cht-llama-cpp: bump version

cht-llama-cpp/README.md

@@ -20,5 +20,5 @@ pip install virtualenv
 ## Run the compiled file
 
 ```bash
-./dist/cht-llama-cpp-mistral-1-aarch64-apple-darwin --model_path ./ml/models/mistral-7b-instruct-v0.1.Q5_0.gguf
+./dist/cht-llama-cpp-mistral-1-aarch64-apple-darwin --model-path ./ml/models/mistral-7b-instruct-v0.1.Q5_0.gguf
 ```

cht-llama-cpp/build-aarch64-apple-darwin.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 set -e
-export VERSION=1.0.0
+export VERSION=1.1.0
 
 virtualenv venv -p=${1:-3.11}
 source ./venv/bin/activate

cht-llama-cpp/build.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 set -e
-export VERSION=1.0.0
+export VERSION=1.1.0
 source "$(dirname "${BASH_SOURCE[0]}")/../utils.sh"
 
 build_cpu ghcr.io/premai-io/chat-mistral-7b-instruct-q5 mistral-7b-instruct-v0.1.Q5_0 --build-arg="MODEL_ID=mistral-7b-instruct-v0.1.Q5_0" --build-arg="MODEL_DOWNLOAD_URL=https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q5_0.gguf" ${@:1}

cht-llama-cpp/main.py

@@ -13,7 +13,7 @@
 MODEL_PATH = f"./ml/models/{os.getenv('MODEL_ID', 'mistral-7b-instruct-v0.1.Q5_0')}.gguf"
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.add_argument("--model_path", help="Path to GGUF", default=MODEL_PATH)
+    parser.add_argument("--model-path", help="Path to GGUF", default=MODEL_PATH)
     parser.add_argument("--port", help="Port to run model server on", type=int, default=8000)
     args = parser.parse_args()
     MODEL_PATH = args.model_path