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
cae9212b70
Merge pull request #89 from LaurentMazare/extending_bert
...
Enabling `roberta` for the example (it's the same model as Bert, with just different naming.)
2023-07-06 16:29:26 +02:00
3f291bdf9d
Enabling roberta for the example (it's the same model as Bert, with
...
just different naming.)
2023-07-06 13:25:21 +02:00
dd60bd84bb
MKL adjustments. ( #87 )
2023-07-06 11:37:27 +01:00
c297a50960
Add mkl support for matrix multiply. ( #86 )
...
* Fix some rebase issues.
* Use mkl instead.
* Use mkl in bert.
* Add the optional mkl feature.
* Conditional compilation based on the mkl feature.
* Add more mkl support.
2023-07-06 11:05:05 +01:00
cd230d26fe
Whisper tweaks ( #85 )
...
* Isolate the decoding bits of the whisper example.
* Decode -> Decoder.
* Add the suppress tokens filter.
* More suppress tokens.
2023-07-06 09:13:20 +01:00
d3418f1cff
Add the original whisper names as comment.
2023-07-06 07:57:03 +01:00
19ab5ea411
Merge pull request #78 from LaurentMazare/whisper_update
...
Adapting whisper for Hub use.
2023-07-06 07:21:58 +01:00
e2bfbcb79c
Support dim indexes in cat.
2023-07-05 20:39:08 +01:00
2c3d871b2e
Add a simpler way to specify the dim index for some ops.
2023-07-05 20:22:43 +01:00
174e57d216
Use avg pooling before the cosine similarity.
2023-07-05 17:05:50 +01:00
914e84deec
Add some sentence similarity comparision to the bert example.
2023-07-05 16:49:57 +01:00
653c5049f8
Adding auto download of audio file.
2023-07-05 15:21:53 +00:00
e85573a4bd
Adapting whisper for Hub use.
2023-07-05 14:35:27 +00:00
bae6d07b7e
Fix the position embeddings size.
2023-07-05 13:43:34 +01:00
93896f6596
Merge branch 'main' into upgrade_bert
2023-07-05 13:06:33 +01:00
d560855c2a
Bugfix for the mel filters.
2023-07-05 12:56:04 +01:00
63e5a266bf
Put everything together.
2023-07-05 12:19:21 +01:00
95f378ebb4
Read wav files.
2023-07-05 11:53:58 +01:00
26d1a7803f
Load the mel filters.
2023-07-05 11:20:33 +01:00
c701ee33a7
Add the mel filters.
2023-07-05 11:05:08 +01:00
648d1511d5
PCM conversion.
2023-07-05 11:02:49 +01:00
dd1d55f5c7
Mel spectogram computation.
2023-07-05 10:49:37 +01:00
f4c8a196a8
Mel spectogram.
2023-07-05 10:14:20 +01:00
7a6bc6d2dc
Mel spectogram computation (fft bits).
2023-07-05 09:54:12 +01:00
a824c5c3e3
Populate the no-speech probability.
2023-07-05 08:54:04 +01:00
d8f75ceeaa
Some polish.
2023-07-05 07:41:14 +00:00
9694e35db0
Clean the decode loop of the whisper example.
2023-07-05 08:37:26 +01:00
963c75cb89
Adding offline mode.
2023-07-05 07:19:57 +00:00
3ba4bfc501
More pretty printing.
2023-07-05 05:50:33 +01:00
8cf803d1a3
Split the model in a separate file.
2023-07-05 05:46:53 +01:00
9fe7a42895
More whisper sampling.
2023-07-04 22:18:07 +01:00
80f25e6fbb
More decoding.
2023-07-04 21:43:20 +01:00
babf3b4065
Sketch the decode step for whisper.
2023-07-04 18:25:47 +01:00
31663bc04f
Add the causal mask in text decoding.
2023-07-04 15:25:47 +01:00
43a007cba4
Upgrading bert example to work with bert-base-uncased.
...
- Always take weights from the hub
- Optional `model_id` + `revision` to use safetensors version
potentially
- Optional loading for `bert-base-uncased` (`weight` vs `gamma`).
- Take the config from the hub.
2023-07-04 14:12:14 +00:00
459e2e1ae3
Properly handle the stride in conv1d.
2023-07-04 15:05:04 +01:00
c3739d001b
Get the audio-encoder to return some values.
2023-07-04 14:06:09 +01:00
99b83773b5
Small cleanup.
2023-07-04 13:21:59 +01:00
599160605c
Use the stored embeddings.
2023-07-04 13:13:28 +01:00
0d99b43792
Line up the textdecoder values with the python implementation.
2023-07-04 12:27:05 +01:00
aea090401d
Run the text decoding bit.
2023-07-04 12:03:28 +01:00
a424d95473
Add more of the conv1d op.
2023-07-04 11:15:45 +01:00
e6b01d0c18
Add the conv1d layer (but not the op).
2023-07-04 10:01:05 +01:00
d71b31144d
Add a weight extraction script.
2023-07-04 09:29:19 +01:00
c09aa4b0f4
Add more to the forward pass and fix the cross-attention.
2023-07-04 09:14:28 +01:00
998cfda9c4
Sinusoid embeddings.
2023-07-04 09:03:25 +01:00
6728a85676
Add more to the whisper inference.
2023-07-04 08:32:03 +01:00
512dd9e4d6
Flesh out the whisper example.
2023-07-04 08:01:06 +01:00
0ca2af6940
Add the residual attention block.
2023-07-04 07:43:36 +01:00
