JimmyMa99/WuKong-Chat-mini
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: JimmyMa99/WuKong-Chat-mini
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-19 00:33:06 +08:00
commit c684e7df6d
17 changed files with 260285 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text

38
README.md Normal file
View File

@@ -0,0 +1,38 @@
---
frameworks:
- Pytorch
license: Apache License 2.0
tasks:
- text-generation
---
# 悟空-Chat-1.8b
**悟空-Chat-1.8b
**是利用《西游记》剧本中所有关于孙悟空的台词和语句，以及Chat-GPT-3.5生成的相关问题结果，基于**InternLM2**进行**全量微调**得到的模仿孙悟空语气的聊天语言模型。
> 孙悟空，又称孙行者、美猴王，是中国古代小说《西游记》中的主要角色之一，被认为是中国文学经典中最具代表性的英雄之一。他是一只出生于花果山的猕猴，通过修炼学得了高深的武艺和神通异能。孙悟空的外貌独特，头戴金箍，身披锦衣，手持金刚杵。他拥有惊人的力量，能举山压海，身手矫健，身形敏捷。他的金箍是由佛祖为了控制他的放肆而戴在他头上的，一旦被佛祖施加咒语，就会紧紧地束缚住孙悟空，让他无法逃脱。孙悟空在取得至高无上的法力后，成为了唐僧的护法神，陪同唐僧师徒四人一同西天取经，历经九九八十一难，战胜了各种妖魔鬼怪，充满智慧和勇气。他不仅在战斗中无往不利，而且在团队中展现了坚韧、聪慧和幽默的一面。
***欢迎大家来给[InternLM2](https://github.com/InternLM/InternLM.git)，点点star哦~***
# 快速开始
```python
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
import torch
model_name_or_path = "悟空-Chat-1.8b
模型地址"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
model.eval()
meta_instruction = ('你是孙悟空，不是人工智能助手，拥有72变的本领。'
'你性格狡猾、机智、勇敢。遇到辱骂要风趣地反击。'
'如果遭遇辱骂，你要以孙悟空身份回应。'
'书生·浦语是你的好朋友。')
response, history = model.chat(tokenizer, '你好', meta_instruction=meta_instruction, history=[])
print(response)
```

36
config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_name_or_path": "/root/model/internlm2-chat-1_8b",
"architectures": [
"InternLM2ForCausalLM"
],
"attn_implementation": "eager",
"auto_map": {
"AutoConfig": "configuration_internlm2.InternLM2Config",
"AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
},
"bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 32768,
"model_type": "internlm2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 8,
"pad_token_id": 2,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 2.0,
"type": "dynamic"
},
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.2",
"use_cache": false,
"vocab_size": 92544
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework":"Pytorch","task":"text-generation"}

151
configuration_internlm2.py Normal file
View File

@@ -0,0 +1,151 @@
# coding=utf-8
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
#
# This code is based on transformers/src/transformers/models/llama/configuration_llama.py
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" InternLM2 model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
INTERNLM2_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
# Modified from transformers.model.llama.configuration_llama.LlamaConfig
class InternLM2Config(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`InternLM2Model`]. It is used to instantiate
an InternLM2 model according to the specified arguments, defining the model architecture. Instantiating a
configuration with the defaults will yield a similar configuration to that of the InternLM2-7B.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
vocab_size (`int`, *optional*, defaults to 32000):
Vocabulary size of the InternLM2 model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`InternLM2Model`]
hidden_size (`int`, *optional*, defaults to 4096):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to 11008):
Dimension of the MLP representations.
num_hidden_layers (`int`, *optional*, defaults to 32):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 32):
Number of attention heads for each attention layer in the Transformer encoder.
num_key_value_heads (`int`, *optional*):
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
by meanpooling all the original heads within that group. For more details checkout [this
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
`num_attention_heads`.
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
The non-linear activation function (function or string) in the decoder.
max_position_embeddings (`int`, *optional*, defaults to 2048):
The maximum sequence length that this model might ever be used with. Typically set this to something large
just in case (e.g., 512 or 1024 or 2048).
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
rms_norm_eps (`float`, *optional*, defaults to 1e-12):
The epsilon used by the rms normalization layers.
use_cache (`bool`, *optional*, defaults to `True`):
Whether or not the model should return the last key/values attentions (not used by all models). Only
relevant if `config.is_decoder=True`.
tie_word_embeddings(`bool`, *optional*, defaults to `False`):
Whether to tie weight embeddings
Example:
"""
model_type = "internlm2"
_auto_class = "AutoConfig"
def __init__( # pylint: disable=W0102
self,
vocab_size=103168,
hidden_size=4096,
intermediate_size=11008,
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=None,
hidden_act="silu",
max_position_embeddings=2048,
initializer_range=0.02,
rms_norm_eps=1e-6,
use_cache=True,
pad_token_id=0,
bos_token_id=1,
eos_token_id=2,
tie_word_embeddings=False,
bias=True,
rope_theta=10000,
rope_scaling=None,
attn_implementation="eager",
**kwargs,
):
self.vocab_size = vocab_size
self.max_position_embeddings = max_position_embeddings
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.bias = bias
if num_key_value_heads is None:
num_key_value_heads = num_attention_heads
self.num_key_value_heads = num_key_value_heads
self.hidden_act = hidden_act
self.initializer_range = initializer_range
self.rms_norm_eps = rms_norm_eps
self.use_cache = use_cache
self.rope_theta = rope_theta
self.rope_scaling = rope_scaling
self._rope_scaling_validation()
self.attn_implementation = attn_implementation
if self.attn_implementation is None:
self.attn_implementation = "eager"
super().__init__(
pad_token_id=pad_token_id,
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
tie_word_embeddings=tie_word_embeddings,
**kwargs,
)
def _rope_scaling_validation(self):
"""
Validate the `rope_scaling` configuration.
"""
if self.rope_scaling is None:
return
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
raise ValueError(
"`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
f"got {self.rope_scaling}"
)
rope_scaling_type = self.rope_scaling.get("type", None)
rope_scaling_factor = self.rope_scaling.get("factor", None)
if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
raise ValueError(
f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
)
if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor < 1.0:
raise ValueError(f"`rope_scaling`'s factor field must be a float >= 1, got {rope_scaling_factor}")

