Results

Populated when training completes.

What the model does

Given the airline policy (as the system prompt), the available tools, and the conversation so far, the model produces the next single tool call:

• Talk to the customer — respond_to_user(message=...) (terminal; ends the turn).
• Act / look up — get_reservation_details, book_reservation, send_certificate, … .
• Reason silently — think(thought=...).
• Escalate to a larger model — defer_to_larger_model(reason=...) on turns whose correct action depends on non-obvious policy eligibility, combining several rules, a multi-step calculation, or a genuinely ambiguous judgement call.
• Hand off to a human — transfer_to_human_agents(summary=...) for out-of-scope requests or explicit human requests (distinct from deferral, which stays automated).

Deferral vs. human transfer

defer_to_larger_model is a capability escalation: a larger, more capable model takes over the same conversation with the same tools and policy — the customer keeps being served automatically. transfer_to_human_agents is for requests outside the tools' scope or when the user asks for a person. Judging when to defer — by the absolute structure of the problem, not the model's own confidence — is the core skill this model is distilled for.

Quick Start

Using Transformers

python
Copy code
import json
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "distil-labs/distil-qwen3-1.7b-customer-support-deferral"
model = AutoModelForCausalLM.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# The full airline policy (system prompt) and the 16 tool schemas ship with the demo
# app as `job_description.json`. Wrap the policy in the distil tool-calling preamble:
TASK_DESCRIPTION = "# Airline Agent Policy\n... (see job_description.json) ..."
SYSTEM = (
    "You are a tool-calling model working on:\n"
    f"<task_description>{TASK_DESCRIPTION}</task_description>\n\n"
    "Respond to the conversation history by generating an appropriate tool call that "
    "satisfies the user request. Generate only the tool call according to the provided "
    "tool schema, do not generate anything else. Always respond with a tool call."
)
TOOLS = [ ... ]  # 16 tools from job_description.json

messages = [
    {"role": "system", "content": SYSTEM},
    {"role": "user", "content": "Can I get a refund for reservation 8JX2WO?"},
]
text = tokenizer.apply_chat_template(
    messages, tools=TOOLS, tokenize=False, add_generation_prompt=True, enable_thinking=False,
)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
# <tool_call>
# {"name": "defer_to_larger_model", "arguments": {"reason": "refund eligibility depends on fare class + travel insurance"}}
# </tool_call>

Using the Demo App

This model powers the Dual-size Customer-Support Bot demo — a terminal cascade where a local SLM handles most airline-support turns and defers hard turns to a larger, OpenAI-compatible model. See the demo repo for the orchestrator and serving setup.

Using llama.cpp

Serve a GGUF build with llama-server and query the OpenAI-compatible API at http://127.0.0.1:8000/v1:

bash
Copy code
llama-server --model distil-qwen3-1.7b-customer-support-deferral.gguf --port 8000 --jinja

Model Details

Training

Details finalized when training completes. The model is distilled with the Distil Labs platform:

1. Traces — airline customer-support conversations (tau-bench airline tool set), processed and cleaned through the distil trace-processing pipeline.
2. Deferral signal — a defer_to_larger_model tool and policy guidance, so the teacher marks genuinely-hard turns for escalation while the student learns the rest.
3. Synthetic expansion + fine-tuning — distilled onto Qwen3-1.7B with GLM-5 as teacher.

Supported Functions (16 tools)

Use Cases

• Cost-efficient customer-support assistants: a small local model handles the bulk of traffic, a larger model is invoked only on the hard minority of turns.
• Any multi-turn tool-calling task with a bounded tool catalog and a difficulty signal worth routing on.

Limitations

• English airline customer-support only; not a general-purpose tool caller.
• Deferral calibration depends on the policy and tool catalog it was trained with.
• Current weights are base Qwen3-1.7B placeholders — they do not yet follow the airline policy or defer reliably. Replace with the distilled weights for real performance.

License

Released under the Apache 2.0 license. See STUDENT_LICENSE (base model) and TEACHER_LICENSE (teacher model) for upstream terms.

Links

• Distil Labs Website
• GitHub
• Hugging Face

Citation

bibtex
Copy code
@misc{distil-qwen3-1.7b-customer-support-deferral,
  author = {Distil Labs},
  title  = {Distil-Qwen3-1.7B-Customer-Support-Deferral: A Fine-tuned SLM for Airline Support with Model Deferral},
  year   = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/distil-labs/distil-qwen3-1.7b-customer-support-deferral}
}