Instructions to use humanailabs/calendar-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use humanailabs/calendar-agent with Transformers:

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

pipe = pipeline("text-generation", model="humanailabs/calendar-agent", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("humanailabs/calendar-agent", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("humanailabs/calendar-agent", trust_remote_code=True)
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 humanailabs/calendar-agent with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/humanailabs/calendar-agent

SGLang

How to use humanailabs/calendar-agent 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 "humanailabs/calendar-agent" \
    --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": "humanailabs/calendar-agent",
		"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 "humanailabs/calendar-agent" \
        --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": "humanailabs/calendar-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use humanailabs/calendar-agent with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for humanailabs/calendar-agent to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for humanailabs/calendar-agent to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for humanailabs/calendar-agent to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="humanailabs/calendar-agent",
    max_seq_length=2048,
)

Docker Model Runner
How to use humanailabs/calendar-agent with Docker Model Runner:
```
docker model run hf.co/humanailabs/calendar-agent
```

calendar-agent (AWQ W4A16)

A fine-tuned Phi-4-mini-instruct model trained to act as a calendar scheduling assistant. This is the AWQ W4A16 quantized version (~2.7GB), optimized for efficient inference.

It parses natural language requests and returns structured JSON tool calls.

What it does

Given a natural language request and context (owner vs visitor, current datetime, timezone), the model returns one of:

tool_call — fires create_event, modify_event, delete_event, or check_availability
clarification — asks for missing required fields (one field at a time)
unsupported — rejects requests outside calendar scope

Output is always raw JSON. No markdown, no explanation.

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "humanailabs/calendar-agent"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "system", "content": "<system prompt here>"},
    {"role": "user", "content": "[Context]\nis_owner: true\ncurrent_datetime: 2026-06-25T09:00:00-07:00\nuser_timezone: America/Los_Angeles\n\n[User Request]\nSchedule a team sync tomorrow at 3pm for 30 minutes."}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
output = model.generate(inputs, max_new_tokens=128)
print(tokenizer.decode(output[0][inputs.shape[1]:], skip_special_tokens=True))
# {"type": "tool_call", "action": "create_event", "parameters": {"title": "Team sync", "start_time": "2026-06-26T15:00:00-07:00", "duration_minutes": 30}}

Quantization details

Scheme: W4A16 (4-bit weights, 16-bit activations)
Group size: 128
Tool: llmcompressor
Calibration: 512 examples
Targets: all Linear layers except lm_head

Training details

Base model: Phi-4-mini-instruct
Method: QLoRA (r=16, alpha=32) → merged to float16 → AWQ quantized
Training data: ~3700 calendar agent examples (owner/visitor scenarios, single-turn and multi-turn)
Framework: Unsloth + TRL SFTTrainer
Loss masking: Assistant responses only

Framework versions

TRL: 0.24.0
Transformers: 5.10.1
PyTorch: 2.11.0
Unsloth: latest

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

I64

I32

BF16

Model tree for humanailabs/calendar-agent

Base model

microsoft/Phi-4-mini-instruct

Finetuned

unsloth/Phi-4-mini-instruct

Quantized

(4)

this model