Hugging Face's logo

Spaces:
ngxson
/
Qwen2.5-Coder-14B-GGUF
Paused

App Files Community
ngxson HF Staff commited on
Commit
d6a2959
·
verified ·
1 Parent(s): f212354

LLAMA_ARG_N_GPU_LAYERS

Browse files
Files changed (1) hide show
  1. Dockerfile +1 -0
Dockerfile CHANGED
@@ -1,5 +1,6 @@
1
  FROM ghcr.io/ggerganov/llama.cpp:server-cuda
2
 
 
3
  ENV LLAMA_ARG_CTX_SIZE=10000
4
  ENV LLAMA_ARG_FLASH_ATTN=1
5
  ENV LLAMA_ARG_HF_REPO=bartowski/Qwen2.5-Coder-14B-GGUF
 
1
  FROM ghcr.io/ggerganov/llama.cpp:server-cuda
2
 
3
+ ENV LLAMA_ARG_N_GPU_LAYERS=9999
4
  ENV LLAMA_ARG_CTX_SIZE=10000
5
  ENV LLAMA_ARG_FLASH_ATTN=1
6
  ENV LLAMA_ARG_HF_REPO=bartowski/Qwen2.5-Coder-14B-GGUF