Instructions to use XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL with Transformers:

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

pipe = pipeline("text-generation", model="XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL")
model = AutoModelForCausalLM.from_pretrained("XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL

SGLang

How to use XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL 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 "XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL" \
    --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": "XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL",
		"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 "XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL" \
        --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": "XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL with Docker Model Runner:
```
docker model run hf.co/XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL
```

ErrOPD-Qwen3-1.7B-student-SQL

Student start (supervised fine-tuning), released with the paper ErrOPD: When Does On-Policy Distillation Transfer Teacher Errors? (Xin Li, Hao Jiang, Annan Wang, Yichi Zhang, Chau Yuen).

Code: https://github.com/LiXin97/ErrOPD · Project page: https://lixin.ai/ErrOPD · All checkpoints and datasets: ErrOPD collection

Checkpoint


Role	Student start (supervised fine-tuning)
What it is	Student fine-tuned (supervised) on clean Spider targets; the starting point of on-policy distillation.
Paper reference	Table 2 (SQL: student start)
Task	Spider 1.0 text-to-SQL: given a SQLite schema and a question, output one SQL query on a single line and nothing else
Training data	`sft_train.jsonl` of XINLI1997/ErrOPD-Spider (1,795 Spider questions, clean)
Base model	Qwen/Qwen3-1.7B
Weights	bf16 safetensors, 1 file, 3.44 GB (1.72 B stored parameters).

Usage

# pip install "transformers>=4.57.0" accelerate datasets torch
import torch
from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "XINLI1997/ErrOPD-Qwen3-1.7B-student-SQL"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")

# one held-out prompt (system + user turns) from the evaluation split
example = load_dataset("XINLI1997/ErrOPD-Spider", split="validation")[0]
messages = [m for m in example["messages"] if m["role"] != "assistant"]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
output = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))

The expected output is one SQLite query on a single line (run it against the Spider database named in metadata.db_id to check it). Prompts, decoding settings and the scoring code used in the paper are in the code repository.

Notes:

The bundled chat template is the one used for fine-tuning, distillation rollouts and evaluation in the paper.

Training

Student fine-tuned (supervised) on clean Spider targets; the starting point of on-policy distillation. Full training configurations and scripts are in the code repository.

Evaluation

This checkpoint is reported in the paper, Table 2 (SQL: student start); see that table for its scores.

Limitations

Trained for one narrow structured-output task. It is not a general assistant, and outputs for other prompts are not meaningful.
Teachers in this release were fine-tuned to make an injected format error on purpose; distilled students may inherit it. This is what the paper measures.
Evaluated on a 500-question subset of Spider dev; generated SQL should be executed in a sandbox.

License

Apache-2.0, inherited from the base model Qwen/Qwen3-1.7B (see LICENSE). The training data keep their own terms (see the dataset card of XINLI1997/ErrOPD-Spider).

Citation

@article{li2026erropd,
  title   = {ErrOPD: When Does On-Policy Distillation Transfer Teacher Errors?},
  author  = {Li, Xin and Jiang, Hao and Wang, Annan and Zhang, Yichi and Yuen, Chau},
  journal = {arXiv preprint arXiv:2605.08737},
  year    = {2026}
}