| license: mit | |
| language: | |
| - fa | |
| - en | |
| library_name: adapter-transformers | |
| I trained Llama2-7B after extending its tokenizer by 21,455 token on about 15B farsi text(common crawl, social, papers) |
| license: mit | |
| language: | |
| - fa | |
| - en | |
| library_name: adapter-transformers | |
| I trained Llama2-7B after extending its tokenizer by 21,455 token on about 15B farsi text(common crawl, social, papers) |