mlboydaisuke commited on
Commit
913ff44
·
verified ·
1 Parent(s): 87fb708

Link the card back to its collection and the request box

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -43,3 +43,13 @@ torch.export -> to_edge_transform_and_lower(partitioner) -> .pte
43
  (conversion scripts: [executorch-models](https://github.com/john-rocky/executorch-models))
44
 
45
  **Notes**: No Core ML build: RAFT's correlation volume is a rank-6 tensor and Core ML caps at rank 5. No fp16 build either — this is a conv-only model, where XNNPACK serializes convolution weights as fp32 whatever the graph dtype, so fp16 would be the same size with extra casts.
 
 
 
 
 
 
 
 
 
 
 
43
  (conversion scripts: [executorch-models](https://github.com/john-rocky/executorch-models))
44
 
45
  **Notes**: No Core ML build: RAFT's correlation volume is a rank-6 tensor and Core ML caps at rank 5. No fp16 build either — this is a conv-only model, where XNNPACK serializes convolution weights as fp32 whatever the graph dtype, so fp16 would be the same size with extra casts.
46
+
47
+ <!-- funnel:v1 -->
48
+
49
+ ---
50
+
51
+ **More models in this format:** [ExecuTorch Model Zoo](https://huggingface.co/collections/mlboydaisuke/executorch-model-zoo-6a7ff328390b63075ffeae5e) — 31 models, each with the recipe that produced it.
52
+
53
+ **Want a different model on-device?** [Open a request](https://github.com/john-rocky/on-device-requests) — free, open weights only; the export and its measured numbers get published publicly.
54
+
55
+ <!-- /funnel:v1 -->