Instructions to use kleinpanic93/canvas-calendar-agent-v7-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kleinpanic93/canvas-calendar-agent-v7-dpo with Transformers:

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

pipe = pipeline("text-generation", model="kleinpanic93/canvas-calendar-agent-v7-dpo")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("kleinpanic93/canvas-calendar-agent-v7-dpo")
model = AutoModelForMultimodalLM.from_pretrained("kleinpanic93/canvas-calendar-agent-v7-dpo", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kleinpanic93/canvas-calendar-agent-v7-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kleinpanic93/canvas-calendar-agent-v7-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kleinpanic93/canvas-calendar-agent-v7-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kleinpanic93/canvas-calendar-agent-v7-dpo

SGLang

How to use kleinpanic93/canvas-calendar-agent-v7-dpo 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 "kleinpanic93/canvas-calendar-agent-v7-dpo" \
    --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": "kleinpanic93/canvas-calendar-agent-v7-dpo",
		"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 "kleinpanic93/canvas-calendar-agent-v7-dpo" \
        --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": "kleinpanic93/canvas-calendar-agent-v7-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kleinpanic93/canvas-calendar-agent-v7-dpo with Docker Model Runner:
```
docker model run hf.co/kleinpanic93/canvas-calendar-agent-v7-dpo
```

Canvas Calendar Agent v7 — DPO

Fine-tuned google/gemma-4-E2B-it (2.7B params) for the Canvas Calendar Agent project. Trained with Direct Preference Optimization (Rafailov et al., 2023, arXiv:2305.18290) on top of an SFT-trained checkpoint.

Intended use

Reads a student's Canvas LMS state (assignments, courses, deadlines) and their calendar, then produces concrete, actionable scheduling plans (study blocks, exam prep, rescheduling). Speaks the native Gemma-4 tool-call format (<|tool_call>call:tool.name{args}<tool_call|>) for 18 Canvas/Calendar/Study tools.

Training procedure

Stage	Method	Data	Wall time
SFT	Full-parameter fine-tuning	181 trajectory rows from Canvas sessions	~12 min
DPO	β=0.1, sigmoid loss, frozen-snapshot reference	1,071 preference pairs labeled by Gemma-4-31B-IT-NVFP4 teacher (3-vote majority at temp=0)	9:03

DPO hyperparameters

DPOConfig(
    loss_type="sigmoid",          # original DPO loss (Rafailov §4)
    beta=0.1,                     # KL implicit coefficient
    num_train_epochs=1,
    per_device_train_batch_size=1,
    gradient_accumulation_steps=8,  # effective batch = 8
    learning_rate=5e-6,
    bf16=True,
    sync_ref_model=False,         # freeze ref at init
    precompute_ref_log_probs=True,
    optim="adamw_torch",
)

Reference policy: snapshot of policy (= SFT model) at training init, frozen via precompute_ref_log_probs=True. Mathematically equivalent to the paper's π_ref = π_SFT.

Training metrics

Metric	Final value
`train_loss`	0.2229
`rewards/accuracies`	0.9032
`rewards/margins`	5.142
`rewards/chosen`	-3.362
`rewards/rejected`	-8.504
`logps/chosen`	-238.5
`logps/rejected`	-328.9
`entropy`	1.01

Random preference accuracy is 0.5; our DPO model correctly ranks 90.3% of held-out preference pairs.

Model architecture

Base: google/gemma-4-E2B-it (2.7B params, decoder-only Transformer)
Precision: bf16 weights, full-parameter fine-tune (no LoRA / no quantization)
Context: 4,096 tokens during training, 8,192 supported at inference
Tool-call format: native Gemma-4 delimiters (<|tool_call>call:NAME{ARGS}<tool_call|>)

Hardware

NVIDIA DGX Spark (Grace-Blackwell GB10 SoC, 122 GiB unified memory, SM121, aarch64). Single GPU. Container: nvcr.io/nvidia/pytorch:25.11-py3. TRL 1.1, Transformers 4.47+, PyTorch 2.10 nightly.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "kleinpanic93/canvas-calendar-agent-v7-dpo",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("kleinpanic93/canvas-calendar-agent-v7-dpo")

messages = [
    {"role": "system", "content": "You are a Canvas calendar agent. ..."},
    {"role": "user", "content": "What assignments do I have due this week?"},
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
out = model.generate(inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(out[0][inputs.shape[1]:], skip_special_tokens=False))

The output will contain <|tool_call>...<tool_call|> delimiters that the canvas_sdk.tool_parser decodes into structured tool calls.

For end-to-end agent usage with auto-download:

pip install canvas-sdk[autodownload]
python -m canvas_sdk.demo "Plan my study schedule for next week"

Data ethics + PII handling

Training data was anonymized through a two-pass process before inclusion:

CRN scrubbing: course identifiers replaced with stable @COURSE_n tokens.
PII pass: emails, phones, professor/student names, building/room references replaced with @PROF_EMAIL/@CONTACT_EMAIL/@PHONE/@PROFn/@STUDENTn/@LOCn. spaCy NER + custom regex.

The training data is the companion dataset.

Limitations

Only trained on 1,071 preference pairs and 181 trajectory rows. Coverage of diverse Canvas course structures is limited.
All training contributors used Virginia Tech instances of Canvas LMS — generalization to other institutions is untested.
Tool-call format is Gemma-4 specific. Will not work with chat templates that don't preserve <|tool_call>...<tool_call|> delimiters.
2.7B model — qualitative reasoning ability is below larger models. The 31B-IT teacher (used for labeling) is sometimes too good at distinguishing pairs the smaller policy cannot perfectly reproduce.

Citation

If you use this model, please cite:

@article{rafailov2023dpo,
  title={Direct Preference Optimization: Your Language Model is Secretly a Reward Model},
  author={Rafailov, Rafael and Sharma, Archit and Mitchell, Eric and Ermon, Stefano and Manning, Christopher D and Finn, Chelsea},
  journal={NeurIPS},
  year={2023},
  url={https://arxiv.org/abs/2305.18290}
}