refactor(model): gptj merge tokenizer

[boss-chanon]

Why this PR

refactor gpt merge tokenizer for customize tokenizer and make file for load and save to locaf tokenizer and merge file to local

Changes

• merge tokenizer get customize tokenizer
• make file for load and save to locaf tokenizer and merge file to local
• merge function will not load merge file

Related Issues

Close #

Checklist

• [ ] PR should be in the Naming convention
• [ ] Assign yourself in to Assigneees
• [ ] Tag related issues
• [ ] Constants name should be ALL_CAPITAL, function name should be snake_case, and class name should be CamelCase
• [ ] complex function/algorithm should have Docstring
• [ ] 1 PR should not have more than 200 lines changes (Exception for test files). If more than that please open multiple PRs
• [ ] At least PR reviewer must come from the task's team (model, eval, data)

[boss-chanon]

I think you should move all of tokenizers (GPTJ tokenizer in this PR) to src/model/openthaigpt_pretraining_model/tokenizers directory. How do you think?

i think we could new pr to move src/model/openthaigpt_pretraining_model/GPTJ_TH_tokenizer and src/model/openthaigpt_pretraining_model/llama_thai_tokenizer to src/model/openthaigpt_pretraining_model/tokenizers