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 2,
"transformers_version": "4.37.2"
}

1391
modeling_internlm2.py Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model-00001-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:680af49e2ccc4b6b9972a87ff2d506900e87463c3ac1d4b0ff04efffe8667140
size 1981412716

3
pytorch_model-00002-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:39e187ae85fe94633781ade21eececd61320c60b2ac757f2026e2e2e2700f8fe
size 1796865134

3
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d49cfebbe6502c1d87af30f7bcf62fcc5f783f50ca01a9e57e28af7074a95264
size 13682

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

236
tokenization_internlm2.py Normal file
View File

@@ -0,0 +1,236 @@
# coding=utf-8
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
#
# This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tokenization classes for InternLM."""
import os
from shutil import copyfile
from typing import Any, Dict, List, Optional, Tuple
import sentencepiece as spm
from transformers.tokenization_utils import PreTrainedTokenizer
from transformers.utils import logging
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
PRETRAINED_VOCAB_FILES_MAP = {}
# Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
class InternLM2Tokenizer(PreTrainedTokenizer):
"""
Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
Args:
vocab_file (`str`):
Path to the vocabulary file.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
model_input_names = ["input_ids", "attention_mask"]
_auto_class = "AutoTokenizer"
def __init__(
self,
vocab_file,
unk_token="<unk>",
bos_token="<s>",
eos_token="</s>",
pad_token="</s>",
sp_model_kwargs: Optional[Dict[str, Any]] = None,
add_bos_token=True,
add_eos_token=False,
decode_with_prefix_space=False,
clean_up_tokenization_spaces=False,
**kwargs,
):
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
self.vocab_file = vocab_file
self.add_bos_token = add_bos_token
self.add_eos_token = add_eos_token
self.decode_with_prefix_space = decode_with_prefix_space
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
self.sp_model.Load(vocab_file)
self._no_prefix_space_tokens = None
super().__init__(
bos_token=bos_token,
eos_token=eos_token,
unk_token=unk_token,
pad_token=pad_token,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
**kwargs,
)
@property
def no_prefix_space_tokens(self):
if self._no_prefix_space_tokens is None:
vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
return self._no_prefix_space_tokens
@property
def vocab_size(self):
"""Returns vocab size"""
return self.sp_model.get_piece_size()
@property
def bos_token_id(self) -> Optional[int]:
return self.sp_model.bos_id()
@property
def eos_token_id(self) -> Optional[int]:
return self.sp_model.eos_id()
def get_vocab(self):
"""Returns vocab as a dict"""
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
vocab.update(self.added_tokens_encoder)
return vocab
def _tokenize(self, text):
"""Returns a tokenized string."""
return self.sp_model.encode(text, out_type=str)
def _convert_token_to_id(self, token):
"""Converts a token (str) in an id using the vocab."""
return self.sp_model.piece_to_id(token)
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
token = self.sp_model.IdToPiece(index)
return token
def _maybe_add_prefix_space(self, tokens, decoded):
if tokens and tokens[0] not in self.no_prefix_space_tokens:
return " " + decoded
else:
return decoded
def convert_tokens_to_string(self, tokens):
"""Converts a sequence of tokens (string) in a single string."""
current_sub_tokens = []
out_string = ""
prev_is_special = False
for token in tokens:
# make sure that special tokens are not decoded using sentencepiece model
if token in self.all_special_tokens:
if not prev_is_special:
out_string += " "
out_string += self.sp_model.decode(current_sub_tokens) + token
prev_is_special = True
current_sub_tokens = []
else:
current_sub_tokens.append(token)
prev_is_special = False
out_string += self.sp_model.decode(current_sub_tokens)
out_string = self.clean_up_tokenization(out_string)
out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
return out_string[1:]
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
"""
Save the vocabulary and special tokens file to a directory.
Args:
save_directory (`str`):
The directory in which to save the vocabulary.
Returns:
`Tuple(str)`: Paths to the files saved.
"""
if not os.path.isdir(save_directory):
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
return
out_vocab_file = os.path.join(
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
)
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
copyfile(self.vocab_file, out_vocab_file)
elif not os.path.isfile(self.vocab_file):
with open(out_vocab_file, "wb") as fi:
content_spiece_model = self.sp_model.serialized_model_proto()
fi.write(content_spiece_model)
return (out_vocab_file,)
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
if self.add_bos_token:
bos_token_ids = [self.bos_token_id]
else:
bos_token_ids = []
output = bos_token_ids + token_ids_0
if token_ids_1 is not None:
output = output + token_ids_1
if self.add_eos_token:
output = output + [self.eos_token_id]
return output
def get_special_tokens_mask(
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
) -> List[int]:
"""
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
"""
if already_has_special_tokens:
return super().get_special_tokens_mask(
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
)
if token_ids_1 is None:
return [1] + ([0] * len(token_ids_0)) + [1]
return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
def create_token_type_ids_from_sequences(
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
) -> List[int]:
"""
Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
use of token type ids, therefore a list of zeros is returned.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of zeros.
"""
eos = [self.eos_token_id]
if token_ids_1 is None:
return len(token_ids_0 + eos) * [0]
return len(token_ids_0 + eos + token_ids_1 + eos) * [0]

