generated from xuyuqing/ailab
add finGPT_merged
This commit is contained in:
mjchen6
parent
6fa776047d
commit
8ec6fa4eae
|
|
@ -0,0 +1 @@
|
|||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
{
|
||||
"_name_or_path": "/home/sdk_models/chatglm2_6b/",
|
||||
"add_bias_linear": false,
|
||||
"add_qkv_bias": true,
|
||||
"apply_query_key_layer_scaling": true,
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"architectures": [
|
||||
"ChatGLMForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"attention_softmax_in_fp32": true,
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
|
||||
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
||||
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
|
||||
},
|
||||
"bias_dropout_fusion": true,
|
||||
"eos_token_id": 2,
|
||||
"ffn_hidden_size": 13696,
|
||||
"fp32_residual_connection": false,
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4096,
|
||||
"kv_channels": 128,
|
||||
"layernorm_epsilon": 1e-05,
|
||||
"model_type": "chatglm",
|
||||
"multi_query_attention": true,
|
||||
"multi_query_group_num": 2,
|
||||
"num_attention_heads": 32,
|
||||
"num_layers": 28,
|
||||
"original_rope": true,
|
||||
"pad_token_id": 0,
|
||||
"padded_vocab_size": 65024,
|
||||
"post_layer_norm": true,
|
||||
"pre_seq_len": null,
|
||||
"prefix_projection": false,
|
||||
"quantization_bit": 0,
|
||||
"rmsnorm": true,
|
||||
"seq_length": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.31.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 65024
|
||||
}
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
from transformers import PretrainedConfig
|
||||
|
||||
|
||||
class ChatGLMConfig(PretrainedConfig):
|
||||
model_type = "chatglm"
|
||||
def __init__(
|
||||
self,
|
||||
num_layers=28,
|
||||
padded_vocab_size=65024,
|
||||
hidden_size=4096,
|
||||
ffn_hidden_size=13696,
|
||||
kv_channels=128,
|
||||
num_attention_heads=32,
|
||||
seq_length=2048,
|
||||
hidden_dropout=0.0,
|
||||
attention_dropout=0.0,
|
||||
layernorm_epsilon=1e-5,
|
||||
rmsnorm=True,
|
||||
apply_residual_connection_post_layernorm=False,
|
||||
post_layer_norm=True,
|
||||
add_bias_linear=False,
|
||||
add_qkv_bias=False,
|
||||
interleaved_qkv=False,
|
||||
bias_dropout_fusion=True,
|
||||
multi_query_attention=False,
|
||||
multi_query_group_num=1,
|
||||
apply_query_key_layer_scaling=True,
|
||||
attention_softmax_in_fp32=True,
|
||||
fp32_residual_connection=False,
|
||||
quantization_bit=0,
|
||||
pre_seq_len=None,
|
||||
prefix_projection=False,
|
||||
**kwargs
|
||||
):
|
||||
self.num_layers = num_layers
|
||||
self.vocab_size = padded_vocab_size
|
||||
self.padded_vocab_size = padded_vocab_size
|
||||
self.hidden_size = hidden_size
|
||||
self.ffn_hidden_size = ffn_hidden_size
|
||||
self.kv_channels = kv_channels
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.seq_length = seq_length
|
||||
self.hidden_dropout = hidden_dropout
|
||||
self.attention_dropout = attention_dropout
|
||||
self.layernorm_epsilon = layernorm_epsilon
|
||||
self.rmsnorm = rmsnorm
|
||||
self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
|
||||
self.post_layer_norm = post_layer_norm
|
||||
self.add_bias_linear = add_bias_linear
|
||||
self.add_qkv_bias = add_qkv_bias
|
||||
self.bias_dropout_fusion = bias_dropout_fusion
|
||||
self.multi_query_attention = multi_query_attention
|
||||
self.multi_query_group_num = multi_query_group_num
|
||||
self.apply_query_key_layer_scaling = apply_query_key_layer_scaling
|
||||
self.attention_softmax_in_fp32 = attention_softmax_in_fp32
|
||||
self.fp32_residual_connection = fp32_residual_connection
|
||||
self.quantization_bit = quantization_bit
|
||||
self.pre_seq_len = pre_seq_len
|
||||
self.prefix_projection = prefix_projection
|
||||
super().__init__(**kwargs)
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
{
|
||||
"_from_model_config": true,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.31.0"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,208 @@
|
|||
{
|
||||
"metadata": {
|
||||
"total_size": 12487168064
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.final_layernorm.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"transformer.output_layer.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00015.bin"
|
||||
}
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1 @@
|
|||
{}
|
||||
|
|
@ -0,0 +1,253 @@
|
|||
import os
|
||||
import torch
|
||||
from typing import List, Optional, Union, Dict
|
||||
