Skip to content

🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.

update config

gongjyaa5d70321fb2
diff --git a/model/tokenizer.model b/model/tokenizer.model
deleted file mode 100644
index 85c0803..0000000
Binary files a/model/tokenizer.model and /dev/null differ
diff --git a/model/tokenizer_config.json b/model/tokenizer_config.json
deleted file mode 100644
index eb538f9..0000000
--- a/model/tokenizer_config.json
+++ /dev/null
@@ -1,44 +0,0 @@
-{
- "add_bos_token": false,
- "add_eos_token": false,
- "add_prefix_space": true,
- "added_tokens_decoder": {
- "0": {
- "content": "<unk>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "1": {
- "content": "<s>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "2": {
- "content": "</s>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- }
- },
- "additional_special_tokens": [],
- "bos_token": "<s>",
- "clean_up_tokenization_spaces": false,
- "eos_token": "</s>",
- "legacy": true,
- "model_max_length": 1000000000000000019884624838656,
- "pad_token": null,
- "sp_model_kwargs": {},
- "spaces_between_special_tokens": false,
- "tokenizer_class": "LlamaTokenizer",
- "unk_token": "<unk>",
- "use_default_system_prompt": false,
- "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<s>user\\n' + content + '</s>\\n<s>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}"
-}