OpenMOSS-Team/MOSS-VL-Instruct-0408

sync offline system prompts with training data: no_thinking -> no system message, deep_thinking -> <think>/<answer> tags

Unify modeling/configuration/tokenizer with the 0708 standard (transformers 4.57 compatible, includes query RoPE fix)

fix: apply query RoPE in cross-attention when reusing cached vision KV during decode

Replace processor with 0708 version (Fast image/video processor, transformers 4.57+); keep 0408 pixel caps

Upload README.md with huggingface_hub

Update README.md

Update processing_moss_vl.py

Update processing_moss_vl.py

fix _tied_weights_keys format

Update modeling_moss_vl.py

Update video_processing_moss_vl.py

Update processing_moss_vl.py

update transformers to 5.5.4

Update code for transformers 5.5.4 (#1)

Update modeling_moss_vl.py

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Delete assets/benchmark_table.png

Delete assets/radar.png

Upload folder using huggingface_hub

Delete assets/timestamp_input copy.svg

Upload folder using huggingface_hub

Update README.md

Upload folder using huggingface_hub

Update README.md

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Delete assets/MOSS-VL-Benchmark.png

Update README.md

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Update README.md

Upload folder using huggingface_hub

Update README.md

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Update README.md