state.json +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/data-00000-of-00003.arrow +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/data-00001-of-00003.arrow +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/data-00002-of-00003.arrow +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/dataset_info.json +0 -0
- {vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/state.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_siglip2_qwen3_1.7b_10pct/checkpoint-900/training_args.bin +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_siglip2_qwen3_1.7b_10pct/checkpoint-900/zero_to_fp32.py +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_siglip2_qwen3_1.7b_10pct/logging.jsonl +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/data-00000-of-00001.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/dataset_info.json +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/state.json +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/v3_patch_meta.json +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/data-00000-of-00001.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/dataset_info.json +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/state.json +0 -0
- {vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/v3_patch_meta.json +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00000_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00001_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00002_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00003_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00004_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00005_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00006_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00007_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00008_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00009_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00010_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00011_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00012_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00013_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00014_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00015_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00000_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00001_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00002_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00003_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00004_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00005_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00006_of_00016.arrow +0 -0
- {vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00007_of_00016.arrow +0 -0
{vmllm_cached β data/vmllm_cached}/qwen3vit/image_10pct/train/data-00000-of-00001.arrow
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/image_10pct/train/dataset_info.json
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/image_10pct/train/state.json
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/data-00000-of-00002.arrow
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/data-00001-of-00002.arrow
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/dataset_info.json
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/image_full/train/state.json
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_10pct/train/data-00000-of-00001.arrow
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_10pct/train/dataset_info.json
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_10pct/train/state.json
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/data-00000-of-00003.arrow
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/data-00001-of-00003.arrow
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/data-00002-of-00003.arrow
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/dataset_info.json
RENAMED
|
File without changes
|
{vmllm_cached β data/vmllm_cached}/qwen3vit/video_full/train/state.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_siglip2_qwen3_1.7b_10pct/checkpoint-900/training_args.bin
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_siglip2_qwen3_1.7b_10pct/checkpoint-900/zero_to_fp32.py
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_siglip2_qwen3_1.7b_10pct/logging.jsonl
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/data-00000-of-00001.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/dataset_info.json
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/state.json
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/image_10pct/train/v3_patch_meta.json
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/data-00000-of-00001.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/dataset_info.json
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/state.json
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/qwenvit_v4_1/video_10pct/train/v3_patch_meta.json
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00000_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00001_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00002_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00003_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00004_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00005_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00006_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00007_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00008_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00009_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00010_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00011_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00012_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00013_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00014_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00015_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00000_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00001_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00002_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00003_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00004_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00005_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00006_of_00016.arrow
RENAMED
|
File without changes
|
{vmllm_cached β legacy/vmllm_cached}/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00007_of_00016.arrow
RENAMED
|
File without changes
|