sugarknight
/

erabi-practical-v1-experimental

@@ -55,7 +55,7 @@ python -m pip install erabi
 erabi predict --request request.json
 ```
-The repository contains three inference formats from the same checkpoint: `model.safetensors` (PyTorch), `onnx/fp32/model.onnx` (CPU), and `onnx/fp16/model.onnx` (NVIDIA GPU). ERABI 0.1.2 or newer is required for `--model-format`; 0.1.1 uses PyTorch safetensors. Upgrade with `python -m pip install --upgrade erabi`. `--model-format auto` downloads only the selected variant: FP32 ONNX for CPU with ONNX Runtime, FP16 ONNX for CUDA with CUDA Execution Provider, and otherwise PyTorch safetensors. Install the compatible `onnxruntime` (CPU) or `onnxruntime-gpu` (GPU) separately; do not install both in one environment. You can also select `--model-format pytorch`, `onnx-fp32`, or `onnx-fp16` explicitly.
 The newly exported ONNX FP32 and FP16 variants preserved the PyTorch top-ranked choice on 37/37 private Exam-QA validation cases, up to 853 input tokens. Experimental INT8 variants changed predictions substantially and are not distributed. The first invocation downloads the selected model; later invocations use the Hugging Face cache. Input and output JSON contracts and runtime recommendations are documented in the [ERABI README](https://github.com/sugarkwork/erabi#モデル形式の自動選択とおすすめ). The public ERABI runtime still defaults to a 512-token fail-closed contract. The weights were trained and experimentally checked at up to 1,024 tokens, but using that length requires changing both the runtime limit and preprocessing length while checking the untruncated input. Candidate probabilities are not calibrated confidence guarantees.

 erabi predict --request request.json
 ```
+The repository contains three inference formats from the same checkpoint: `model.safetensors` (PyTorch), `onnx/fp32/model.onnx` (CPU), and `onnx/fp16/model.onnx` (NVIDIA GPU). ERABI 0.1.3 pins this updated checkpoint by default; 0.1.2 pins the earlier Practical V1-only revision. Upgrade with `python -m pip install --upgrade erabi`. `--model-format auto` downloads only the selected variant: FP32 ONNX for CPU with ONNX Runtime, FP16 ONNX for CUDA with CUDA Execution Provider, and otherwise PyTorch safetensors. Install the compatible `onnxruntime` (CPU) or `onnxruntime-gpu` (GPU) separately; do not install both in one environment. You can also select `--model-format pytorch`, `onnx-fp32`, or `onnx-fp16` explicitly.
 The newly exported ONNX FP32 and FP16 variants preserved the PyTorch top-ranked choice on 37/37 private Exam-QA validation cases, up to 853 input tokens. Experimental INT8 variants changed predictions substantially and are not distributed. The first invocation downloads the selected model; later invocations use the Hugging Face cache. Input and output JSON contracts and runtime recommendations are documented in the [ERABI README](https://github.com/sugarkwork/erabi#モデル形式の自動選択とおすすめ). The public ERABI runtime still defaults to a 512-token fail-closed contract. The weights were trained and experimentally checked at up to 1,024 tokens, but using that length requires changing both the runtime limit and preprocessing length while checking the untruncated input. Candidate probabilities are not calibrated confidence guarantees.