Instructions to use cfahlgren1/natural-functions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cfahlgren1/natural-functions with Transformers:

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

pipe = pipeline("text-generation", model="cfahlgren1/natural-functions")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cfahlgren1/natural-functions")
model = AutoModelForCausalLM.from_pretrained("cfahlgren1/natural-functions")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cfahlgren1/natural-functions with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cfahlgren1/natural-functions"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cfahlgren1/natural-functions",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cfahlgren1/natural-functions

SGLang

How to use cfahlgren1/natural-functions 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 "cfahlgren1/natural-functions" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cfahlgren1/natural-functions",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cfahlgren1/natural-functions" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cfahlgren1/natural-functions",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cfahlgren1/natural-functions with Docker Model Runner:
```
docker model run hf.co/cfahlgren1/natural-functions
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

NaturalFunctions-7B

Mistral-7B finetuned for Function Calling

Examples

System Prompt

You are a helpful assistant with access to the following functions. Use them if required -

{
  "name": "create_event",
  "description": "Create a new event in the calendar",
  "parameters": {
    "type": "object",
    "properties": {
      "title": {
        "type": "string",
        "description": "The title of the event"
      },
      "date": {
        "type": "string",
        "format": "date",
        "description": "The date of the event"
      },
      "time": {
        "type": "string",
        "format": "time",
        "description": "The time of the event"
      },
      "location": {
        "type": "string",
        "description": "The location of the event (optional)"
      }
    },
    "required": [
      "title",
      "date",
      "time"
    ]
  }
}

System Prompt

You are a helpful assistant with access to the following functions. Use them if required

{
    "name": "calculate_shipping_cost",
    "description": "Calculate the shipping cost for a package",
    "parameters": {
        "type": "object",
        "properties": {
            "weight": {
                "type": "number",
                "description": "The weight of the package in kilograms"
            },
            "destination": {
                "type": "string",
                "description": "The destination address"
            }
        },
        "required": [
            "weight",
            "destination"
        ]
    }
}

Downloads last month: 12

Safetensors

Model size

7B params

Tensor type

F16

Model tree for cfahlgren1/natural-functions

Quantizations

2 models

Datasets used to train cfahlgren1/natural-functions

Spaces using cfahlgren1/natural-functions 16

Collection including cfahlgren1/natural-functions

NaturalFunctions

Collection

LLMs fine tuned for function calling 🤖 • 2 items • Updated Jan 28, 2024 • 3