]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : implement YaRN RoPE scaling (#2268)
authorcebtenzzre <redacted>
Wed, 1 Nov 2023 22:04:33 +0000 (18:04 -0400)
committerGitHub <redacted>
Wed, 1 Nov 2023 22:04:33 +0000 (18:04 -0400)
commit898aeca90a9bb992f506234cf3b8b7f7fa28a1df
tree125f8a9b466efd4534ecd3e64419ece001c86a7d
parentc43c2da8afacaddfe51c09b21dbd9922cd0ea46b
llama : implement YaRN RoPE scaling (#2268)

Co-authored-by: cebtenzzre <redacted>
Co-authored-by: Jeffrey Quesnelle <redacted>
15 files changed:
common/common.cpp
common/common.h
convert-baichuan-hf-to-gguf.py
convert.py
examples/finetune/finetune.cpp
examples/server/server.cpp
examples/train-text-from-scratch/train-text-from-scratch.cpp
ggml-cuda.cu
ggml-metal.m
ggml-metal.metal
ggml.c
ggml.h
gguf-py/gguf/gguf.py
llama.cpp
llama.h