Instructions to use MMOPD/Qwen3-4B-OT3-tau2-3ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MMOPD/Qwen3-4B-OT3-tau2-3ep with Transformers:

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

pipe = pipeline("text-generation", model="MMOPD/Qwen3-4B-OT3-tau2-3ep")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MMOPD/Qwen3-4B-OT3-tau2-3ep")
model = AutoModelForCausalLM.from_pretrained("MMOPD/Qwen3-4B-OT3-tau2-3ep", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MMOPD/Qwen3-4B-OT3-tau2-3ep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MMOPD/Qwen3-4B-OT3-tau2-3ep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MMOPD/Qwen3-4B-OT3-tau2-3ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MMOPD/Qwen3-4B-OT3-tau2-3ep

SGLang

How to use MMOPD/Qwen3-4B-OT3-tau2-3ep 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 "MMOPD/Qwen3-4B-OT3-tau2-3ep" \
    --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": "MMOPD/Qwen3-4B-OT3-tau2-3ep",
		"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 "MMOPD/Qwen3-4B-OT3-tau2-3ep" \
        --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": "MMOPD/Qwen3-4B-OT3-tau2-3ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MMOPD/Qwen3-4B-OT3-tau2-3ep with Docker Model Runner:
```
docker model run hf.co/MMOPD/Qwen3-4B-OT3-tau2-3ep
```

Qwen3-4B-OT3-tau2-3ep (tool-use / τ²-bench teacher, SFT, epoch 3)

Qwen3-4B-OT3-tau2-3ep is the tool-use (τ²-bench) domain teacher of the MMOPD study: MMOPD/Qwen3-4B-OT3-2ep fine-tuned (supervised) on the agent turns of inclusionAI/AReaL-tau2-data (airline / retail / telecom customer-service dialogues with tool calls and thinking). This repository holds the epoch-3 checkpoint (step 390 of a 3-epoch run); the sibling repositories MMOPD/Qwen3-4B-OT3-tau2-{1ep,2ep,3ep} hold the other epochs of the same run.

Training


init	`MMOPD/Qwen3-4B-OT3-2ep`
data	`inclusionAI/AReaL-tau2-data` `tau2_sft_train.jsonl`: 32,758 of 33,531 single-turn rows (retail 11,395 / airline 12,320 / telecom 9,043); each row = dialogue context → the next assistant turn (thinking + reply or tool calls)
filtering	251 telecom rows whose task id is in the τ²-bench telecom `base` or `test` split were removed (evaluation contamination); 522 airline rows longer than 32,768 tokens were dropped (no truncation of system prompts)
rendering	native Qwen3 chat template with the official τ²-bench tool schemas (`Tool.openai_schema` of each domain) in the system turn; the target is the final assistant turn only: `<think>…</think>` + text, or `<think>…</think>` + `<tool_call>` block; earlier assistant turns in the context carry text + tool calls without thinking (as at inference)
recipe	SFT, 3 of 3 epochs (this checkpoint), LR 5e-6 cosine to 5e-7 (5% warmup), 32,768-token flatten packing (8,273 bins per epoch, 64 bins per optimizer step on 64 GPUs), bf16 + ZeRO-2, loss on the assistant target only; ~265M target-context tokens per epoch

Evaluation (τ²-bench telecom)

Official harness sierra-research/tau2-bench v1.0.1, telecom base split (114 tasks), 1 trial, user simulator gpt-4.1-2025-04-14 (temperature 0), agent served by vLLM 0.12 with --tool-call-parser hermes --reasoning-parser qwen3 (the stock Qwen3 parsers), temperature 1.0 / top-p 1.0 / top-k off, 32,768-token context, --max-retries 3 (no retry was needed in these runs). "Official prompt" = the harness' own LLMAgent system prompt (policy + technical-support manual); "AReaL prompt" = the shorter system prompt used in the training data, a NON-official protocol. pass^1 in %; "clean" = pass^1 on the 94 base tasks whose ids do not occur in the SFT data.

