gemma-4-E2b-it

Sleeping

gefdsv commited on Apr 5

Commit

866d36e

verified ·

1 Parent(s): 07f3dff

Update Dockerfile

Files changed (1) hide show

Dockerfile CHANGED Viewed

@@ -1,7 +1,7 @@
-FROM ghcr.io/ggml-org/llama.cpp:full-openvino
 RUN apt update && apt install wget -y
 RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF/resolve/main/gemma-4-E2B-it-Q3_K_S.gguf" -O /model.gguf
-CMD ["--server", "-m", "/model.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512", "--backend", "cpu"]

+FROM ghcr.io/ggml-org/llama.cpp:full-intel
 RUN apt update && apt install wget -y
 RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF/resolve/main/gemma-4-E2B-it-Q3_K_S.gguf" -O /model.gguf
+CMD ["--server", "-m", "/model.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "1024", "--no-mmap", "--jinja", "--flash-attn on", "--temp 1.0", "--top-p 0.95", "--top-k 64", "--reasoning-budget 1024", "-c 4096"]