Delete model.baar

Delete model.baar2

Delete model_strict_sub50mb.baar2

Delete model_int4_sub50mb.baar2

Deploy BAAR2-150M: Embedded 10K authentic tokenizer & pure INT8/INT4 .baar2 models

Delete vlite_manifest.json with huggingface_hub

Delete model_slim_int4.vlite with huggingface_hub

Delete model_shared_int4.vlite with huggingface_hub

Delete model_shared_int3.vlite with huggingface_hub

Delete model_shared_int2.vlite with huggingface_hub

Delete model_shared_int1.vlite with huggingface_hub

Delete model_shared.vlite with huggingface_hub

Delete model_micro_int4.vlite with huggingface_hub

Delete model_micro_int3.vlite with huggingface_hub

Delete model_micro_int2.vlite with huggingface_hub

Delete model_micro_int1.vlite with huggingface_hub

Delete model_full_int4.vlite with huggingface_hub

Delete model_full_int3.vlite with huggingface_hub

Delete model_full_int2.vlite with huggingface_hub

Delete model_full_int1.vlite with huggingface_hub

Delete model.vlite with huggingface_hub

Upload checkpoint_step_93900.pt with huggingface_hub

Upload checkpoint_step_93600.pt with huggingface_hub

Update README.md

Deploy 100% pure INT4 full performance .baar2 (73.46 MB)

Deploy sub-50MB .baar2 (48.37 MB)

Export & Deploy synced .baar2 model under 50MB (49.40 MB)

Deploy confirmed sub-50MB .baar2 model (49.40 MB)

Deploy strict sub-50MB .baar2 model (47.30 MB)

Deploy performance-balanced .baar2 model (49.53 MB)

Deploy single-file All-in-One <50MB .baar2 model

Deploy QAT-adapted <50MB .baar2 model

Upload 45MB Ultra 4-bit model.baar2 (Full 10K vocab preserved)

Upload compact 46MB .baar2 model (Full 10K vocab preserved, INT4)

Upload model.baar with huggingface_hub

Update README.md

Update README.md

Update README.md

Upload model_slim_int4.vlite with huggingface_hub

Upload model_slim_int4.vlite with huggingface_hub

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Upload folder using huggingface_hub

Update README.md

Update README.md