|
|
@@ -299,7 +299,7 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 2,
|
|
|
+ "execution_count": 12,
|
|
|
"metadata": {},
|
|
|
"outputs": [],
|
|
|
"source": [
|
|
|
@@ -312,119 +312,98 @@
|
|
|
"source": [
|
|
|
"#### Now we can learn about the various prompt formats available \n",
|
|
|
"\n",
|
|
|
- "When you run the cell below-you will see all the options for different template"
|
|
|
+ "When you run the cell below-you will see models available and then we can check details for model specific prompts"
|
|
|
]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 90,
|
|
|
+ "execution_count": 20,
|
|
|
"metadata": {},
|
|
|
"outputs": [
|
|
|
{
|
|
|
"name": "stdout",
|
|
|
"output_type": "stream",
|
|
|
"text": [
|
|
|
- "+-----------+---------------------------------+\n",
|
|
|
- "\u001b[1m\u001b[97m| Role | Template Name |\u001b[0m\n",
|
|
|
- "+-----------+---------------------------------+\n",
|
|
|
- "| user | user-default |\n",
|
|
|
- "| assistant | assistant-builtin-tool-call |\n",
|
|
|
- "| assistant | assistant-custom-tool-call |\n",
|
|
|
- "| assistant | assistant-default |\n",
|
|
|
- "| system | system-builtin-and-custom-tools |\n",
|
|
|
- "| system | system-builtin-tools-only |\n",
|
|
|
- "| system | system-custom-tools-only |\n",
|
|
|
- "| system | system-default |\n",
|
|
|
- "| tool | tool-success |\n",
|
|
|
- "| tool | tool-failure |\n",
|
|
|
- "+-----------+---------------------------------+\n"
|
|
|
+ "Traceback (most recent call last):\n",
|
|
|
+ " File \"/opt/miniconda3/bin/llama\", line 8, in <module>\n",
|
|
|
+ " sys.exit(main())\n",
|
|
|
+ " ^^^^^^\n",
|
|
|
+ " File \"/opt/miniconda3/lib/python3.12/site-packages/llama_toolchain/cli/llama.py\", line 44, in main\n",
|
|
|
+ " parser.run(args)\n",
|
|
|
+ " File \"/opt/miniconda3/lib/python3.12/site-packages/llama_toolchain/cli/llama.py\", line 38, in run\n",
|
|
|
+ " args.func(args)\n",
|
|
|
+ " File \"/opt/miniconda3/lib/python3.12/site-packages/llama_toolchain/cli/model/prompt_format.py\", line 59, in _run_model_template_cmd\n",
|
|
|
+ " raise argparse.ArgumentTypeError(\n",
|
|
|
+ "argparse.ArgumentTypeError: llama3_1 is not a valid Model. Choose one from --\n",
|
|
|
+ "Llama3.1-8B\n",
|
|
|
+ "Llama3.1-70B\n",
|
|
|
+ "Llama3.1-405B\n",
|
|
|
+ "Llama3.1-8B-Instruct\n",
|
|
|
+ "Llama3.1-70B-Instruct\n",
|
|
|
+ "Llama3.1-405B-Instruct\n",
|
|
|
+ "Llama3.2-1B\n",
|
|
|
+ "Llama3.2-3B\n",
|
|
|
+ "Llama3.2-1B-Instruct\n",
|
|
|
+ "Llama3.2-3B-Instruct\n",
|
|
|
+ "Llama3.2-11B-Vision\n",
|
|
|
+ "Llama3.2-90B-Vision\n",
|
|
|
+ "Llama3.2-11B-Vision-Instruct\n",
|
|
|
+ "Llama3.2-90B-Vision-Instruct\n"
|
|
|
]
|
|
|
}
|
|
|
],
|
|
|
"source": [
|
|
|
- "!llama model template"
|
|
|
- ]
|
|
|
- },
|
|
|
- {
|
|
|
- "cell_type": "markdown",
|
|
|
- "metadata": {},
|
|
|
- "source": [
|
|
|
- "## Tool Calling: Using the correct Prompt Template\n",
|
|
|
- "\n",
|
|
|
- "With `llama-cli` we can learn the correct way of defining `System_prompt` and finally get the correct behaviour from the model"
|
|
|
+ "!llama model prompt-format "
|
|
|
]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 92,
|
|
|
+ "execution_count": 21,
|
|
|
"metadata": {},
|
|
|
"outputs": [
|
|
|
{
|
|
|
"name": "stdout",
|
|
|
"output_type": "stream",
|
|
|
"text": [
|
|
|
- "+----------+--------------------------------------------------------------+\n",
|
|
|
- "| Name | \u001b[1m\u001b[97msystem-builtin-tools-only\u001b[0m |\n",
|
|
|
- "+----------+--------------------------------------------------------------+\n",
|
|
|
