Triangle104/Arch-Function-3B-Q4_K_S-GGUF

This model was converted to GGUF format from katanemo/Arch-Function-3B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

Model details:

The Katanemo Arch-Function collection of large language models (LLMs) is a collection state-of-the-art (SOTA) LLMs specifically designed for function calling tasks. The models are designed to understand complex function signatures, identify required parameters, and produce accurate function call outputs based on natural language prompts. Achieving performance on par with GPT-4, these models set a new benchmark in the domain of function-oriented tasks, making them suitable for scenarios where automated API interaction and function execution is crucial.

In summary, the Katanemo Arch-Function collection demonstrates:

State-of-the-art performance in function calling
Accurate parameter identification and suggestion, even in ambiguous or incomplete inputs
High generalization across multiple function calling use cases, from API interactions to automated backend tasks.
Optimized low-latency, high-throughput performance, making it suitable for real-time, production environments.

Arch-Function is the core LLM used in then open source Arch Gateway to seamlessly integrate user prompts with developers APIs Key Features Functionality Definition Single Function Calling Call only one function per user query Parallel Function Calling Call the same function multiple times but with different set of parameter values Multiple Function Calling Call different functions per user query Parallel & Multiple Perform both parallel and multiple function calling Training Details

Katanemo Arch-Function collection is built on top of the Qwen 2.5. A blog with technical details leading to our models will be published soon. Performance Benchmarks

We evaluate Katanemo Arch-Function series on the Berkeley Function-Calling Leaderboard (BFCL). For each model family, we select the one with the highest rank. The results are shwon below: Rank Model Overall Single Turn Multi Turn Hallucination Non-live (AST) Non-live (Exec) Live (AST) Overall Relevance Irrelevance 1 GPT-4-turbo-2024-04-09 59.49% 82.65% 83.80% 73.39% 21.62% 70.73% 79.79% 3 xLAM-8x22b-r 59.13% 89.75% 89.32% 72.81% 15.62% 97.56% 75.23% Arch-Function-7B 57.48% 87.50% 86.80% 72.19% 13.75% 82.93% 79.54% Arch-Function-3B 56.23% 85.10% 89.16% 70.72% 12.28% 90.24% 73.98% 7 mistral-large-2407 55.82% 84.12% 83.09% 67.17% 20.50% 78.05% 48.93% 9 Claude-3.5-Sonnet-20240620 54.83% 70.35% 66.34% 71.39% 23.5% 63.41% 75.91% Arch-Function-1.5B 53.61% 82.60% 87.36% 68.19% 8.62% 87.80% 75.90% 11 o1-mini-2024-09-12 53.43% 75.48% 76.86% 71.17% 11.00% 46.34% 88.07% 12 Gemini-1.5-Flash-Preview-0514 53.01% 77.10% 71.23% 71.17% 13.12% 60.98% 76.15% Requirements

The code of Arch-Function-3B has been in the Hugging Face transformers library and we advise you to install latest version:

pip install transformers>=4.37.0

How to use

We use the following example to illustrate how to use our model to perform function calling tasks. Please note that, our model works best with our provided prompt format. It allows us to extract JSON output that is similar to the function-calling mode of ChatGPT. Single Turn Example

import json from typing import Any, Dict, List from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "katanemo/Arch-Function-3B" model = AutoModelForCausalLM.from_pretrained( model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True ) tokenizer = AutoTokenizer.from_pretrained(model_name)

Please use our provided prompt for best performance

TASK_PROMPT = """ You are a helpful assistant. """.strip()

TOOL_PROMPT = """

Tools

You may call one or more functions to assist with the user query.

You are provided with function signatures within XML tags: {tool_text} """.strip()

FORMAT_PROMPT = """ For each function call, return a json object with function name and arguments within XML tags: {"name": , "arguments": } """.strip()

Define available tools

get_weather_api = { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a location", "parameters": { "type": "object", "properties": { "location": { "type": "str", "description": "The city and state, e.g. San Francisco, New York", }, "unit": { "type": "str", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return", }, }, "required": ["location"], }, }, }

openai_format_tools = [get_weather_api]

def convert_tools(tools: List[Dict[str, Any]]): return "\n".join([json.dumps(tool) for tool in tools])

Helper function to create the system prompt for our model

def format_prompt(tools: List[Dict[str, Any]]): tool_text = convert_tools(tools)

return (
    TASK_PROMPT
    + "\n\n"
    + TOOL_PROMPT.format(tool_text=tool_text)
    + "\n\n"
    + FORMAT_PROMPT
    + "\n"
)

system_prompt = format_prompt(openai_format_tools)

messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": "What is the weather in Seattle?"}, ]

inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device)

outputs = model.generate( inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, )

response = tokenizer.decode(outputs[0][len(inputs[0]) :], skip_special_tokens=True) print(response)

Then you should be able to see the following output string in JSON format:

{"name": "get_weather", "arguments": {"location": "Seattle"}}

Multi Turn Example

Upon getting results from functions, you can add it to the messages list as a user message and pass it to the model to get responses for users.

Suppose we receive the following result from the function:

get_weather_api_result = {'name': 'get_weather', 'results': {'temperature': '62°', 'unit': 'fahrenheit'}} execution_results = [get_weather_api_result]

def add_execution_results(messages: List[Dict[str, Any]], execution_results: List[Dict[str, Any]]): content = "\n".join([f"\n{json.dumps(result)}" for result in execution_results]) messages.append({"role": "user", "content": content}) return messages

messages = add_execution_results(messages, execution_results)

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)

outputs = model.generate( inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, )

response = tokenizer.decode(outputs[0][len(inputs[0]) :], skip_special_tokens=True) print(response)

Then you should be able to see the following output:

The current temperature in Seattle is 62 degrees in Fahrenheit.

License

Katanemo Arch-Function collection is distributed under the Katanemo license.

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Arch-Function-3B-Q4_K_S-GGUF --hf-file arch-function-3b-q4_k_s.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Arch-Function-3B-Q4_K_S-GGUF --hf-file arch-function-3b-q4_k_s.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Triangle104/Arch-Function-3B-Q4_K_S-GGUF --hf-file arch-function-3b-q4_k_s.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Arch-Function-3B-Q4_K_S-GGUF --hf-file arch-function-3b-q4_k_s.gguf -c 2048