Files
turkish-gpt2-medium-350m-in…/tokenizer_config.json
ModelHub XC 049f816aed 初始化项目,由ModelHub XC社区提供模型
Model: ytu-ce-cosmos/turkish-gpt2-medium-350m-instruct-v0.1
Source: Original Platform
2026-08-08 02:43:17 +08:00

32 lines
1.2 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "<|stop|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|endoftext|>",
"chat_template": "{% set message_count = messages|length %}{% if message_count >= 4 and messages[-4].role == 'user' %}{% set recent_messages = messages[-4:] %}{% elif message_count > 3 %}{% set recent_messages = messages[-3:] %}{% else %}{% set recent_messages = messages %}{% endif %}{% for message in recent_messages %}{% if message.role == 'user' %}### Kullanıcı:\n{{ message.content }}\n{% elif message.role == 'assistant' %}### Asistan:\n{{ message.content }}\n{% endif %}{% endfor %}{% if messages[-1]['role'] == 'user' %}### Asistan:\n{% endif %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|stop|>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}