Model	prompt	pass^1	clean	terminations: user_stop / too_many_errors / max_steps
Qwen3-4B-OT3-tau2-1ep	official	43.9	39.4	77 / 31 / 6
Qwen3-4B-OT3-tau2-1ep	AReaL	24.6	25.5	45 / 67 / 2
Qwen3-4B-OT3-tau2-2ep	official	57.9	55.3	98 / 11 / 5
Qwen3-4B-OT3-tau2-2ep	AReaL	63.2	60.6	103 / 11 / 0
Qwen3-4B-OT3-tau2-3ep (this)	official	64.9	62.8	109 / 5 / 0
Qwen3-4B-OT3-tau2-3ep (this)	AReaL	63.2	58.5	103 / 11 / 0

An earlier measurement of the 1-epoch and 2-epoch checkpoints used a stricter reasoning parser that rejected agent turns emitting <think> followed directly by a tool call without </think>; every such turn raised an exception and the harness re-ran the task from scratch (--max-retries 3), so those numbers include a best-of-up-to-4 effect on format slips and are NOT comparable with the table above (official prompt / AReaL prompt):

Model	official (strict parser + retries)	AReaL (strict parser + retries)
Qwen3-4B-OT3-tau2-1ep	42.1	16.7
Qwen3-4B-OT3-tau2-2ep	71.9	60.5

Notes

Weights are stored in bfloat16 (the SFT checkpoint as saved). Apache-2.0.
The model keeps the Qwen3 thinking format. At temperature 1.0 the 1-epoch checkpoint often emits <think> immediately followed by a <tool_call> without closing the think block (the training data contains 848 turns with empty thinking); the 2- and 3-epoch checkpoints rarely do. vLLM's stock qwen3 reasoning parser passes such turns through (the tool call is executed, the stray <think> stays in the message content); a parser that requires a closed think block rejects them.
Telecom base-split scores are reported both on all 114 tasks and on the 94 tasks whose ids do not occur in the SFT data (the τ²-bench telecom task ids are deterministic subtask compositions and 20 of the 114 base tasks appear in AReaL-tau2-data; those rows were excluded from training, but the scenario texts of the full split also underlie the AReaL RL data, so the whole telecom split should be considered exposed).
Part of the MMOPD model family together with MMOPD/Qwen3-4B-OT3-{1ep,2ep}, MMOPD/Qwen3-1.7B-OT3-{1ep,2ep} and the other domain teachers MMOPD/Qwen3-4B-OT3-{medical,law,finance,if}.

How to use

Serve with vLLM and the Qwen3 tool-call / reasoning parsers, then run the official τ²-bench harness against it:

vllm serve MMOPD/Qwen3-4B-OT3-tau2-3ep --served-model-name student --max-model-len 32768 \
  --enable-auto-tool-choice --tool-call-parser hermes --reasoning-parser qwen3 --generation-config vllm
tau2 run --domain telecom --task-split-name base --agent llm_agent --user user_simulator \
  --agent-llm openai/student --agent-llm-args '{"api_base":"http://127.0.0.1:8000/v1","api_key":"EMPTY","temperature":1.0,"top_p":1.0}' \
  --user-llm gpt-4.1-2025-04-14 --user-llm-args '{"temperature":0.0}' --num-trials 1 --save-to my_run

Plain chat with tools (transformers):

from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "MMOPD/Qwen3-4B-OT3-tau2-3ep"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype="auto", device_map="auto")
tools = [{"type": "function", "function": {"name": "get_customer_by_phone", "description": "Look up a customer by phone number.",
          "parameters": {"type": "object", "properties": {"phone_number": {"type": "string"}}, "required": ["phone_number"]}}}]
messages = [{"role": "system", "content": "You are a customer service agent for a telecom company. Follow the policy."},
            {"role": "user", "content": "Hi, I can't send MMS messages since this morning. My number is 555-123-2002."}]
text = tok.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True, enable_thinking=True)
out = model.generate(**tok(text, return_tensors="pt").to(model.device), max_new_tokens=4096, do_sample=True, temperature=1.0, top_p=1.0)
print(tok.decode(out[0][tok(text, return_tensors="pt").input_ids.shape[1]:], skip_special_tokens=False))

Downloads last month: 230

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for MMOPD/Qwen3-4B-OT3-tau2-3ep

Base model

Qwen/Qwen3-4B-Base

Finetuned

MMOPD/Qwen3-4B-OT3-2ep