add token

This commit is contained in:
mjchen6 2023-06-13 19:26:58 +08:00
parent 1f07d09542
commit bbbac7704b
4 changed files with 60 additions and 0 deletions

31
config.json Normal file
View File

@ -0,0 +1,31 @@
{
"_name_or_path": "THUDM/chatglm-6b",
"architectures": [
"ChatGLMModel"
],
"auto_map": {
"AutoConfig": "THUDM/chatglm-6b--configuration_chatglm.ChatGLMConfig",
"AutoModel": "THUDM/chatglm-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "THUDM/chatglm-6b--modeling_chatglm.ChatGLMForConditionalGeneration"
},
"bos_token_id": 130004,
"eos_token_id": 130005,
"gmask_token_id": 130001,
"hidden_size": 4096,
"inner_hidden_size": 16384,
"layernorm_epsilon": 1e-05,
"mask_token_id": 130000,
"max_sequence_length": 2048,
"model_type": "chatglm",
"num_attention_heads": 32,
"num_layers": 28,
"pad_token_id": 3,
"position_encoding_2d": true,
"pre_seq_len": null,
"prefix_projection": false,
"quantization_bit": 0,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 130528
}

BIN
ice_text.model Normal file

Binary file not shown.

7
special_tokens_map.json Normal file
View File

@ -0,0 +1,7 @@
{
"bos_token": "<sop>",
"eos_token": "<eop>",
"mask_token": "[MASK]",
"pad_token": "<pad>",
"unk_token": "<unk>"
}

22
tokenizer_config.json Normal file
View File

@ -0,0 +1,22 @@
{
"auto_map": {
"AutoTokenizer": [
"THUDM/chatglm-6b--tokenization_chatglm.ChatGLMTokenizer",
null
]
},
"bos_token": "<sop>",
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"end_token": "</s>",
"eos_token": "<eop>",
"gmask_token": "[gMASK]",
"mask_token": "[MASK]",
"model_max_length": 2048,
"num_image_tokens": 0,
"pad_token": "<pad>",
"padding_side": "left",
"remove_space": false,
"tokenizer_class": "ChatGLMTokenizer",
"unk_token": "<unk>"
}