Working Open Llama 3B in a box

docker/README.md

@@ -24,7 +24,7 @@
 - `Dockerfile` - a single OpenBLAS and CuBLAS combined Dockerfile that automatically installs a previously downloaded model `model.bin`
  
 ## Download a Llama Model from Hugging Face
-- To download a MIT licensed Llama model run: `python3 ./hug_model.py -a vihangd -s open_llama_7b_700bt_ggml`
+- To download a MIT licensed Llama model you can run: `python3 ./hug_model.py -a vihangd -s open_llama_7b_700bt_ggml -f ggml-model-q5_1.bin`
 - To select and install a restricted license Llama model run: `python3 ./hug_model.py -a TheBloke -t llama`
 - You should now have a model in the current directory and `model.bin` symlinked to it for the subsequent Docker build and copy step. e.g.
 ```
@@ -37,9 +37,10 @@ lrwxrwxrwx 1 user user   24 May 23 18:30 model.bin -> <downloaded-model-file>q5_
 
 | Model |  Quantized size |
 |------:|----------------:|
+|    3B |            3 GB |
 |    7B |            5 GB |
 |   13B |           10 GB |
-|   30B |           25 GB |
+|   33B |           25 GB |
 |   65B |           50 GB |
 
 **Note #2:** If you want to pass or tune additional parameters, customise `./start_server.sh` before running `docker build ...`

docker/open_llama/build.sh

@@ -0,0 +1,14 @@
+#!/bin/sh
+
+MODEL="open_llama_3b"
+# Get  open_llama_3b_ggml q5_1 quantization
+python3 ./hug_model.py -a SlyEcho -s ${MODEL} -f "q5_1"
+ls -lh *.bin
+
+# Build the default OpenBLAS image
+docker build -t $MODEL .
+docker images | egrep "^(REPOSITORY|$MODEL)"
+
+echo
+echo "To start the docker container run:"
+echo "docker run -t -p 8000:8000 $MODEL"

docker/open_llama/hug_model.py

@@ -76,13 +76,15 @@ def main():
 
     # Arguments
     parser.add_argument('-v', '--version', type=int, default=0x0003,
-                        help='an integer for the version to be used')
+                        help='hexadecimal version number of ggml file')
     parser.add_argument('-a', '--author', type=str, default='TheBloke',
-                        help='an author to be filtered')
+                        help='HuggingFace author filter')
-    parser.add_argument('-t', '--tags', type=str, default='llama',
+    parser.add_argument('-t', '--tag', type=str, default='llama',
-                        help='tags for the content')
+                        help='HuggingFace tag filter')
     parser.add_argument('-s', '--search', type=str, default='',
-                        help='search term')
+                        help='HuggingFace search filter')
+    parser.add_argument('-f', '--filename', type=str, default='q5_1',
+                        help='HuggingFace model repository filename substring match')
 
     # Parse the arguments
     args = parser.parse_args()
@@ -90,7 +92,7 @@ def main():
     # Define the parameters
     params = {
         "author": args.author,
-        "tags": args.tags,
+        "tags": args.tag,
         "search": args.search
     }
 
@@ -108,11 +110,15 @@ def main():
 
         for sibling in model_info.get('siblings', []):
             rfilename = sibling.get('rfilename')
-            if rfilename and 'q5_1' in rfilename:
+            if rfilename and args.filename in rfilename:
                 model_list.append((model_id, rfilename))
 
     # Choose the model
-    if len(model_list) == 1:
+    model_list.sort(key=lambda x: x[0])
+    if len(model_list) == 0:
+        print("No models found")
+        exit(1)
+    elif len(model_list) == 1:
         model_choice = model_list[0]
     else:
         model_choice = get_user_choice(model_list)
@@ -120,13 +126,14 @@ def main():
     if model_choice is not None:
         model_id, rfilename = model_choice
         url = f"https://huggingface.co/{model_id}/resolve/main/{rfilename}"
-        download_file(url, rfilename)
+        dest = f"{model_id.replace('/', '_')}_{rfilename}"
-        _, version = check_magic_and_version(rfilename)
+        download_file(url, dest)
+        _, version = check_magic_and_version(dest)
         if version != args.version:
              print(f"Warning: Expected version {args.version}, but found different version in the file.")
     else:
         print("Error - model choice was None")
-        exit(1)
+        exit(2)
 
 if __name__ == '__main__':
     main()

docker/open_llama/start.sh

@@ -0,0 +1,28 @@
+#!/bin/sh
+
+MODEL="open_llama_3b"
+
+# Start Docker container
+docker run --cap-add SYS_RESOURCE -p 8000:8000 -t $MODEL &
+sleep 10
+echo
+docker ps | egrep "(^CONTAINER|$MODEL)"
+
+# Test the model works
+echo
+curl -X 'POST'   'http://localhost:8000/v1/completions'   -H 'accept: application/json'   -H 'Content-Type: application/json'   -d '{
+  "prompt": "\n\n### Instructions:\nWhat is the capital of France?\n\n### Response:\n",
+  "stop": [
+    "\n",
+    "###"
+  ]
+}' | grep Paris
+if [ $? -eq 0 ]
+then
+    echo
+    echo "$MODEL is working!!"
+else
+    echo
+    echo "ERROR: $MODEL not replying."
+    exit 1
+fi

docker/open_llama/start_server.sh

@@ -1,6 +1,6 @@
 #!/bin/sh
 
-# For mmap support
+# For mlock support
 ulimit -l unlimited
 
 if [ "$IMAGE" = "python:3-slim-bullseye" ]; then