You can deploy this model and start earning money today!

gwenweng/
gemma

Name: gemma
Availability: InStock

safetensors

Views

No views yet

TRACE HMM Model (Gemma-2b)

This is the pre-trained Hidden Markov Model used in the TRACE (Tractable Reasoning for Adaptable Controllable gEneration) paper for controllable text generation with toxicity reduction.

Model Details

Base Model: Gemma-2b
Training Data: RealToxicityPrompts dataset
Sequence Length: 32 tokens
Hidden Size: 4096
Training Samples: 10M
Purpose: Guidance for reducing toxicity in language generation

Usage

python

from huggingface_hub import snapshot_download

# Download the model
model_path = snapshot_download(
    repo_id="gwenweng/gemma",
    local_dir="models/gemma"
)

# Use with TRACE
# See: https://github.com/yidouweng/trace

Citation

@inproceedings{weng2025trace,
  title={TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable
Language Generation},
  author={Weng, Yidou and Wang, Benjie and Van den Broeck, Guy},
  booktitle={Proceedings of the 42nd International Conference on Machine Learning
(ICML)},
  year={2025}
}

License

MIT License - see https://github.com/yidouweng/trace for details.