various updates across several ai/vm related systems

podman/graduated/localai/localai.md

@@ -123,15 +123,15 @@ mkdir -p $MODEL_DIR
 
 # LOCALAI_SINGLE_ACTIVE_BACKEND will unload the previous model before loading the next one
 # LOCALAI_API_KEY will set an API key, omit to run unprotected.
+# HF_TOKEN will set a login token for Hugging Face
 # Good for single-gpu systems.
 # Use the below to generate a quadlet for /etc/containers/systemd/local-ai.container
 # podman run --rm ghcr.io/containers/podlet --install --description "Local AI" \
 podman run \
 -d \
 -p 8080:8080 \
--e LOCALAI_SINGLE_ACTIVE_BACKEND=true \
--e HF_TOKEN=$(cat ~/.cache/huggingface/token) \
 -e LOCALAI_API_KEY=$(cat ~/.localai/token) \
+-e LOCALAI_SINGLE_ACTIVE_BACKEND=true \
 --device /dev/dri \
 --device /dev/kfd \
 --name local-ai \
@@ -146,12 +146,11 @@ quay.io/go-skynet/local-ai:master-hipblas-ffmpeg
 podman run \
 -d \
 -p 8081:8080 \
--e HF_TOKEN=$(cat ~/.cache/huggingface/token) \
 --name local-ai-webui \
 --network local-ai \
 -v $MODEL_DIR:/build/models \
 -v localai-tmp:/tmp/generated \
-quay.io/go-skynet/local-ai:master-ffmpeg
+quay.io/go-skynet/local-ai:master-hipblas-ffmpeg
 ```
 
 ## Running Anything LLM