the-tokenizer-v1.5 / special_tokens_map.json
eliebak's picture
eliebak HF staff
Upload tokenizer
4ab427c verified
{
"additional_special_tokens": [
"<|endoftext|>",
"<|im_start|>",
"<|im_end|>",
"<fim_suffix>",
"<fim_pad>",
"<repo_name>",
"<file_sep>",
"<issue_start>",
"<issue_comment>",
"<issue_closed>",
"<jupyter_start>",
"<jupyter_text>",
"<jupyter_code>",
"<jupyter_output>",
"<jupyter_script>",
"<empty_output>",
"<code_to_intermediate>",
"<intermediate_to_code>",
"<pr>",
"<pr_status>",
"<repo_name>",
"<pr_is_merged>",
"<pr_file>",
"<pr_base_code>",
"<pr_diff>",
"<pr_diff_hunk>",
"<pr_comment>",
"<pr_event_id>",
"<pr_review>",
"<pr_review_state>",
"<pr_review_comment>",
"<pr_in_reply_to_review_id>",
"<pr_in_reply_to_comment_id>",
"<pr_diff_hunk_comment_line>"
],
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}