LocalAI-io/LocalVQE
Sync model card with upstream GitHub inference README
Upload localvqe-pi-aec-v1-49k-f32.gguf with huggingface_hub
Upload localvqe-pi-v1-49k-f32.gguf with huggingface_hub
Upload localvqe-v1.4-aec-2.7K-f32.gguf with huggingface_hub
Upload localvqe-v1.4-aec-200K-bf16.gguf with huggingface_hub
Upload localvqe-v1.4-aec-200K-f32.gguf with huggingface_hub
Sync model card with upstream GitHub inference README
Sync model card with upstream GitHub inference README
Sync model card with upstream GitHub inference README
Sync model card with upstream GitHub inference README
Upload localvqe-v1.3-4.8M-f32.gguf with huggingface_hub
Upload localvqe-v1.3-4.8M.pt with huggingface_hub
Sync model card with upstream GitHub inference README
Upload localvqe-v1.2-1.3M-f32.gguf with huggingface_hub
Upload localvqe-v1.2-1.3M.pt with huggingface_hub
paper: fix GitHub org URL (LocalAI-io -> localai-org)
Sync model card with upstream GitHub inference README
Sync model card with upstream GitHub inference README
Upload localvqe-v1.1-1.3M-f32.gguf with huggingface_hub
Upload localvqe-v1.1-1.3M.pt with huggingface_hub
Sync model card with upstream GitHub inference README
Sync model card with upstream GitHub inference README
Sync model card with upstream GitHub inference README
Add LocalVQE technical report PDF
Sync model card with upstream GitHub inference README
Upload localvqe-v1-1.3M-f32.gguf with huggingface_hub
Upload localvqe-v1-1.3M.pt with huggingface_hub
ckpt: register align.temperature as buffer (carries trained value 0.1 in state_dict)
gguf: re-export with AlignBlock temperature folded into smoothing conv
Sync model card with upstream GitHub inference README
Sync model card with upstream GitHub inference README
remove old localvqe-v1-f32.gguf, replaced by localvqe-v1-1.3M variants
remove old localvqe-v1.pt, replaced by localvqe-v1-1.3M variants
Upload localvqe-v1-1.3M-f32.gguf with huggingface_hub
Upload localvqe-v1-1.3M.pt with huggingface_hub
Sync model card with upstream GitHub inference README
Upload localvqe-v1-f32.gguf with huggingface_hub
Upload localvqe-v1.pt with huggingface_hub
Sync model card with upstream GitHub inference README
Upload localvqe-v1-f32.gguf with huggingface_hub
Upload localvqe-v1.pt with huggingface_hub
Sync model card with upstream GitHub inference README
Update README.md
Sync model card with upstream GitHub inference README
Remove stale pre-rename file: localvqe-finetune.gguf
Remove stale pre-rename file: finetune.pt
Remove stale pre-rename file: localvqe-baseline.gguf
Remove stale pre-rename file: baseline.pt
Upload localvqe-v1-f32.gguf with huggingface_hub
Upload localvqe-v1.pt with huggingface_hub