- "| Template | \u001b[1m\u001b[33m<|begin_of_text|>\u001b[0m\u001b[1m\u001b[33m<|start_header_id|>\u001b[0msystem\u001b[1m\u001b[33m<|end_header_id|>\u001b[0m↵ |\n",
|
|
|
- "| | ↵ |\n",
|
|
|
- "| | Environment: ipython↵ |\n",
|
|
|
- "| | Tools: brave_search, wolfram_alpha↵ |\n",
|
|
|
- "| | Cutting Knowledge Date: December 2023↵ |\n",
|
|
|
- "| | Today Date: 15 September 2024↵ |\n",
|
|
|
- "| | ↵ |\n",
|
|
|
- "| | You are a helpful assistant.↵ |\n",
|
|
|
- "| | \u001b[1m\u001b[33m<|eot_id|>\u001b[0m\u001b[1m\u001b[33m<|start_header_id|>\u001b[0massistant\u001b[1m\u001b[33m<|end_header_id|>\u001b[0m↵ |\n",
|
|
|
- "| | ↵ |\n",
|
|
|
- "| | |\n",
|
|
|
- "+----------+--------------------------------------------------------------+\n",
|
|
|
- "| Notes | ↵ represents newline |\n",
|
|
|
- "+----------+--------------------------------------------------------------+\n"
|
|
|
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[m━━━━━━━━━━━━━━━━━━━┓\u001b[m\n",
|
|
|
+ "┃ \u001b[1mLlama 3.1 - Prompt Formats\u001b[0m \u001b[m\u001b[1m\u001b[0m ┃\u001b[m\n",
|
|
|
+ "┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[m━━━━━━━━━━━━━━━━━━━┛\u001b[m\n",
|
|
|
+ "\u001b[m\n",
|
|
|
+ "\u001b[m\n",
|
|
|
+ " \u001b[1;4mTokens\u001b[0m \u001b[m\u001b[1;4m\u001b[0m \u001b[m\n",
|
|
|
+ "\u001b[m\n",
|
|
|
+ "Here is a list of special tokens that are supported by Llama 3.1: \u001b[m \u001b[m\n",
|
|
|
+ "\u001b[m\n",
|
|
|
+ "\u001b[1;33m • \u001b[0m\u001b[1;36;40m<|begin_of_text|>\u001b[0m: Specifies the start of the prompt \u001b[m\u001b[1;33m\u001b[0m\u001b[1;36;40m\u001b[0m \u001b[m\n",
|
|
|
+ "\u001b[1;33m • \u001b[0m\u001b[1;36;40m<|end_of_text|>\u001b[0m: Model will cease to generate more tokens. This token is gene\u001b[m\u001b[1;33m\u001b[0m\u001b[1;36;40m\u001b[0mrated only by the \u001b[m\n",
|
|
|
+ "\u001b[1;33m \u001b[0mbase models. \u001b[m\u001b[1;33m\u001b[0m \u001b[m\n",
|
|
|
+ "\u001b[1;33m • \u001b[0m\u001b[1;36;40m<|finetune_right_pad_id|>\u001b[0m: This token is used for padding text sequences to t\u001b[m\u001b[1;33m\u001b[0m\u001b[1;36;40m\u001b[0mhe same length in a \u001b[m\n",
|
|
|
+ "\u001b[1;33m \u001b[0mbatch. \u001b[m:\u001b[K"
|
|
|
]
|
|
|
}
|
|
|
],
|
|
|
"source": [
|
|
|
- "!llama model template --name system-builtin-tools-only"
|
|
|
+ "!llama model prompt-format -m Llama3.1-8B"
|
|
|
]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "If everything is setup correctly-the model should now wrap function calls with the `|<python_tag>|` following the actualy function call. \n",
|
|
|
- "\n",
|
|
|
- "This can allow you to manage your function calling logic accordingly. \n",
|
|
|
+ "## Tool Calling: Using the correct Prompt Template\n",
|
|
|
"\n",
|
|
|
- "Time to test the theory"
|
|
|
+ "With `llama-cli` we have already learned the right behaviour of the model"
|
|
|
]
|
|
|
},
|
|
|
{
|
|
|
- "cell_type": "code",
|
|
|
- "execution_count": 94,
|
|
|
+ "cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
- "outputs": [
|
|
|
- {
|
|
|
- "name": "stdout",
|
|
|
- "output_type": "stream",
|
|
|
- "text": [
|
|
|
- "+----------+----------------------------------------------------------------------------------+\n",
|
|
|
- "| Name | \u001b[1m\u001b[97massistant-builtin-tool-call\u001b[0m |\n",
|
|
|
- "+----------+----------------------------------------------------------------------------------+\n",
|
|
|
- "| Template | \u001b[1m\u001b[33m<|begin_of_text|>\u001b[0m\u001b[1m\u001b[33m<|start_header_id|>\u001b[0massistant\u001b[1m\u001b[33m<|end_header_id|>\u001b[0m↵ |\n",
|
|
|
