Macbert4mdcspell V1 is an open-source language model by Macropodus. Features: LLM, VRAM: 0.4GB, Context: 0.5K, License: apache-2.0, LLM Explorer Score: 0.18.
Arxiv:2004.13922 Arxiv:2004.14166 Arxiv:2005.07421 Arxiv:2105.12306 Arxiv:2203.00991 Arxiv:2210.10996 Arxiv:2212.04068 Arxiv:2301.06323 Arxiv:2305.14783 Arxiv:2305.17721 Arxiv:2308.08796 Arxiv:2407.15498 Arxiv:2412.12863 Base model:finetune:hfl/chines... Base model:hfl/chinese-macbert... Bert Chinese-spelling-check Chinses-spelling-correct Csc Pytorch Region:us Text-correct Zh 中文拼写纠错 文本纠错
Model Card on HF 🤗: https://huggingface.co/Macropodus/macbert4mdcspell_v1
Macbert4mdcspell V1 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)
Macbert4mdcspell V1 Parameters and Internals
| LLM Name | Macbert4mdcspell V1 |
| Repository 🤗 | https://huggingface.co/Macropodus/macbert4mdcspell_v1 |
| Base Model(s) | |
| Required VRAM | 0.4 GB |
| Updated | 2025-09-23 |
| Maintainer | Macropodus |
| Model Type | bert |
| Model Files | |
| Supported Languages | zh |
| Model Architecture | BertForMaskedLM |
| License | apache-2.0 |
| Context Length | 512 |
| Model Max Length | 512 |
| Transformers Version | 4.30.2 |
| Tokenizer Class | BertTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 21128 |
Rank the Macbert4mdcspell V1 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? 52721 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 v20260328a