Base model:finetune:ku-nlp/gpt... Base model:ku-nlp/gpt2-medium-... Dataset:miwa-keita/zenz-v2.5-d... Gpt2 Ja Japanese input Kana kanji conversion Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Miwa-Keita/zenz-v2.5-medium
Zenz V2.5 Medium 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)
Zenz V2.5 Medium Parameters and Internals
| LLM Name | Zenz V2.5 Medium |
| Repository 🤗 | https://huggingface.co/Miwa-Keita/zenz-v2.5-medium |
| Base Model(s) | |
| Model Size | 309.5m |
| Required VRAM | 0.6 GB |
| Updated | 2025-09-23 |
| Maintainer | Miwa-Keita |
| Model Type | gpt2 |
| Model Files | |
| Supported Languages | ja |
| Model Architecture | GPT2LMHeadModel |
| License | cc-by-sa-4.0 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | GPT2Tokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | [UNK] |
| Vocabulary Size | 6000 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu_new |
| Errors | replace |
Rank the Zenz V2.5 Medium 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124