Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -58,7 +58,7 @@ Measured on one RTX 4090, end to end over HTTP, against the model author's own s
|
|
| 58 |
|
| 59 |
Weights are unchanged from `convaiinnovations/laya`; this repo adds only the ONNX export and the serving manifest. Conversion and serving are verified against the golden standard (the official Laya SDK, CPU fp32, 40-case corpus): identical answers on CPU and on CUDA (RTX 4090).
|
| 60 |
|
| 61 |
-
Accuracy PK — both servers on one RTX 4090 (CUDA), graded against the same golden standard:
|
| 62 |
|
| 63 |
| | Verdict | `laya-serve` | result |
|
| 64 |
|---|---:|---:|:--|
|
|
|
|
| 58 |
|
| 59 |
Weights are unchanged from `convaiinnovations/laya`; this repo adds only the ONNX export and the serving manifest. Conversion and serving are verified against the golden standard (the official Laya SDK, CPU fp32, 40-case corpus): identical answers on CPU and on CUDA (RTX 4090).
|
| 60 |
|
| 61 |
+
Accuracy PK — against `laya-serve` 0.4.7; both servers on one RTX 4090 (CUDA), graded against the same golden standard:
|
| 62 |
|
| 63 |
| | Verdict | `laya-serve` | result |
|
| 64 |
|---|---:|---:|:--|
|