Exqrch/Rebuttal-javanese-pixelgpt-debug
收藏Hugging Face2026-04-08 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/Exqrch/Rebuttal-javanese-pixelgpt-debug
下载链接
链接失效反馈官方服务:
资源简介:
# Javanese PixelGPT Tokenizer Ablation Dataset
Optimized with **Font Size 6** and **Dynamic Trimming**.
## Tokenizer Schema
1. `tok_grapheme`: Language-specific Grapheme BPE (izzako/javanese-llama-tokenizer)
2. `tok_llama2`: Standard Llama-2 BPE (ernie-research/DualGPT)
3. `tok_komodo`: SEA-Optimized BPE (yellow-ai-central/komodo-7b-v1)
4. `tok_mt5`: Google Multilingual Unigram (google/mt5-small)
提供机构:
Exqrch



