Instructions to use fireworks-ai/llama-3-firefunction-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fireworks-ai/llama-3-firefunction-v2 with Transformers:

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

pipe = pipeline("text-generation", model="fireworks-ai/llama-3-firefunction-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fireworks-ai/llama-3-firefunction-v2")
model = AutoModelForCausalLM.from_pretrained("fireworks-ai/llama-3-firefunction-v2", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fireworks-ai/llama-3-firefunction-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fireworks-ai/llama-3-firefunction-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fireworks-ai/llama-3-firefunction-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fireworks-ai/llama-3-firefunction-v2

SGLang

How to use fireworks-ai/llama-3-firefunction-v2 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 "fireworks-ai/llama-3-firefunction-v2" \
    --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": "fireworks-ai/llama-3-firefunction-v2",
		"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 "fireworks-ai/llama-3-firefunction-v2" \
        --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": "fireworks-ai/llama-3-firefunction-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fireworks-ai/llama-3-firefunction-v2 with Docker Model Runner:
```
docker model run hf.co/fireworks-ai/llama-3-firefunction-v2
```

raymond513 commited on Jun 18, 2024

Commit

6384fb1

verified ·

1 Parent(s): 6e3c81c

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -3

README.md CHANGED Viewed

@@ -10,13 +10,21 @@ tags:
 FireFunction is a state-of-the-art function calling model with a commercially viable license. View detailed info in our [announcement blog](https://fireworks.ai/blog/firefunction-v2-launch-post). Key info and highlights:
-🐾 Successor of the [FireFunction](https://fireworks.ai/models/fireworks/firefunction-v1) model
-📏 Signifficant quality improvements over FireFunction v1 across the broad range of metrics
 🔆 Support of parallel function calling (unlike FireFunction v1) and good instruction following
-💡 Hosted on the [Fireworks](https://fireworks.ai/models/fireworks/firefunction-v2) platform
 ## Intended Use and Limitations

 FireFunction is a state-of-the-art function calling model with a commercially viable license. View detailed info in our [announcement blog](https://fireworks.ai/blog/firefunction-v2-launch-post). Key info and highlights:
+**Comparison with other models:**
+- Competitive with GPT-4o at function-calling, scoring 0.81 vs 0.80 on a medley of public evaluations
+- Trained on Llama 3 and retains Llama 3’s conversation and instruction-following capabilities, scoring 0.84 vs Llama 3’s 0.89 on MT bench
+- Significant quality improvements over FireFunction v1 across the broad range of metrics
+**General info:**
+🐾 Successor of the [FireFunction](https://fireworks.ai/models/fireworks/firefunction-v1) model
 🔆 Support of parallel function calling (unlike FireFunction v1) and good instruction following
+💡 Hosted on the [Fireworks](https://fireworks.ai/models/fireworks/firefunction-v2) platform at < 10% of the cost of GPT 4o and 2x the speed
 ## Intended Use and Limitations