Updating to New, Better Quantized Model

Trial and error, here's another trial! Think that this one is going to go off w/o a hitch. If it doesn't, then the issue is a memory-related problem, not lack of resource. But the model should be able to spin this up w/o too much issue.

Dockerfile

@@ -15,7 +15,7 @@ RUN pip install -U pip setuptools wheel && \
 
 # Download model
 RUN mkdir model && \
-    curl -L https://huggingface.co/TheBloke/CodeBooga-34B-v0.1-GGUF/resolve/main/codebooga-34b-v0.1.Q2_K.gguf -o model/gguf-model.bin
+    curl -L https://huggingface.co/TheBloke/CodeBooga-34B-v0.1-GGUF/resolve/main/codebooga-34b-v0.1.Q6_K.gguf -o model/gguf-model.bin
 
 COPY ./start_server.sh ./
 COPY ./main.py ./