Fix mmap convert hf #4732
ggerganov
merged
36 commits into
ggml-org:master
from
namtranase:fix-mmap-convert-hf
update: awq support llama-7b model
2ea3934e
update: change order
8a3ceced
update: benchmark results for llama2-7b
0adf4c73
update: mistral 7b v1 benchmark
e851199a
update: support 4 models
eb9a790c
fix: Readme
576d28b7
update: ready for PR
4cad8d7d
update: readme
f97c5876
fix: readme
ef61a666
update: change order import
f8cf7839
black
1b300cbd
format code
8fece75e
update: work for bot mpt and awqmpt
8177ad4e
update: readme
d2e9d00c
Rename to llm_build_ffn_mpt_awq
0610672b
Formatted other files
c02f6df7
Fixed params count
71c0a27f
Merge branch 'github' of https://gitlab.vinai.io/mlbooster/llama.cpp …
741b7fb5
fix: remove code
e04b8f0e
update: more detail for mpt
48cd819e
fix: readme
6fcdb077
fix: readme
b00e2d90
update: change folder architecture
440cc2f4
fix: common.cpp
00f48ade
fix: readme
9b742c5a
Merge branch 'master' of https://github.com/ggerganov/llama.cpp into …
e8fae2db
fix: remove ggml_repeat
a600c61d
update: cicd
2187a8de
update: cicd
e9ad5fe0
uppdate: remove use_awq arg
13f60c41
Merge branch 'master' of https://github.com/namtranase/llama.cpp
44f4ce22
update: readme
d0898424
Merge branch 'master' into HEAD
278f3e99
llama : adapt plamo to new ffn
9174699f
Merge branch 'master' of https://github.com/ggerganov/llama.cpp
6c46cb1d
fix: update torch version
9e02214e
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub