Instructions to use empower-dev/llama3-empower-functions-large-v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use empower-dev/llama3-empower-functions-large-v1.1 with Transformers:

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

pipe = pipeline("text-generation", model="empower-dev/llama3-empower-functions-large-v1.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("empower-dev/llama3-empower-functions-large-v1.1")
model = AutoModelForCausalLM.from_pretrained("empower-dev/llama3-empower-functions-large-v1.1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use empower-dev/llama3-empower-functions-large-v1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "empower-dev/llama3-empower-functions-large-v1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "empower-dev/llama3-empower-functions-large-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/empower-dev/llama3-empower-functions-large-v1.1

SGLang

How to use empower-dev/llama3-empower-functions-large-v1.1 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 "empower-dev/llama3-empower-functions-large-v1.1" \
    --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": "empower-dev/llama3-empower-functions-large-v1.1",
		"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 "empower-dev/llama3-empower-functions-large-v1.1" \
        --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": "empower-dev/llama3-empower-functions-large-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use empower-dev/llama3-empower-functions-large-v1.1 with Docker Model Runner:
```
docker model run hf.co/empower-dev/llama3-empower-functions-large-v1.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Empower Functions Model v1.1

https://github.com/empower-ai/empower-functions

Empower Functions is a family of LLMs(large language models) that offer GPT-4 level capabilities for real-world "tool using" use cases, with full compatibility support to serve as a drop-in replacement.

Key Features

Automatic tool using, able to decide when to use tools and when to converse, optimized for long conversations
Parallel call, supports calling one function multiple times, multiple functions, or a combination of both
Sequential calling, supports calling multiple functions sequentially to fulfill the user request
Streaming

Family of Models

Model	Specs	Links	Notes
llama3-empower-functions-small	128k context, based on Llama3.1 8B	model, gguf	Most cost-effective, locally runnable
llama3-empower-functions-large	128k context, based on Llama3.1 70B	model	Best accuracy

Hardware Requirement

We have tested and the family of models in following setup:

empower-functions-small: fp16 on 1xA100 40G, GGUF and 4bit GGUF on Macbook M2 Pro with 32G RAM, in minimal the 4bit GGUF version requires 7.56G RAM.
empower-functions-medium: fp16 on 2xA100 80G
empower-functions-large: fp16 on 4xA100 80G

Usage

There are three ways to use the empower-functions model. You can either directly prompt the raw model, run it locally through llama-cpp-python, or use our hosted API

Evaluation

v1.1 is the newer version trained based on meta llama3.1 with the newly updated dataset, it has achieved state-of-the-art performance on the Berkeley Function Calling leaderboard:

(captured on Sep 10, 2024)