Downloads · 30 days
69
19% of all-time downloads
dalle-mini-js
rocca/dalle-mini-js
dalle-mini-js is a machine learning model from rocca. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Working tflite conversion in this notebook. Note that the encoder and decoder need to be converted separately for some reason. More info on this bug.
All-time downloads
359
Public
Repo size
5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tflite3.4 GB · 68%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 29, 2022
- Updated
- Jul 2, 2022
- SHA
- b1d5519e
Model card
From the Hugging Face model README
DALL-E Mini Running in the Browser (work in progress)
Notes:
- Working tflite conversion in this notebook.
- Note that the encoder and decoder need to be converted separately for some reason. More info on this bug.
- But these models currently require TF Select operators due to bitwise operations that aren't supported in the default tflite opset. This issue tracks the potential inclusion of TF Select ops in tfjs-tflite, so models like this can be used on the web.
- The encoder requires the TF Select
Erfop. The decoder requires these TF Select ops:Bitcast,BitwiseOr,BitwiseXor,ConcatV2,Erf,LeftShift,RightShift,ScatterNd,SelectV2,StridedSlice - Here are the two models:
- ONNX conversion is blocked on support for
Bitcast,BitwiseOrandBitwiseXor: https://github.com/onnx/tensorflow-onnx/issues/1985 The need for theBitwiseAndop can be avoided by pullingjax.random.PRNGKeyoutside of the encode-decode function, but I'm not sure where the other ops are coming from - netron doesn't seem to "expand" certain types of nodes, so I think they're hidden within some other nodes. - TF.js conversion is blocked on lack of support for these ops:
BitwiseXor,Bitcast,LeftShift,BitwiseOr,RightShift(relevant issue)
- License
- mit
- Created
- Jun 29, 2022
- Updated
- Jul 2, 2022