Arxiv:2104.09864 Autotrain compatible Endpoints compatible Gptj Ja Japanese Pytorch Region:us Sentencepiece T5tokenizer
Model Card on HF 🤗: https://huggingface.co/naclbit/gpt-j-japanese-6.8b
GPT J Japanese 6.8B 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)
GPT J Japanese 6.8B Parameters and Internals
| LLM Name | GPT J Japanese 6.8B |
| Repository 🤗 | https://huggingface.co/naclbit/gpt-j-japanese-6.8b |
| Model Size | 6.8b |
| Updated | 2025-09-30 |
| Maintainer | naclbit |
| Model Type | gptj |
| Supported Languages | ja |
| Model Architecture | GPTJForCausalLM |
| License | apache-2.0 |
| Transformers Version | 4.10.0.dev0 |
| Tokenizer Class | T5Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 52500 |
| Activation Function | gelu_new |
Rank the GPT J Japanese 6.8B 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? 51547 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124