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 5)
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}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/mp_rank_00_model_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/latest +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/model.safetensors +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/processor_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_0.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_1.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_2.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_3.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_4.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_5.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_6.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_7.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/scheduler.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/tokenizer.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/tokenizer_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/trainer_state.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/training_args.bin +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/zero_to_fp32.py +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/args.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/chat_template.jinja +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/generation_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/mp_rank_00_model_states.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/latest +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/model.safetensors +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/processor_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_0.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_1.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_2.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_4.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_5.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_7.pth +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/scheduler.pt +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/tokenizer.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/tokenizer_config.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/trainer_state.json +0 -0
- {video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/training_args.bin +0 -0
.gitattributes
CHANGED
|
@@ -72,3 +72,6 @@ legacy/video_mllm_swift/s1_declip_siglip2_qwen3_1.7b/v0-20260314-141147/checkpoi
|
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 75 |
+
legacy/video_mllm_swift/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
legacy/video_mllm_swift/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
legacy/video_mllm_swift/s2_siglip2_qwen3_1.7b_10pct/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/global_step300/mp_rank_00_model_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/latest
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/model.safetensors
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/processor_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_0.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_1.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_2.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_3.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_4.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_5.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_6.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/rng_state_7.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/scheduler.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/tokenizer.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/tokenizer_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/trainer_state.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/training_args.bin
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-300/zero_to_fp32.py
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/args.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/chat_template.jinja
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/generation_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/global_step400/mp_rank_00_model_states.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/latest
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/model.safetensors
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/processor_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_0.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_1.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_2.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_4.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_5.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/rng_state_7.pth
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/scheduler.pt
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/tokenizer.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/tokenizer_config.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/trainer_state.json
RENAMED
|
File without changes
|
{video_mllm_swift β legacy/video_mllm_swift}/s2_image_only_10pct/v1-20260316-135215/checkpoint-400/training_args.bin
RENAMED
|
File without changes
|