llama.cpp
Add llama 3.1 rope scaling factors to llama conversion and inference
#8676
Merged
Merged
Add llama 3.1 rope scaling factors to llama conversion and inference #8676
ggerganov
merged
6 commits into
ggml-org:master
from
jmorganca:master
jmorganca
commented
on 2024-07-24
Galunid
commented
on 2024-07-24
jxy
commented
on 2024-07-24
compilade
commented
on 2024-07-25
compilade
commented
on 2024-07-25
bartowski1182
commented
on 2024-07-26
compilade
commented
on 2024-07-26
Add llama 3.1 rope scaling factors to llama conversion and inference
e6bacb40
Update convert_hf_to_gguf.py
24540dd2
address comments
1a3a1b6d
address comments
90fd87df
compilade
commented
on 2024-07-26
Update src/llama.cpp
e6d5bed7
Update convert_hf_to_gguf.py
658041d1
Reviewers
Assignees
No one assigned
Labels
Nvidia GPU
python
Milestone
No milestone
Login to write a write a comment.
Login via GitHub