- "| | ↵ |\n",
|
|
|
- "| | \u001b[1m\u001b[33m<|python_tag|>\u001b[0mbrave_search.call(query=\"Who won NBA in |\n",
|
|
|
- "| | 2024?\")\u001b[1m\u001b[33m<|eom_id|>\u001b[0m\u001b[1m\u001b[33m<|start_header_id|>\u001b[0massistant\u001b[1m\u001b[33m<|end_header_id|>\u001b[0m↵ |\n",
|
|
|
- "| | ↵ |\n",
|
|
|
- "| | |\n",
|
|
|
- "+----------+----------------------------------------------------------------------------------+\n",
|
|
|
- "| Notes | ↵ represents newline |\n",
|
|
|
- "| | Notice <|python_tag|> |\n",
|
|
|
- "+----------+----------------------------------------------------------------------------------+\n"
|
|
|
- ]
|
|
|
- }
|
|
|
- ],
|
|
|
"source": [
|
|
|
- "!llama model template --name assistant-builtin-tool-call"
|
|
|
+ "If everything is setup correctly-the model should now wrap function calls with the `|<python_tag>|` following the actualy function call. \n",
|
|
|
+ "\n",
|
|
|
+ "This can allow you to manage your function calling logic accordingly. \n",
|
|
|
+ "\n",
|
|
|
+ "Time to test the theory"
|
|
|
]
|
|
|
},
|
|
|
{
|
|
|
@@ -684,48 +663,7 @@
|
|
|
"\n",
|
|
|
"[Here](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_2#-tool-calling-(1b/3b)-) are the docs for your reference that we will be using. \n",
|
|
|
"\n",
|
|
|
- "Let's verify the details from `llama-toolchain` again and then start the prompt engineering for the small Llamas."
|
|
|
- ]
|
|
|
- },
|
|
|
- {
|
|
|
- "cell_type": "code",
|
|
|
- "execution_count": 18,
|
|
|
- "metadata": {},
|
|
|
- "outputs": [
|
|
|
- {
|
|
|
- "name": "stdout",
|
|
|
- "output_type": "stream",
|
|
|
- "text": [
|
|
|
- "Traceback (most recent call last):\n",
|
|
|
- " File \"/opt/miniconda3/bin/llama\", line 8, in <module>\n",
|
|
|
- " sys.exit(main())\n",
|
|
|
- " ^^^^^^\n",
|
|
|
- " File \"/opt/miniconda3/lib/python3.12/site-packages/llama_toolchain/cli/llama.py\", line 44, in main\n",
|
|
|
- " parser.run(args)\n",
|
|
|
- " File \"/opt/miniconda3/lib/python3.12/site-packages/llama_toolchain/cli/llama.py\", line 38, in run\n",
|
|
|
- " args.func(args)\n",
|
|
|
- " File \"/opt/miniconda3/lib/python3.12/site-packages/llama_toolchain/cli/model/prompt_format.py\", line 59, in _run_model_template_cmd\n",
|
|
|
- " raise argparse.ArgumentTypeError(\n",
|
|
|
- "argparse.ArgumentTypeError: llama3_1 is not a valid Model. Choose one from --\n",
|
|
|
- "Llama3.1-8B\n",
|
|
|
- "Llama3.1-70B\n",
|
|
|
- "Llama3.1-405B\n",
|
|
|
- "Llama3.1-8B-Instruct\n",
|
|
|
- "Llama3.1-70B-Instruct\n",
|
|
|
- "Llama3.1-405B-Instruct\n",
|
|
|
- "Llama3.2-1B\n",
|
|
|
- "Llama3.2-3B\n",
|
|
|
- "Llama3.2-1B-Instruct\n",
|
|
|
- "Llama3.2-3B-Instruct\n",
|
|
|
- "Llama3.2-11B-Vision\n",
|
|
|
- "Llama3.2-90B-Vision\n",
|
|
|
- "Llama3.2-11B-Vision-Instruct\n",
|
|
|
- "Llama3.2-90B-Vision-Instruct\n"
|
|
|
- ]
|
|
|
- }
|
|
|
- ],
|
|
|
- "source": [
|
|
|
- "!llama model prompt-format"
|
|
|
+ "Excercise for viewer: Use `llama-toolchain` again to verify like we did earlier and then start the prompt engineering for the small Llamas."
|
|
|
]
|
|
|
},
|
|
|
{
|
|
|
@@ -903,7 +841,16 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Hello Regex, my good old friend :) "
|
|
|
+ "### Handling Tool-Calling logic for the model"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "markdown",
|
|
|
+ "metadata": {},
|
|
|
+ "source": [
|
|
|
+ "Hello Regex, my good old friend :) \n",
|
|
|
+ "\n",
|
|
|
+ "With Regex, we can write a simple way to handle tool_calling and return either the model or tool call response"
|
|
|
]
|
|
|
},
|
|
|
{
|
Sanyam Bhutani