 Piotr Wilkin
|
0dd6110fdc
v1.0
|
3 months ago |
|
Piotr Wilkin
|
adcbd9428f
Linear layer output convergence
|
3 months ago |
|
Piotr Wilkin
|
666fc0583d
Parity on delta!
|
3 months ago |
|
Piotr Wilkin
|
a2c7b6794e
Proper handling for n_tokens > GGML_DELTA_NET_CHUNK
|
3 months ago |
|
Piotr Wilkin
|
c1e46f62fa
Achieve pre-chunk-attention parity; remove most of the LLM generated crap
|
3 months ago |
|
Piotr Wilkin
|
c87e8d550c
Tensor preparation for delta_net complete
|
3 months ago |
|
Piotr Wilkin
|
7ec2df64a4
Added: tri, cumsum. Still a mess.
|
3 months ago |
|
Piotr Wilkin
|
6d0ad37cf4
Fix QKV extraction post-convolution
|
3 months ago |
|
Piotr Wilkin
|
845a3d7166
Convolution
|
4 months ago |
|
Piotr Wilkin
|
638057a29b
Transpose input for convolution
|
4 months ago |
|
Piotr Wilkin
|
835d389fc5
Fix BA views as well
|
4 months ago |
|
Piotr Wilkin
|
594c1f98ef
QKV splits done right
|
4 months ago |
|
Piotr Wilkin
|
dbd4d97cf2
Fix cb calls
|
4 months ago |
|
Piotr Wilkin
|
32dcee47ef
Some attempts to get the convolution input right.
|
4 months ago |
|
Piotr Wilkin
|
7bedf4c66c
Refactor llama-model.cpp
|
4 months ago |
