3 GB

Ctrl+K

1 contributor

History: 18 commits

dejanseo

Add training pipelines, consistency distillation scripts, and interactive dashboard server

69dcf19 verified about 1 month ago

bin
Release sub-millisecond 1-bit consistency retriever: ONNX, INT4 QAT checkpoint, and native C++ engine about 2 months ago
checkpoints
Fix ONNX time conditioning and sinusoidal embedding parity with PyTorch about 2 months ago
cpp
Release sub-millisecond 1-bit consistency retriever: ONNX, INT4 QAT checkpoint, and native C++ engine about 2 months ago
data
Upload 540k subquery index embeddings and text for nearest neighbor decoding about 2 months ago
models
Release sub-millisecond 1-bit consistency retriever: ONNX, INT4 QAT checkpoint, and native C++ engine about 2 months ago
scripts
Add training pipelines, consistency distillation scripts, and interactive dashboard server about 1 month ago
src
Add training pipelines, consistency distillation scripts, and interactive dashboard server about 2 months ago
static
Add training pipelines, consistency distillation scripts, and interactive dashboard server about 1 month ago
triton_model_repository
Release sub-millisecond 1-bit consistency retriever: ONNX, INT4 QAT checkpoint, and native C++ engine about 2 months ago
.gitattributes

1.67 kB
Add training pipelines, consistency distillation scripts, and interactive dashboard server about 2 months ago
README.md

7.46 kB
Add training pipelines, consistency distillation scripts, and interactive dashboard server about 1 month ago
diffusion_540k_best.pt

165 MB
xet

Update best checkpoint with stabilized EDM log-normal schedule (val loss 0.6571) about 2 months ago
fanout_deployment_bundle.zip

27.5 MB
xet

Release sub-millisecond 1-bit consistency retriever: ONNX, INT4 QAT checkpoint, and native C++ engine about 2 months ago
journal.db

270 kB
xet

Add training pipelines, consistency distillation scripts, and interactive dashboard server about 1 month ago
load_model.py

9.7 kB
Fix ONNX input/output feed tensor names about 2 months ago