add PLaMo model #3557
ggerganov
merged
19 commits into
ggml-org:master
from
okdshin:add_pfnet_plamo_13b
okdshin
commented
on 2023-10-09
add plamo mock
feb0966a
add tensor loading
4c585b4c
plamo convert
b2330f57
update norm
9d492365
able to compile
4a3ef4f2
fix norm_rms_eps hparam
a22040a8
runnable
86d5348f
use inp_pos
f76fd392
seems ok
ca8f6986
update kqv code
febc6359
remove develop code
907b9218
update README
9339ffc9
shuffle attn_q.weight and attn_output.weight for broadcasting
db1b18dc
remove plamo_llm_build_kqv and use llm_build_kqv
26340a19
fix style
700f7c60
Merge branch 'master' into add_pfnet_plamo_13b_2
602cc71b
update
307481f2
llama : remove obsolete KQ_scale
eedd4345
plamo : fix tensor names for correct GPU offload
1949c955
ggerganov
approved these changes
on 2023-12-24
Login to write a write a comment.
Login via GitHub