RT-J — int8 (Q8_0-style) quantized checkpoints
Int8 quantizations of stanford-star/rt-j,
the Relational Transformer foundation model for in-context learning over
relational databases. Produced and consumed by the
RelativeDB native inference engine
(cpp/rt_quantize --type q8). Weights stay quantized-resident at
inference: the engine's CPU (Accelerate / portable SIMD) and Metal/MPS
kernels dequantize inside the GEMM, so DRAM weight traffic is the int8
payload.
Sibling repos: rt-j-int4 · rt-j-fp16
| File | Task head | Size |
|---|---|---|
classification/model.q8.safetensors | classification / ranking (logits — apply sigmoid) | 86 MB |
regression/model.q8.safetensors | regression / forecasting (normalized values) | 86 MB |
(vs. 171 MB bf16 upstream, 342 MB fp32 in memory.)
Quantization format
Q8_0-style, plain safetensors — no custom container:
- Every transformer-block projection (
wq/wk/wv/wg,wo,ffn.w1/w2/w3across all 12 blocks — ~99% of parameters) is stored as anI8tensor with a per-output-row symmetric fp32 scale in a<name>.q_scalecompanion tensor:W[o,i] ≈ q[o,i] * scale[o],scale[o] = max|W[o,:]| / 127. - The value/col-name encoders, decoder head, norms, biases and mask embeddings stay fp32 (like llama.cpp's embedding/output layers): input-side quantization error would propagate through all 12 blocks for a negligible size win.
Any safetensors reader can load these files; dequantization is one line per row. The RelativeDB engine keeps the int8 payload resident and dequantizes 64-row tiles (CPU) or in-register while staging GEMM tiles (Metal); the CUDA backend is fp32-only for now.
Accuracy
Measured on the RelativeDB golden batch (B=5, S=16 churn example) against the PyTorch reference, identical on CPU and Metal/MPS:
| Metric | fp32 | int8 |
|---|---|---|
yhat max abs. error vs. torch | 3.9e-3 | 1.1e-2 |
yhat mean abs. error | 5.1e-4 | 3.5e-3 |
| target-score sign / ranking | preserved | preserved |
Worst per-row mean relative weight error: ≈5%.
Usage (RelativeDB native engine)
# direct path
./build/rt_test testdata classification/model.q8.safetensors --quantized --device mps
# via the Java / Python / Rust bindings: place the .q8 file next to the fp32
# checkpoint (or point at a directory containing it) and opt in with
export RELATIVEDB_RT_QUANTIZED=q8 # (or 1/true; q4 and f16 select siblings)
The C ABI (rt_model_load) accepts these files directly — the format is
auto-detected from the tensor dtypes.
Reproduce
cmake -B build -S cpp && cmake --build build -j
./build/rt_quantize <rt-j>/classification/model.safetensors classification/model.q8.safetensors
./build/rt_quantize <rt-j>/regression/model.safetensors regression/model.q8.safetensors
License & attribution
Derivative of stanford-star/rt-j (Stanford STAR lab), redistributed under the same CC-BY-NC-SA-4.0 license. Architecture and training details are described in the upstream model card; only the weight storage format differs here.