Laurent Mazare
21109e1983
Recommend using maturin. ( #717 )
2023-09-02 16:19:35 +01:00
Laurent Mazare
ad796eb4be
More quantized llama in python. ( #716 )
...
* More quantized llama in python.
* Expose a couple more functions.
* Apply the last layer.
* Use the vocab from the ggml files.
2023-09-02 13:41:48 +01:00
Laurent Mazare
e8e33752f4
Sketch a quantized llama using the pyo3 api. ( #715 )
...
* Sketch a quantized llama using the pyo3 api.
* Add more ops.
* Expose a few more functions to use in the quantized model.
* Rope embeddings.
* Get the forward pass to work.
2023-09-02 11:26:05 +01:00
Laurent Mazare
dabaa479b9
Update README.md ( #714 )
2023-09-02 07:56:12 +01:00
Laurent Mazare
2c1df6bba1
Add a repeat penality to the llama2-c command line example. ( #713 )
...
* Add a repeat penality to the llama2-c command line example.
* Another fix attempt.
2023-09-01 20:38:58 +01:00
Laurent Mazare
4d56cef583
Handle the empty sequence case properly. ( #712 )
...
* Handle the empty sequence case properly.
* Proper fix.
2023-09-01 20:12:30 +01:00
Laurent Mazare
19042962d5
Whisper fix ( #711 )
...
* Remove unnecessary file.
* Whisper fix.
2023-09-01 20:04:07 +01:00
Laurent Mazare
731e3ffb03
Remove unnecessary file. ( #710 )
2023-09-01 19:42:23 +01:00
Laurent Mazare
2fef14cb14
Add a repeat penalty to the llama2.c wasm example. ( #709 )
2023-09-01 19:32:28 +01:00
Laurent Mazare
1e5b2cc1d5
Add some quantized functions to pyo3. ( #708 )
2023-09-01 19:45:36 +02:00
Laurent Mazare
2ed78ab336
Support for quantized tensors in the python api. ( #706 )
...
* Add more pyo3 support.
* Add some support for quantized tensors in pyo3.
* Add an arc layer on qmatmul.
* Add the quantized matmul.
* Quantization support.
* More quantization support.
* Test the python quantization.
2023-09-01 15:53:42 +01:00
Laurent Mazare
237323c2bc
Cleanup the pyo3 setup. ( #705 )
2023-09-01 14:26:18 +01:00
Laurent Mazare
af552a5274
Fix the rnn tests for accelerate. ( #704 )
2023-09-01 13:21:38 +01:00
Laurent Mazare
7529531056
Add the optimizer trait. ( #702 )
2023-09-01 12:55:39 +01:00
Laurent Mazare
f2d476ca65
Replace the discord link. ( #701 )
2023-09-01 09:43:55 +01:00
Laurent Mazare
f9f482d4e5
Add some doc to the varbuilder. ( #700 )
2023-09-01 08:28:35 +01:00
Lennard
9736236175
Allow retrieving and setting prefix of VarBuilder ( #699 )
2023-09-01 08:08:41 +01:00
Laurent Mazare
30a4b593d7
More ops again. ( #697 )
2023-08-31 22:28:48 +01:00
Laurent Mazare
949f1eae6f
Implement a couple more binary ops. ( #693 )
2023-08-31 21:30:15 +01:00
Laurent Mazare
7cef35c84d
Tweak some quantized args ( #692 )
...
* Print the args + change the default temp/repeat penalty.
* Minor formatting tweak.
2023-08-31 17:25:21 +01:00
Laurent Mazare
7509c98970
Interactive mode for the quantized model. ( #690 )
2023-08-31 10:52:42 +01:00
Laurent Mazare
94aa234dfd
Add the kv-cache to the whisper wasm version. ( #689 )
...
* Add the kv-cache to the whisper wasm version.
* Improve the handling of special tokens.
2023-08-31 09:37:44 +01:00
Laurent Mazare
db59816087
Add a GRU layer. ( #688 )
...
* Add a GRU layer.
* Fix the n gate computation.
2023-08-31 08:43:10 +01:00
Laurent Mazare
d210c71d77
Set the learning rate. ( #687 )
2023-08-31 08:03:40 +01:00
Laurent Mazare
8e84d8a59b
Llama2.c wasm module. ( #686 )
2023-08-31 07:44:32 +01:00
Radamés Ajna
9bd486fb96
Add Yolo Pose to JS Example ( #684 )
...
* add support for yolo pose models
* fix copy
2023-08-31 06:32:57 +01:00
Laurent Mazare
eaf760a751
Add a python variant for the lstm test. ( #682 )
2023-08-30 22:32:08 +01:00
Radamés Ajna
1d0bb48fae
Improve Whisper WASM UI example ( #669 )
...
