4bf2ebf836
Use u8 tensors for masks. ( #273 )
2023-07-29 11:32:58 +01:00
3eb2bc6d07
Softmax numerical stability. ( #267 )
...
* Softmax numerical stability.
* Fix the flash-attn test.
2023-07-28 13:13:01 +01:00
43c7223292
Rename the .r functions to .dims so as to be a bit more explicit. ( #220 )
2023-07-22 10:39:27 +01:00
50b0946a2d
Tensor mutability ( #154 )
...
* Working towards tensor mutability.
* Use a ref-cell to provide tensor mutability.
2023-07-13 11:04:40 +01:00
eae646d322
Use arange in the examples. ( #146 )
2023-07-12 12:12:34 +01:00
674eb35e10
Remove some dead-code pragmas. ( #137 )
2023-07-11 09:33:59 +01:00
b46c28a2ac
VarBuilder path creation ( #131 )
...
* Use a struct for the safetensor+routing.
* Group the path and the var-builder together.
* Fix for the empty path case.
2023-07-10 22:37:34 +01:00
1aa7fbbc33
Move the var-builder in a central place. ( #130 )
2023-07-10 20:49:50 +01:00
b06e1a7e54
[nn] Move the Embedding and Activation parts. ( #116 )
...
* Share the Embedding and Activation parts.
* Tweak some activations.
2023-07-10 10:24:52 +01:00
9ce0f1c010
Sketch the candle-nn crate. ( #115 )
...
* Sketch the candle-nn crate.
* Tweak the cuda dependencies.
* More cuda tweaks.
2023-07-10 08:50:09 +01:00
03dffe9ecc
Use F32 for the reduce ops. ( #105 )
2023-07-07 17:55:21 +01:00
e923b3adc2
Add a KV cache to falcon. ( #104 )
2023-07-07 17:24:38 +01:00
05ff1cff66
Add some caching to the causal mask. ( #103 )
2023-07-07 12:56:44 +01:00
bac4ef40f3
Add some text generation pipeline for falcon. ( #98 )
2023-07-07 06:34:22 +01:00
2b8e8c9f14
Bugfixes. ( #97 )
2023-07-06 23:26:11 +01:00
a3f3b93d16
Add the call to dense in the attention layer. ( #96 )
2023-07-06 23:22:08 +01:00
0f679fe42e
Fix some shape issues in falcon. ( #95 )
...
* Fix some shape issues.
* Use different dtypes.
2023-07-06 19:23:54 +01:00
4afa461b34
Sketch the Falcon model. ( #93 )
...
* Sketch the Falcon model.
* Add more substance to the falcon example.
* Falcon (wip).
* Falcon (wip again).
* Falcon inference.
* Get the weights from the api and properly generate the model.
* Use the proper model.
* Fix the file/revision names.
* Fix bias handling.
* Recompute the rot embeddings.
* Fix the input shape.
* Add the release-with-debug profile.
* Silly bugfix.
* More bugfixes.
* Stricter shape checking in matmul.
2023-07-06 19:01:21 +01:00
