MET-D-Qwen3-4B-zh-only API & Inference Endpoint

Model Details

Base model: Qwen/Qwen3-4B
Task: for a given (situation, character description, action) triple, answer two questions from the character's perspective:
1. Is the action acceptable? (Yes / No / Ambiguous)
2. Would (not) doing it be emotionally/mentally discomforting? (Yes / No)
Training data: self-generated reasoning traces, rejection-sampled against the ground truth per character perspective, in Chinese only
Language coverage: this checkpoint is trained on Chinese only. The multilingual model and other single-language variants are also available (see Model Variants below).
License: Apache 2.0 (inherited from the base model)

How to Get Started

python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

model_id = "launch/MET-D-Qwen3-4B-zh-only"
tokenizer = AutoTokenizer.from_pretrained(model_id)
llm = LLM(model=model_id, max_model_len=16384)

situation = "..."            # the moral dilemma narrative
character = "..."            # the character description
action = "..."                # the candidate action to judge

prompt = f"""我会给你提供一个道德困境，并提供一个角色性格描述及其对应的一些问题。
第一个问题的回答应该为"是"，"否"或者"不确定"。第二个问题的回答应该为"是"或"否"。
因为你的回答会被自动分割，所以你必须严格遵守回答的格式规定。
对于全部的两个问题，你必须确保同时输出"原因："和"回答"。

道德困境:
{situation}

角色性格描述:
{character}

问题:
1. 从 A的角度来说，下面的行动——此行动已经采取、考虑被采取、可能考虑被采取、或在情境的内容中被质疑——是可接受的？"{action}"
2. 如果前者的回答为是，A 是否会因采取该行动而在情绪或精神上感觉不适？相反地，如果前者回答为否，A 是否会因为不采取该行动而在情绪或精神上感觉不适？

你的回答：
1. 原因: {{原因}} 回答: {{是/否/不确定}}
2. 原因: {{原因}} 回答: {{是/否}}
"""

chat_prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    tokenize=False,
    add_generation_prompt=True,
)

sampling_params = SamplingParams(temperature=0.0, max_tokens=2048)
outputs = llm.generate(chat_prompt, sampling_params)
print(outputs[0].outputs[0].text)

Model Variants

This checkpoint is part of the MET collection, which includes the same task across base models and language subsets:

Table with columns: Repo, Base model, Language(s)
Repo	Base model	Language(s)
`launch/MET-D-Qwen3-4B`	Qwen3-4B	all 6 (mixed)
`launch/MET-D-Qwen3-4B-en-only`	Qwen3-4B	English only
`launch/MET-D-Qwen3-4B-es-only`	Qwen3-4B	Spanish only
`launch/MET-D-Qwen3-4B-hi-only`	Qwen3-4B	Hindi only

Citation

If you use this, please cite:

bibtex
@article{lee2026met,
  title={MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning},
  author={Lee, Ayoung and Kwon, Ryan and Zhang, Yunxiang and Liu, Yuxuan and Railton, Peter and Wang, Lu},
  journal={arXiv preprint arXiv:2607.11736},
  year={2026}
}

python

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

model_id = "launch/MET-D-Qwen3-4B-zh-only"
tokenizer = AutoTokenizer.from_pretrained(model_id)
llm = LLM(model=model_id, max_model_len=16384)

situation = "..."            # the moral dilemma narrative
character = "..."            # the character description
action = "..."                # the candidate action to judge

prompt = f"""我会给你提供一个道德困境，并提供一个角色性格描述及其对应的一些问题。
第一个问题的回答应该为"是"，"否"或者"不确定"。第二个问题的回答应该为"是"或"否"。
因为你的回答会被自动分割，所以你必须严格遵守回答的格式规定。
对于全部的两个问题，你必须确保同时输出"原因："和"回答"。

道德困境:
{situation}

角色性格描述:
{character}

问题:
1. 从 A的角度来说，下面的行动——此行动已经采取、考虑被采取、可能考虑被采取、或在情境的内容中被质疑——是可接受的？"{action}"
2. 如果前者的回答为是，A 是否会因采取该行动而在情绪或精神上感觉不适？相反地，如果前者回答为否，A 是否会因为不采取该行动而在情绪或精神上感觉不适？

你的回答：
1. 原因: {{原因}} 回答: {{是/否/不确定}}
2. 原因: {{原因}} 回答: {{是/否}}
"""

chat_prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    tokenize=False,
    add_generation_prompt=True,
)

sampling_params = SamplingParams(temperature=0.0, max_tokens=2048)
outputs = llm.generate(chat_prompt, sampling_params)
print(outputs[0].outputs[0].text)

Repo

Base model

Language(s)

launch/MET-D-Qwen3-4B

Qwen3-4B

all 6 (mixed)

launch/MET-D-Qwen3-4B-en-only

Qwen3-4B

English only

launch/MET-D-Qwen3-4B-es-only

Qwen3-4B

Spanish only

launch/MET-D-Qwen3-4B-hi-only

Qwen3-4B

Hindi only

bibtex

@article{lee2026met,
  title={MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning},
  author={Lee, Ayoung and Kwon, Ryan and Zhang, Yunxiang and Liu, Yuxuan and Railton, Peter and Wang, Lu},
  journal={arXiv preprint arXiv:2607.11736},
  year={2026}
}

MET-D-Qwen3-4B-zh-only

README

Model Details

How to Get Started

Model Variants

Citation

Explore FriendliAI today

README

Model Details

How to Get Started

Model Variants

Citation