Instructions to use meetkai/functionary-medium-v2.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meetkai/functionary-medium-v2.4 with Transformers:

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

pipe = pipeline("text-generation", model="meetkai/functionary-medium-v2.4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meetkai/functionary-medium-v2.4")
model = AutoModelForCausalLM.from_pretrained("meetkai/functionary-medium-v2.4")
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 meetkai/functionary-medium-v2.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meetkai/functionary-medium-v2.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meetkai/functionary-medium-v2.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meetkai/functionary-medium-v2.4

SGLang

How to use meetkai/functionary-medium-v2.4 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 "meetkai/functionary-medium-v2.4" \
    --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": "meetkai/functionary-medium-v2.4",
		"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 "meetkai/functionary-medium-v2.4" \
        --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": "meetkai/functionary-medium-v2.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meetkai/functionary-medium-v2.4 with Docker Model Runner:
```
docker model run hf.co/meetkai/functionary-medium-v2.4
```

Context Length?

by deleted - opened May 2, 2024

Discussion

deleted

May 2, 2024

Hey, just wanted to know what's the context-length of these models? Is it still 4k or does it now support 32k now with function calls?

Thanks.

flymonk

May 3, 2024

It's 32k according to config.json.

deleted

May 3, 2024

Yeah, but the last model I tried (I guess it was medium v2.2), in that after a certain context size, the model kept forgetting that it does have function access... Guess that was near around 3-4k context only.

jeffreymeetkai

May 3, 2024

Hi, the context length that we used to train v2.4 models is 8k. You can refer to here for more details about all our models.

deleted

May 3, 2024

That's cool... thanks for sharing!

deleted changed discussion status to closed May 3, 2024

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