Llama-3.2-3B-Instruct-Q8_0-GGUF-DEMO2

Sleeping

codebyam commited on Jul 19, 2025

Commit

ac3dadf

verified ·

1 Parent(s): 0ad26e4

Update Dockerfile

Files changed (1) hide show

Dockerfile CHANGED Viewed

@@ -38,7 +38,7 @@ RUN cd /llama.cpp/build && ./bin/llama-server --list-devices
 # Download model
 RUN mkdir -p /models && \
-    wget -O /models/model.q8_0.gguf https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-F16.gguf
 RUN pip install fastapi uvicorn openai

 # Download model
 RUN mkdir -p /models && \
+    wget -O /models/model.q8_0.gguf https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q6_K.gguf
 RUN pip install fastapi uvicorn openai