Add/update model card for medium
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ base_model: roboflow/rfdetr
|
|
| 13 |
|
| 14 |
# RF-DETR Medium — GGUF for rfdetr.cpp
|
| 15 |
|
| 16 |
-
GGUF-format weights of [Roboflow RF-DETR Medium](https://github.com/roboflow/rf-detr) (detection variant) for use with [rfdetr.cpp](https://github.com/mudler/
|
| 17 |
|
| 18 |
This repo contains all four standard quantizations of this variant. **F16 is the recommended default** — same accuracy as F32, 1.85× smaller, and typically the fastest on modern CPUs thanks to ggml's F32×F16 matmul fast path.
|
| 19 |
|
|
@@ -48,7 +48,7 @@ All accuracy numbers are computed against the upstream PyTorch reference (`rfdet
|
|
| 48 |
|
| 49 |
```bash
|
| 50 |
# 1. Clone + build rfdetr.cpp
|
| 51 |
-
git clone https://github.com/mudler/
|
| 52 |
cd rt-detr.cpp
|
| 53 |
cmake -B build -DRFDETR_BUILD_CLI=ON && cmake --build build -j
|
| 54 |
|
|
@@ -67,7 +67,7 @@ build/bin/rfdetr-cli detect \
|
|
| 67 |
|
| 68 |
All accuracy metrics are computed against the upstream PyTorch reference (rfdetr 1.7.0) on 7 COCO val2017 images at threshold 0.5. Each detection match uses greedy Hungarian-style assignment by IoU (≥ 0.5 lenient, ≥ 0.95 strict) with class equality required.
|
| 69 |
|
| 70 |
-
See [BENCHMARK.md](https://github.com/mudler/
|
| 71 |
|
| 72 |
## License
|
| 73 |
|
|
|
|
| 13 |
|
| 14 |
# RF-DETR Medium — GGUF for rfdetr.cpp
|
| 15 |
|
| 16 |
+
GGUF-format weights of [Roboflow RF-DETR Medium](https://github.com/roboflow/rf-detr) (detection variant) for use with [rfdetr.cpp](https://github.com/mudler/rf-detr.cpp), a C++/ggml implementation that matches the upstream PyTorch model on CPU.
|
| 17 |
|
| 18 |
This repo contains all four standard quantizations of this variant. **F16 is the recommended default** — same accuracy as F32, 1.85× smaller, and typically the fastest on modern CPUs thanks to ggml's F32×F16 matmul fast path.
|
| 19 |
|
|
|
|
| 48 |
|
| 49 |
```bash
|
| 50 |
# 1. Clone + build rfdetr.cpp
|
| 51 |
+
git clone https://github.com/mudler/rf-detr.cpp
|
| 52 |
cd rt-detr.cpp
|
| 53 |
cmake -B build -DRFDETR_BUILD_CLI=ON && cmake --build build -j
|
| 54 |
|
|
|
|
| 67 |
|
| 68 |
All accuracy metrics are computed against the upstream PyTorch reference (rfdetr 1.7.0) on 7 COCO val2017 images at threshold 0.5. Each detection match uses greedy Hungarian-style assignment by IoU (≥ 0.5 lenient, ≥ 0.95 strict) with class equality required.
|
| 69 |
|
| 70 |
+
See [BENCHMARK.md](https://github.com/mudler/rf-detr.cpp/blob/main/BENCHMARK.md) and [`benchmarks/results/accuracy_sweep.json`](https://github.com/mudler/rf-detr.cpp/blob/main/benchmarks/results/accuracy_sweep.json) for the full sweep across all 32 (variant × quant) cells.
|
| 71 |
|
| 72 |
## License
|
| 73 |
|