from sentencepiece import SentencePieceProcessor
|
||||
from transformers import PreTrainedTokenizer
|
||||
from transformers.utils import logging, PaddingStrategy
|
||||
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
||||
|
||||
|
||||
class SPTokenizer:
|
||||
def __init__(self, model_path: str):
|
||||
# reload tokenizer
|
||||
assert os.path.isfile(model_path), model_path
|
||||
self.sp_model = SentencePieceProcessor(model_file=model_path)
|
||||
|
||||
# BOS / EOS token IDs
|
||||
self.n_words: int = self.sp_model.vocab_size()
|
||||
self.bos_id: int = self.sp_model.bos_id()
|
||||
self.eos_id: int = self.sp_model.eos_id()
|
||||
self.pad_id: int = self.sp_model.unk_id()
|
||||
assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
|
||||
|
||||
special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"]
|
||||
self.special_tokens = {}
|
||||
self.index_special_tokens = {}
|
||||
for token in special_tokens:
|
||||
self.special_tokens[token] = self.n_words
|
||||
self.index_special_tokens[self.n_words] = token
|
||||
self.n_words += 1
|
||||
|
||||
def tokenize(self, s: str):
|
||||
return self.sp_model.EncodeAsPieces(s)
|
||||
|
||||
def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
|
||||
assert type(s) is str
|
||||
t = self.sp_model.encode(s)
|
||||
if bos:
|
||||
t = [self.bos_id] + t
|
||||
if eos:
|
||||
t = t + [self.eos_id]
|
||||
return t
|
||||
|
||||
def decode(self, t: List[int]) -> str:
|
||||
return self.sp_model.decode(t)
|
||||
|
||||
def decode_tokens(self, tokens: List[str]) -> str:
|
||||
text = self.sp_model.DecodePieces(tokens)
|
||||
return text
|
||||
|
||||
def convert_token_to_id(self, token):
|
||||
""" Converts a token (str) in an id using the vocab. """
|
||||
if token in self.special_tokens:
|
||||
return self.special_tokens[token]
|
||||
return self.sp_model.PieceToId(token)
|
||||
|
||||
def convert_id_to_token(self, index):
|
||||
"""Converts an index (integer) in a token (str) using the vocab."""
|
||||
if index in self.index_special_tokens or index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
|
||||
return ""
|
||||
return self.sp_model.IdToPiece(index)
|
||||
|
||||
|
||||
class ChatGLMTokenizer(PreTrainedTokenizer):
|
||||
vocab_files_names = {"vocab_file": "tokenizer.model"}
|
||||
|
||||
model_input_names = ["input_ids", "attention_mask", "position_ids"]
|
||||
|
||||
def __init__(self, vocab_file, padding_side="left", **kwargs):
|
||||
super().__init__(padding_side=padding_side, **kwargs)
|
||||
self.name = "GLMTokenizer"
|
||||
|
||||
self.vocab_file = vocab_file
|
||||
self.tokenizer = SPTokenizer(vocab_file)
|
||||
self.special_tokens = {
|
||||
"<bos>": self.tokenizer.bos_id,
|
||||
"<eos>": self.tokenizer.eos_id,
|
||||
"<pad>": self.tokenizer.pad_id
|
||||
}
|
||||
|
||||
def get_command(self, token):
|
||||
if token in self.special_tokens:
|
||||
return self.special_tokens[token]
|
||||
assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
|
||||
return self.tokenizer.special_tokens[token]
|
||||
|
||||
@property
|
||||
def pad_token(self) -> str:
|
||||
return "<unk>"
|
||||
|
||||
@property
|
||||
def pad_token_id(self):
|
||||
return self.get_command("<pad>")
|
||||
|
||||
@property
|
||||
def eos_token(self) -> str:
|
||||
return "</s>"
|
||||
|
||||
@property
|
||||
def eos_token_id(self):
|
||||
return self.get_command("<eos>")
|
||||
|
||||
@property
|
||||
def vocab_size(self):
|
||||
return self.tokenizer.n_words
|
||||
|
||||
def get_vocab(self):
|
||||
""" Returns vocab as a dict """
|
||||
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
||||
vocab.update(self.added_tokens_encoder)
|
||||
return vocab
|
||||
|
||||
def _tokenize(self, text, **kwargs):
|
||||
return self.tokenizer.tokenize(text)
|
||||
|
||||
def _convert_token_to_id(self, token):
|
||||
""" Converts a token (str) in an id using the vocab. """
|
||||
return self.tokenizer.convert_token_to_id(token)
|
||||
|
||||
def _convert_id_to_token(self, index):
|
||||
"""Converts an index (integer) in a token (str) using the vocab."""
|
||||
return self.tokenizer.convert_id_to_token(index)
|
||||
|
||||
def convert_tokens_to_string(self, tokens: List[str]) -> str:
|
||||
return self.tokenizer.decode_tokens(tokens)
|
||||
|
||||
def save_vocabulary(self, save_directory, filename_prefix=None):
|
||||
"""
|
||||
Save the vocabulary and special tokens file to a directory.
|
||||
|
||||
Args:
|
||||
save_directory (`str`):
|
||||
The directory in which to save the vocabulary.
