Instructions to use Taxonomy-Aligned-Conversational-Tutor/TACTutor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Taxonomy-Aligned-Conversational-Tutor/TACTutor with Transformers:

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

pipe = pipeline("text-generation", model="Taxonomy-Aligned-Conversational-Tutor/TACTutor")
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("Taxonomy-Aligned-Conversational-Tutor/TACTutor")
model = AutoModelForMultimodalLM.from_pretrained("Taxonomy-Aligned-Conversational-Tutor/TACTutor", 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 Taxonomy-Aligned-Conversational-Tutor/TACTutor with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Taxonomy-Aligned-Conversational-Tutor/TACTutor

SGLang

How to use Taxonomy-Aligned-Conversational-Tutor/TACTutor 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 "Taxonomy-Aligned-Conversational-Tutor/TACTutor" \
    --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": "Taxonomy-Aligned-Conversational-Tutor/TACTutor",
		"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 "Taxonomy-Aligned-Conversational-Tutor/TACTutor" \
        --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": "Taxonomy-Aligned-Conversational-Tutor/TACTutor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Taxonomy-Aligned-Conversational-Tutor/TACTutor with Docker Model Runner:
```
docker model run hf.co/Taxonomy-Aligned-Conversational-Tutor/TACTutor
```

TACTutor

TACTutor is a 4B-parameter conversational English tutor from TACT (Taxonomy-Aligned Conversational Tutor). Starting from Qwen3.5-4B-Base, the model was post-trained with supervised fine-tuning (SFT) followed by taxonomy-aligned Group Relative Policy Optimization (GRPO). It is distributed as a merged Hugging Face Transformers model rather than a LoRA adapter.

TACT organization: https://huggingface.co/Taxonomy-Aligned-Conversational-Tutor
Demonstration samples: https://huggingface.co/datasets/Taxonomy-Aligned-Conversational-Tutor/TACTBench-Samples

Intended Use

TACTutor generates the next teacher response in an ongoing English-learning conversation. It is intended for research on pedagogically adaptive dialogue, including feedback, guided revision, clarification, and learner-supportive conversation management.

The model is a research artifact, not a replacement for a qualified teacher. Outputs should be reviewed before use in high-stakes educational settings.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Taxonomy-Aligned-Conversational-Tutor/TACTutor"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

One prompt used in our evaluation is:

You are an expert ESL tutoring teacher.

Your job is to write the next teacher response in an ongoing teacher-student chat.
Respond naturally and pedagogically. Do not explain your reasoning. Do not mention
taxonomy labels, rubrics, or evaluation criteria.

Pass this instruction as the system message, followed by the dialogue history, and use the tokenizer's chat template to construct the model input.

Evaluation

On the 78-item TACTBench diagnostic benchmark, the selected checkpoint achieved:

Metric	Score
TACT Overall	0.832051
Accept	0.871795
Leak	0.025641
Off-task	0.025641

The scores above were measured before five representative benchmark examples were released. Those public examples are demonstration data and should be excluded from future hidden-set scoring.

Training Data and Limitations

The post-training data are derived from authentic English tutoring dialogue and taxonomy-guided augmentation. The complete training corpus and hidden benchmark are not included in this repository. Five short full-context demonstration examples are available in the companion dataset repository.

The source dialogue is derived from the Teacher-Student Chatroom Corpus version 2 (TSCC v2), which is governed by its own user agreement. This model may produce incorrect, overly explicit, or contextually inappropriate tutoring responses, and its behavior outside English-language tutoring has not been established.

Citation

Please cite the following paper when using TACTutor:

@article{yang2026tact,
  title   = {TACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring},
  author  = {Yang, Dongjie and Lin, Siyan and Shen, Leixian and Sheng, Rui and Qu, Huamin and Chen, Zixin},
  year    = {2026}
}

License

The model weights are released under the Apache License 2.0. The TSCC-derived source data remain subject to the TSCC user agreement and are not redistributed with the model weights.

Downloads last month: 458

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for Taxonomy-Aligned-Conversational-Tutor/TACTutor

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

(182)

this model