Doge 20M Chinese is an open-source language model by wubingheng. Features: 20m LLM, VRAM: 0.1GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.19.
Arxiv:2412.11834 Conversational Custom code Dataset:wubingheng/doge pt chi... Doge Endpoints compatible Pt Region:us Safetensors Tensorboard Zh
Model Card on HF 🤗: https://huggingface.co/wubingheng/Doge-20M-Chinese
Doge 20M Chinese Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Doge 20M Chinese Parameters and Internals
| LLM Name | Doge 20M Chinese |
| Repository 🤗 | https://huggingface.co/wubingheng/Doge-20M-Chinese |
| Model Size | 20m |
| Required VRAM | 0.1 GB |
| Updated | 2026-03-24 |
| Maintainer | wubingheng |
| Model Type | doge |
| Model Files | |
| Supported Languages | zh |
| Model Architecture | DogeForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 32768 |
| Torch Data Type | float32 |
Rank the Doge 20M Chinese Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52052 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b