Downloads · 30 days
1.6K
26% of all-time downloads
chinese-babylm-v3
zymonody/chinese-babylm-v3
chinese-babylm-v3 is a fill-mask model from zymonody. Use it when you need the model to fill a missing word. The card lists the license as apache-2.0.
A Chinese masked language model for the NLPCC 2026 Chinese BabyLM Challenge, pretrained within the ≤102M Jieba-word data budget.
All-time downloads
6.2K
Public
Parameters
103M
410 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors410 MB · 100%
At a glance
- Task
- Fill-Mask
- License
- apache-2.0
- Model type
- deberta-v2
- Access
- Public
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026
- SHA
- d5e04ae4
Try a prompt
Model card
From the Hugging Face model README
Chinese BabyLM 2026 submission (v3)
A Chinese masked language model for the NLPCC 2026 Chinese BabyLM Challenge, pretrained within the ≤102M Jieba-word data budget.
- Architecture: DeBERTa-v2 base (12 layers, hidden 768, 12 heads), ~102M params
- Tokenizer: character-level
- Objective: masked language modeling
Methodology details will be released in the technical report after the evaluation period.
Usage
from transformers import AutoTokenizer, AutoModelForMaskedLM
tok = AutoTokenizer.from_pretrained("zymonody/chinese-babylm-v3")
model = AutoModelForMaskedLM.from_pretrained("zymonody/chinese-babylm-v3")
- Task
- Fill-Mask
- Type
- deberta-v2
- License
- apache-2.0
- Languages
- zh
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026