Instructions to use fireworks-ai/firefunction-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fireworks-ai/firefunction-v1 with Transformers:

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

pipe = pipeline("text-generation", model="fireworks-ai/firefunction-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fireworks-ai/firefunction-v1")
model = AutoModelForCausalLM.from_pretrained("fireworks-ai/firefunction-v1")
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

vLLM

How to use fireworks-ai/firefunction-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fireworks-ai/firefunction-v1"
# 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/firefunction-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fireworks-ai/firefunction-v1

SGLang

How to use fireworks-ai/firefunction-v1 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/firefunction-v1" \
    --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/firefunction-v1",
		"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/firefunction-v1" \
        --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/firefunction-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fireworks-ai/firefunction-v1 with Docker Model Runner:
```
docker model run hf.co/fireworks-ai/firefunction-v1
```

firefunction-v1 / tokenizer_config.json

bchenfireworks

Update tokenizer (+ add tokenizer.json) (#1)

d193253 verified about 2 years ago

raw

history blame contribute delete

3.18 kB

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"add_prefix_space": true,
	"added_tokens_decoder": {
	"0": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32000": {
	"content": "<functioncall>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"32001": {
	"content": "<plain>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	}
	},
	"additional_special_tokens": [],
	"bos_token": "<s>",
	"chat_template": "{%- set message_roles = ['SYSTEM', 'FUNCTIONS', 'USER', 'ASSISTANT', 'TOOL'] -%}\n{%- set ns = namespace(seen_non_system=false, messages=messages, content='', functions=[]) -%}\n{{ bos_token }}\n{#- Basic consistency checks -#}\n{%- if not ns.messages -%}\n {{ raise_exception('No messages') }}\n{%- endif -%}\n{%- if ns.messages[0]['role'] \| upper != 'SYSTEM' -%}\n {%- set ns.messages = [{'role': 'SYSTEM', 'content': 'You are a helpful assistant with access to functions. Use them if required.'}] + ns.messages -%}\n{%- endif -%}\n{%- if ns.messages \| length < 2 or ns.messages[0]['role'] \| upper != 'SYSTEM' or ns.messages[1]['role'] \| upper != 'FUNCTIONS' -%}\n {{ raise_exception('Expected either \"functions\" or [\"system\", \"functions\"] as the first messages') }}\n{%- endif -%}\n{%- for message in ns.messages -%}\n {%- set role = message['role'] \| upper -%}\n {#- Validation -#}\n {%- if role not in message_roles -%}\n {{ raise_exception('Invalid role ' + message['role'] + '. Only ' + message_roles + ' are supported.') }}\n {%- endif -%}\n {%- set ns.content = message['content'] if message.get('content') else '' -%}\n {#- Move tool calls inside the content -#}\n {%- if 'tool_calls' in message -%}\n {%- for call in message['tool_calls'] -%}\n {%- set ns.content = ns.content + '<functioncall>{\"name\": \"' + call['function']['name'] + '\", \"arguments\": ' + call['function']['arguments'] + '}' -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if role == 'ASSISTANT' and '<functioncall>' not in ns.content -%}\n {%- set ns.content = '<plain>' + ns.content -%}\n {%- endif -%}\n {%- if role == 'ASSISTANT' -%}\n {%- set ns.content = ns.content + eos_token -%}\n {%- endif -%}\n {{ role }}: {{ ns.content }}{{ '\\n\\n' }}\n{%- endfor -%}\nASSISTANT:{{ ' ' }}\n",
	"clean_up_tokenization_spaces": false,
	"eos_token": "</s>",
	"legacy": false,
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<unk>",
	"sp_model_kwargs": {},
	"spaces_between_special_tokens": false,
	"tokenizer_class": "LlamaTokenizer",
	"unk_token": "<unk>",
	"use_default_system_prompt": false
	}