Flor commited on
Commit
9b50ae7
·
verified ·
1 Parent(s): 29592dc

card: update from fastforks 1cbf1671

Browse files
Files changed (1) hide show
  1. README.md +4 -3
README.md CHANGED
@@ -2,7 +2,7 @@
2
  library_name: "fastforks"
3
  pipeline_tag: "image-classification"
4
  license: "other"
5
- license_name: "bsd-3-clause-code-weights-unstated"
6
  license_link: "https://github.com/pytorch/vision/blob/1f1a920d685d46dfbe187934b785b7ecb7a182f2/LICENSE"
7
  tags:
8
  - "classification"
@@ -10,6 +10,7 @@ tags:
10
  - "cuda"
11
  - "pytorch"
12
  - "fastforks"
 
13
  ---
14
  # DenseNet (fastforks)
15
 
@@ -31,7 +32,7 @@ Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex di
31
 
32
  ## Licence
33
 
34
- Original-code strings, recorded as they are (research-use package; check them before any other use). Code: BSD-3-Clause. Files: .
35
 
36
  Code licence: BSD-3-Clause; the authors do not state a separate weights licence.
37
 
@@ -101,4 +102,4 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
101
 
102
  `classification.load("densenet121.tv_in1k", mode="kernels")` runs our CUDA kernels (`cudnn_hacc`, `fvm_conv`, `fvm_extra`, `fvm_mb`, `fvm_r3`). 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.
103
 
104
- <!-- staged from fastforks 24802779 (2026-11-15) -->
 
2
  library_name: "fastforks"
3
  pipeline_tag: "image-classification"
4
  license: "other"
5
+ license_name: "see-model-card"
6
  license_link: "https://github.com/pytorch/vision/blob/1f1a920d685d46dfbe187934b785b7ecb7a182f2/LICENSE"
7
  tags:
8
  - "classification"
 
10
  - "cuda"
11
  - "pytorch"
12
  - "fastforks"
13
+ - "fastforks-card"
14
  ---
15
  # DenseNet (fastforks)
16
 
 
32
 
33
  ## Licence
34
 
35
+ Original-code strings, recorded as they are (research-use package; check them before any other use). Code: BSD-3-Clause.
36
 
37
  Code licence: BSD-3-Clause; the authors do not state a separate weights licence.
38
 
 
102
 
103
  `classification.load("densenet121.tv_in1k", mode="kernels")` runs our CUDA kernels (`cudnn_hacc`, `fvm_conv`, `fvm_extra`, `fvm_mb`, `fvm_r3`). 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.
104
 
105
+ <!-- staged from fastforks 1cbf1671 (2026-11-15) -->