 Guillaume Wenzek
|
6fbb465f2b
generate_sequence return full results
|
2 years ago |
|
Guillaume Wenzek
|
1756897d23
simplify _finalize_hypothesis
|
2 years ago |
|
Guillaume Wenzek
|
f49763de86
fix beam size and scores
|
2 years ago |
|
Guillaume Wenzek
|
184c1e1da3
};
|
2 years ago |
|
Guillaume Wenzek
|
c28db8c8ac
wip beam-size=2
|
2 years ago |
|
Guillaume Wenzek
|
3d69d4975f
batching -> StandardTransformerDecoder
|
2 years ago |
|
Guillaume Wenzek
|
b24dbe3030
batching -> TransformerEmbeddingFrontend_forward
|
2 years ago |
|
Guillaume Wenzek
|
b3e6d3c0c7
test_flatten
|
2 years ago |
|
Guillaume Wenzek
|
86993cbd00
fix StandardTransformerEncoder
|
2 years ago |
|
Guillaume Wenzek
|
28ed039370
fix MultiheadAttention_forward
|
2 years ago |
|
Guillaume Wenzek
|
b7b31a3978
rm python 3.11 idiom
|
2 years ago |
|
Guillaume Wenzek
|
81cdf80eb9
WIP: MultiheadAttention_forward
|
2 years ago |
|
Guillaume Wenzek
|
f2b5007277
start testing with batch size > 1
|
2 years ago |
|
Guillaume Wenzek
|
eb80195345
use ggml_diag_mask_inf
|
2 years ago |
|
Guillaume Wenzek
|
f7d2c90ceb
_almost_contiguous
|
2 years ago |
|
Guillaume Wenzek
|
88b0690a72
split tests files
|
2 years ago |
|
Guillaume Wenzek
|
bfbafd9603
fix generation with beam_size=1
|
2 years ago |
|
Guillaume Wenzek
|
45f986055a
add naive tweaking of lprobs
|
2 years ago |
|
Guillaume Wenzek
|
7c9b2a1b95
pass correct prefix sequence in test
|
2 years ago |
|
Guillaume Wenzek
|
c7b89f32f4
disable flash attn because of cross attention
|
2 years ago |
|
Guillaume Wenzek
|
bf9b2510df
missing file
|
2 years ago |
|
Guillaume Wenzek
|
dcb9535666
wip: generate_sequence
|
2 years ago |
|
Guillaume Wenzek
|
78e7c9a311
fix TransformerEmbeddingFrontend
|
2 years ago |
|
Guillaume Wenzek
|
2238cea072
SinusoidalPositionEncoder + WIP: TransformerEmbeddingFrontend
|
2 years ago |
|
Guillaume Wenzek
|
2fb09f34fb
generate fairseq2.cpp
|
2 years ago |
|
Guillaume Wenzek
|
f1f33dbec1
has_layer + transformer decoder
|
2 years ago |
|
Guillaume Wenzek
|
9b157d0384
allclose
|
2 years ago |
|
Guillaume Wenzek
|
e1faba0c5d
text encoder
|
2 years ago |
|
Guillaume Wenzek
|
b81061704c
StandardTransformerEncoderLayer_forward
|
2 years ago |
|
Guillaume Wenzek
|
e7c3b7a4ba
allow flash attn
|
2 years ago |
