Flor commited on
Commit
0a3fc31
·
verified ·
1 Parent(s): 97bfe58

card: update from fastforks 1cbf1671

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -9,6 +9,7 @@ tags:
9
  - "cuda"
10
  - "pytorch"
11
  - "fastforks"
 
12
  ---
13
  # Segment Anything (SAM) (fastforks)
14
 
@@ -32,7 +33,7 @@ Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex di
32
 
33
  ## Licence
34
 
35
- Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Files: `LICENSE`.
36
 
37
  Training data: SA-1B (11M licensed images, 1.1B automatically generated masks) per the paper; the dataset itself is under the SA-1B research licence.
38
 
@@ -120,4 +121,4 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
120
 
121
  `promptable_segmentation.load("sam-vit-b", mode="kernels")` runs our CUDA kernels (`dpt_fused`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.
122
 
123
- <!-- staged from fastforks 24802779 (2026-11-15) -->
 
9
  - "cuda"
10
  - "pytorch"
11
  - "fastforks"
12
+ - "fastforks-card"
13
  ---
14
  # Segment Anything (SAM) (fastforks)
15
 
 
33
 
34
  ## Licence
35
 
36
+ Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Licence files: `LICENSE`.
37
 
38
  Training data: SA-1B (11M licensed images, 1.1B automatically generated masks) per the paper; the dataset itself is under the SA-1B research licence.
39
 
 
121
 
122
  `promptable_segmentation.load("sam-vit-b", mode="kernels")` runs our CUDA kernels (`dpt_fused`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.
123
 
124
+ <!-- staged from fastforks 1cbf1671 (2026-11-15) -->