Instructions to use katanemo/Arch-Function-Chat-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use katanemo/Arch-Function-Chat-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="katanemo/Arch-Function-Chat-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("katanemo/Arch-Function-Chat-7B")
model = AutoModelForCausalLM.from_pretrained("katanemo/Arch-Function-Chat-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use katanemo/Arch-Function-Chat-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "katanemo/Arch-Function-Chat-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "katanemo/Arch-Function-Chat-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/katanemo/Arch-Function-Chat-7B

SGLang

How to use katanemo/Arch-Function-Chat-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "katanemo/Arch-Function-Chat-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "katanemo/Arch-Function-Chat-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "katanemo/Arch-Function-Chat-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "katanemo/Arch-Function-Chat-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use katanemo/Arch-Function-Chat-7B with Docker Model Runner:
```
docker model run hf.co/katanemo/Arch-Function-Chat-7B
```

Using Arch-Function-Chat with Llama.cpp

by mosix11 - opened Apr 13, 2025

Discussion

mosix11

Apr 13, 2025

Hi,
Could you please tell me what is the proper way of using this model with llama.cpp?
The chat template defined in the tokenizer_config.json is the default qwen-2.5 chat template and this is the chat template that is used with the GGUF files loaded by llama.cpp. However in the example in the model card, it seems the system prompt is formatted differently from what is standard to qwen-2.5. So, should I use the default chat template generated by llama.cpp (based on the qwen-2.5 chat template) or I have to use the format in the model card? Since if I pass the tool descriptions to the chat completion api of llama.cpp, it would format them using the chat template which is different from what is used in the model card.
Also could you please tell me how multi-turn conversations should be constructed? I want to use the model in a conversation scenario where the tool responses should be sent back to the model to generate proper responses. As I see in the qwen chat template, there is a role called tool which we have to use to specify the tool responses, is it also the way the this model works?

parachas

Katanemo org Apr 13, 2025

@nehcgs can you please assist on this one.

nehcgs

Katanemo org Apr 14, 2025

For llama.cpp, you don't have to change anything, simply use the same chat template. If you want to use this model for function calling, make sure you include a system message in the format we provided (see usage for more detail). To construct multi-turn conversations, you can simply use that chat template as well. Nothing needs to be changed. The role tool will work.

nehcgs changed discussion status to closed May 12, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment