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 4)
Browse filesThis view is limited to 50 files because it contains too many changes. Β See raw diff
- .gitattributes +3 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/scheduler.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/tokenizer.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/tokenizer_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/trainer_state.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/training_args.bin +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/zero_to_fp32.py +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/args.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/chat_template.jinja +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/generation_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/mp_rank_00_model_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/latest +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/model.safetensors +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/processor_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_0.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_1.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_2.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_3.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_4.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_5.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_6.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_7.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/scheduler.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/tokenizer.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/tokenizer_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/trainer_state.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/training_args.bin +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/zero_to_fp32.py +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/logging.jsonl +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/args.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/args.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/chat_template.jinja +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/generation_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -0
.gitattributes
CHANGED
|
@@ -69,3 +69,6 @@ data/ms-swift-data/video_sft_small_10pct_sharegpt.json filter=lfs diff=lfs merge
|
|
| 69 |
legacy/self_refine/qwen3vl_2b_10pct/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 70 |
legacy/video_mllm_swift/s1_declip_siglip2_qwen3_1.7b/v0-20260314-141147/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 71 |
legacy/video_mllm_swift/s1_declip_siglip2_qwen3_1.7b/v0-20260314-141147/checkpoint-2181/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
legacy/self_refine/qwen3vl_2b_10pct/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 70 |
legacy/video_mllm_swift/s1_declip_siglip2_qwen3_1.7b/v0-20260314-141147/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 71 |
legacy/video_mllm_swift/s1_declip_siglip2_qwen3_1.7b/v0-20260314-141147/checkpoint-2181/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
legacy/video_mllm_swift/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
legacy/video_mllm_swift/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
legacy/video_mllm_swift/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/scheduler.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/tokenizer.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/tokenizer_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/trainer_state.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/training_args.bin
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2000/zero_to_fp32.py
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/args.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/chat_template.jinja
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/generation_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/global_step2181/mp_rank_00_model_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/latest
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/model.safetensors
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/processor_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_0.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_1.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_2.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_3.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_4.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_5.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_6.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/rng_state_7.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/scheduler.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/tokenizer.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/tokenizer_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/trainer_state.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/training_args.bin
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/checkpoint-2181/zero_to_fp32.py
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s1_siglip2_qwen3_1.7b/v11-20260314-090153/logging.jsonl
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/args.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/args.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/chat_template.jinja
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/generation_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_declip_siglip2_qwen3_1.7b_10pct/checkpoint-1000/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|