How to use from
Docker Model Runner
docker model run hf.co/UEC-InabaLab/CounselTrajLM-Qwen3-8B
Quick Links

CounselTrajLM โ€” Qwen3-8B

๐Ÿ“„ Paper: arXiv:2611.24168

CounselTrajLM generates the next Chinese counselor response from a counseling dialogue history. This version is fine-tuned on CounselTrajD, using Qwen3-8B as its base.

The repository contains the complete merged BF16 model, in nine safetensors shards totaling approximately 16.4 GB, together with its tokenizer, chat template, inference script, and checksums. It loads directly with Transformers. Inference uses non-thinking mode (enable_thinking=False).

This response-generation model is separate from the CounselTraj trajectory planner. Project, dataset, and evaluation prompts are available in the CounselTraj repository.

Training details

Item Value
Base model Qwen/Qwen3-8B
Base revision b968826d9c46dd6066d109eabc6255188de91218
Training data CounselTrajD; dialogue-disjoint 90/10 train/validation split
Training / validation examples 425,679 / 47,528 next-response examples
Fine-tuning method QLoRA; adapter merged into the unquantized BF16 base for release
LoRA rank / alpha / dropout 32 / 64 / 0.05
Learning rate 0.0002
Schedule / warmup ratio Cosine / 0.06
Epochs 3; final-epoch export
Final optimizer step 79,815
Effective batch size 16
Maximum training sequence length 2,048 tokens
Maximum history length Last 1,800 characters
Thinking mode Disabled
Release format Complete merged BF16 safetensors

Validation was used for monitoring. The released model is the final epoch. See training_summary.json for the recorded settings.

Generate a reply

Download the public model repository and install the inference dependencies:

pip install huggingface_hub
python -c 'from huggingface_hub import snapshot_download; snapshot_download("UEC-InabaLab/CounselTrajLM-Qwen3-8B", local_dir="CounselTrajLM-Qwen3-8B")'
cd CounselTrajLM-Qwen3-8B
pip install -r requirements.txt
python generate_reply.py --model . --input-file examples/histories.jsonl

Or provide a history directly:

python generate_reply.py --model . --history 'client:ๆœ€่ฟ‘ๅทฅไฝœๅŽ‹ๅŠ›ๅพˆๅคง๏ผŒๆ™šไธŠๆ€ปๆ˜ฏ็กไธๅฅฝใ€‚'

Input JSONL rows contain an optional id and a nonempty history string. Use client: and counselor: speaker prefixes within the history. The script uses the original counselor system instruction and training prompt format, retaining the last 1,800 history characters. It outputs JSON with the generated response. The three bundled histories are newly written synthetic examples.

After downloading the repository, it can also be used from Python:

from generate_reply import load_model, generate_reply

tokenizer, model = load_model("UEC-InabaLab/CounselTrajLM-Qwen3-8B")
response = generate_reply(
    tokenizer, model,
    "client:ๆœ€่ฟ‘ๅทฅไฝœๅŽ‹ๅŠ›ๅพˆๅคง๏ผŒๆ™šไธŠๆ€ปๆ˜ฏ็กไธๅฅฝใ€‚",
)
print(response)

The complete weights load in BF16, with additional memory required for inference. A separate base-model download or PEFT adapter loading is not required. The release was checked with Transformers 5.13.0, PyTorch 2.5.1, Accelerate 1.13.0, and safetensors 0.8.0. The GPU generation checks and integrity results are recorded in validation.json; file checksums are in SHA256SUMS.

Training data and references

CounselTrajD contains 10,964 synthetic Chinese counseling dialogues expanded from three sources:

  • SmileChat: Qiu et al. (2024), SMILE.
  • PsyDTCorpus: Xie et al. (2025), PsyDT.
  • CPsyCounD: Zhang et al. (2024), CPsyCoun.

See the project's licensing scope and source notices for the source-specific data terms. The model is released under Apache-2.0; see LICENSE.

Intended use and limitations

The model is intended for research on Chinese counseling dialogue generation. Its training data are synthetic. Generated responses may be inaccurate, inappropriate, or unsafe, and the model is not a substitute for professional mental health care.

Citation

@inproceedings{qi-inaba-2027-counseltraj,
    title = "{CounselTraj}: Synthesizing Process-Aware Psychological Counseling Dialogues via Dialogue-Act Trajectory Planning",
    author = "Qi, Zhiyang and Inaba, Michimasa",
    booktitle = "Proceedings of the 20th Conference of the European Chapter of the Association for Computational Linguistics",
    year = "2027",
    url = "https://arxiv.org/abs/2611.24168",
}
Downloads last month
4
Safetensors
Model size
8B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for UEC-InabaLab/CounselTrajLM-Qwen3-8B

Finetuned
Qwen/Qwen3-8B
Finetuned
(2,345)
this model

Paper for UEC-InabaLab/CounselTrajLM-Qwen3-8B