* wip add module and js worker example
* params
* clean up, send error
* final UI with whisper webworker
* add simple instructions
2023-08-30 20:35:41 +02:00
Laurent Mazare
21e1c73892
Add a LSTM test. ( #681 )
...
* Add a LSTM test.
* Clippy.
2023-08-30 20:05:42 +02:00
Laurent Mazare
2047d34b7c
More robust tests (so that they pass on accelerate). ( #679 )
2023-08-30 18:10:10 +01:00
Laurent Mazare
9874d843f1
Fix the accelerate build ( #678 )
...
* Cosmetic changes.
* Fix the accelerate build for tanh.
2023-08-30 18:31:14 +02:00
Laurent Mazare
7d753d3acd
Mnist training dropout ( #677 )
...
* Use dropout in the mnist training.
* Fix.
2023-08-30 16:41:01 +01:00
Laurent Mazare
3159982a89
Add a Dropout layer ( #676 )
...
* Add a dropout layer.
* Add an actual layer.
2023-08-30 16:19:28 +01:00
Laurent Mazare
ad8a62dbf5
Add tanh. ( #675 )
...
* Add tanh.
* Use tanh in the lstm block.
* Add a test for tanh forward and backward passes.
2023-08-30 13:54:50 +01:00
Laurent Mazare
f35b9f6baa
Add some recurrent neural networks ( #674 )
...
* Add the rnn module.
* More LSTM.
* Implement the RNN forward pass.
* More forward pass for LSTM.
2023-08-30 13:27:09 +01:00
Laurent Mazare
618f4e4c78
Add some documentation. ( #673 )
...
* Add some documentation.
* Bump the crate version.
2023-08-30 11:54:00 +01:00
Laurent Mazare
5ac0a98f01
Changelog update. ( #672 )
2023-08-30 09:27:56 +01:00
Laurent Mazare
393690387f
Support dilation in conv-transpose2d. ( #671 )
2023-08-30 09:22:00 +01:00
Laurent Mazare
9b25113393
Small cleanups (avoid some possible mutations) ( #670 )
...
* More mut cleanup.
* Factor out some common bits.
2023-08-30 08:54:00 +01:00
Laurent Mazare
a1a5ab8b0a
Neon optimized vecdot ( #666 )
...
* Q5k vecdot.
* Add the q3k vecdot.
* Q2k vecdot.
* Move the quantized model to its own file.
2023-08-29 22:28:46 +01:00
Laurent Mazare
59b731de99
Add the powf op. ( #664 )
...
* Add the powf op.
* Cuda kernels and backprop.
* Add a test.
2023-08-29 20:48:18 +01:00
Laurent Mazare
2d3fcad267
Simplify usage of the pool functions. ( #662 )
...
* Simplify usage of the pool functions.
* Small tweak.
* Attempt at using apply to simplify the convnet definition.
2023-08-29 19:12:16 +01:00
Laurent Mazare
b31d41e26a
Add a convnet training example. ( #661 )
...
* Add a convnet example.
* Dataset fix.
* Randomize batches.
2023-08-29 18:23:01 +01:00
Laurent Mazare
71221559d3
Fix the dilated convolutions. ( #659 )
2023-08-29 16:37:42 +01:00
Laurent Mazare
a044907ffc
Dilated convolutions ( #657 )
...
* Add the dilation parameter.
* Restore the basic optimizer example.
* Dilation support in cudnn.
* Use the dilation parameter in the cpu backend.
* More dilation support.
* No support for dilation in transposed convolutions.
* Add dilation to a test.
* Remove a print.
* Helper function.
2023-08-29 16:12:11 +01:00
Lukas Kreussel
ee8bb1bde1
Add `avx` implemenetations of `q2k`, `q3k` and `q5k` vec-dot functions ( #654 )
...
* `q2k` avx implementation
* `q3k` avx implementation
* `q5k` avx implementation
* `avx` make masks constant
* clippy stuff
2023-08-29 13:35:56 +01:00
Nicolas Patry
3d2d3c7edb
Merge pull request #658 from huggingface/upgrade_hf_hub2
...
Upgrading hf-hub (for windows support, removing symlink requirement).
2023-08-29 14:32:15 +02:00
Nicolas Patry
1aca6fa291
Upgrading hf-hub.
2023-08-29 14:18:54 +02:00
Nicolas Patry
4ed202447e
Upgrading hf-hub.
2023-08-29 14:14:26 +02:00
Laurent Mazare
1d6bff53fc
Changelog update. ( #656 )
2023-08-29 12:55:56 +01:00