Downloads · 30 days
11
22% of all-time downloads
gemma
gwenweng/gemma
gemma is a machine learning model from gwenweng. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
--- license: mit datasets: - allenai/real-toxicity-prompts language: - en pipelinetag: text-generation tags: - controllable-generation - toxicity-reduction - hmm - language-model ---
All-time downloads
51
Public
Parameters
1.1B
4.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.3 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 2, 2025
- Updated
- Sep 2, 2025
- SHA
- 9e6b91ce
Model card
From the Hugging Face model README
license: mit datasets:
- allenai/real-toxicity-prompts language:
- en pipeline_tag: text-generation tags:
- controllable-generation
- toxicity-reduction
- hmm
- language-model
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
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.
- Created
- Sep 2, 2025
- Updated
- Sep 2, 2025