|
||||
filename_prefix (`str`, *optional*):
|
||||
An optional prefix to add to the named of the saved files.
|
||||
|
||||
Returns:
|
||||
`Tuple(str)`: Paths to the files saved.
|
||||
"""
|
||||
if os.path.isdir(save_directory):
|
||||
vocab_file = os.path.join(
|
||||
save_directory, self.vocab_files_names["vocab_file"]
|
||||
)
|
||||
else:
|
||||
vocab_file = save_directory
|
||||
|
||||
with open(self.vocab_file, 'rb') as fin:
|
||||
proto_str = fin.read()
|
||||
|
||||
with open(vocab_file, "wb") as writer:
|
||||
writer.write(proto_str)
|
||||
|
||||
return (vocab_file,)
|
||||
|
||||
def get_prefix_tokens(self):
|
||||
prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
|
||||
return prefix_tokens
|
||||
|
||||
def build_prompt(self, query, history=None):
|
||||
if history is None:
|
||||
history = []
|
||||
prompt = ""
|
||||
for i, (old_query, response) in enumerate(history):
|
||||
prompt += "[Round {}]\n\n问：{}\n\n答：{}\n\n".format(i + 1, old_query, response)
|
||||
prompt += "[Round {}]\n\n问：{}\n\n答：".format(len(history) + 1, query)
|
||||
return prompt
|
||||
|
||||
def build_inputs_with_special_tokens(
|
||||
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
||||
) -> List[int]:
|
||||
"""
|
||||
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
||||
adding special tokens. A BERT sequence has the following format:
|
||||
|
||||
- single sequence: `[CLS] X [SEP]`
|
||||
- pair of sequences: `[CLS] A [SEP] B [SEP]`
|
||||
|
||||
Args:
|
||||
token_ids_0 (`List[int]`):
|
||||
List of IDs to which the special tokens will be added.
|
||||
token_ids_1 (`List[int]`, *optional*):
|
||||
Optional second list of IDs for sequence pairs.
|
||||
|
||||
Returns:
|
||||
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
||||
"""
|
||||
prefix_tokens = self.get_prefix_tokens()
|
||||
token_ids_0 = prefix_tokens + token_ids_0
|
||||
if token_ids_1 is not None:
|
||||
token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
|
||||
return token_ids_0
|
||||
|
||||
def _pad(
|
||||
self,
|
||||
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
||||
max_length: Optional[int] = None,
|
||||
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
||||
pad_to_multiple_of: Optional[int] = None,
|
||||
return_attention_mask: Optional[bool] = None,
|
||||
) -> dict:
|
||||
"""
|
||||
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
|
||||
|
||||
Args:
|
||||
encoded_inputs:
|
||||
Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
|
||||
max_length: maximum length of the returned list and optionally padding length (see below).
|
||||
Will truncate by taking into account the special tokens.
|
||||
padding_strategy: PaddingStrategy to use for padding.
|
||||
|
||||
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
|
||||
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
|
||||
- PaddingStrategy.DO_NOT_PAD: Do not pad
|
||||
The tokenizer padding sides are defined in self.padding_side:
|
||||
|
||||
- 'left': pads on the left of the sequences
|
||||
- 'right': pads on the right of the sequences
|
||||
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
|
||||
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
|
||||
`>= 7.5` (Volta).
|
||||
return_attention_mask:
|
||||
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
||||
"""
|
||||
# Load from model defaults
|
||||
assert self.padding_side == "left"
|
||||
|
||||
required_input = encoded_inputs[self.model_input_names[0]]
|
||||
seq_length = len(required_input)
|
||||
|
||||
if padding_strategy == PaddingStrategy.LONGEST:
|
||||
max_length = len(required_input)
|
||||
|
||||
if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
|
||||
max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
|
||||
|
||||
needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
|
||||
|
||||
# Initialize attention mask if not present.
|
||||
if "attention_mask" not in encoded_inputs:
|
||||
encoded_inputs["attention_mask"] = [1] * seq_length
|
||||
|
||||
if "position_ids" not in encoded_inputs:
|
||||
encoded_inputs["position_ids"] = list(range(seq_length))
|
||||
|
||||
if needs_to_be_padded:
|
||||
difference = max_length - len(required_input)
|
||||
|
||||
if "attention_mask" in encoded_inputs:
|
||||
encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
|
||||
if "position_ids" in encoded_inputs:
|
||||
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
||||
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
||||
|
||||
return encoded_inputs
|
||||
Binary file not shown.
|
|
@ -0,0 +1,14 @@
|
|||
{
|
||||
"auto_map": {
|
||||
"AutoTokenizer": [
|
||||
"tokenization_chatglm.ChatGLMTokenizer",
|
||||
null
|
||||
]
|
||||
},
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"do_lower_case": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"padding_side": "left",
|
||||
"remove_space": false,
|
||||
"tokenizer_class": "ChatGLMTokenizer"
|
||||
}
|
||||
Loading…
Reference in New Issue