llama.cpp
898aeca9 - llama : implement YaRN RoPE scaling (#2268)

Commit

1 year ago

llama : implement YaRN RoPE scaling (#2268) Co-authored-by: cebtenzzre <cebtenzzre@gmail.com> Co-authored-by: Jeffrey Quesnelle <jquesnelle@gmail.com>

References

#2268 - llama: implement YaRN RoPE scaling

Author

cebtenzzre

Parents

c43c2da8

Files15

common
- common.cpp
- common.h
convert-baichuan-hf-to-gguf.py
convert.py
examples
- finetune
  - finetune.cpp
- server
  - server.cpp
- 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

llama.cpp 898aeca9 - llama : implement YaRN RoPE scaling (#2268)

llama.cpp
898aeca9 - llama : implement YaRN RoPE scaling (#2268)