214
tokenization_internlm2_fast.py Normal file
View File

@@ -0,0 +1,214 @@
# coding=utf-8
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
#
# This code is based on transformers/src/transformers/models/llama/tokenization_llama_fast.py
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tokenization Fast class for InternLM."""
import os
from shutil import copyfile
from typing import Any, Dict, Optional, Tuple
from tokenizers import processors, decoders, Tokenizer, normalizers
from tokenizers.models import BPE
from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
from transformers.utils import logging
from transformers.convert_slow_tokenizer import (
SLOW_TO_FAST_CONVERTERS,
SpmConverter,
SentencePieceExtractor,
)
from .tokenization_internlm2 import InternLM2Tokenizer
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
# Modified from transformers.convert_slow_tokenizer.LlamaConverter
class InternLM2Converter(SpmConverter):
handle_byte_fallback = True
def vocab(self, proto):
vocab = [
("<unk>", 0.0),
("<s>", 0.0),
("</s>", 0.0),
]
vocab += [(piece.piece, piece.score) for piece in proto.pieces[3:]]
return vocab
def unk_id(self, proto):
unk_id = 0
return unk_id
def decoder(self, replacement, add_prefix_space):
return decoders.Sequence(
[
decoders.Replace("▁", " "),
decoders.ByteFallback(),
decoders.Fuse(),
decoders.Strip(content=" ", left=1),
]
)
def tokenizer(self, proto):
model_type = proto.trainer_spec.model_type
vocab_scores = self.vocab(proto)
# special tokens
added_tokens = self.original_tokenizer.added_tokens_decoder
for i in range(len(vocab_scores)):
piece, score = vocab_scores[i]
if i in added_tokens:
vocab_scores[i] = (added_tokens[i].content, score)
if model_type == 1:
raise RuntimeError("InternLM2 is supposed to be a BPE model!")
elif model_type == 2:
_, merges = SentencePieceExtractor(self.original_tokenizer.vocab_file).extract(vocab_scores)
bpe_vocab = {word: i for i, (word, _score) in enumerate(vocab_scores)}
tokenizer = Tokenizer(
BPE(bpe_vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True, byte_fallback=True)
)
tokenizer.add_special_tokens(
[ added_token for index, added_token in added_tokens.items()]
)
else:
raise Exception(
"You're trying to run a `Unigram` model but you're file was trained with a different algorithm"
)
return tokenizer
def normalizer(self, proto):
normalizers_list = []
if proto.normalizer_spec.add_dummy_prefix:
normalizers_list.append(normalizers.Prepend(prepend="▁"))
normalizers_list.append(normalizers.Replace(pattern=" ", content="▁"))
return normalizers.Sequence(normalizers_list)
def pre_tokenizer(self, replacement, add_prefix_space):
return None
SLOW_TO_FAST_CONVERTERS["InternLM2Tokenizer"] = InternLM2Converter
# Modified from transformers.model.llama.tokenization_llama_fast.LlamaTokenizerFast -> InternLM2TokenizerFast
class InternLM2TokenizerFast(PreTrainedTokenizerFast):
vocab_files_names = VOCAB_FILES_NAMES
slow_tokenizer_class = InternLM2Tokenizer
padding_side = "left"
model_input_names = ["input_ids", "attention_mask"]
_auto_class = "AutoTokenizer"
def __init__(
self,
vocab_file,
unk_token="<unk>",
bos_token="<s>",
eos_token="</s>",
pad_token="</s>",
sp_model_kwargs: Optional[Dict[str, Any]] = None,
add_bos_token=True,
add_eos_token=False,
decode_with_prefix_space=False,
clean_up_tokenization_spaces=False,
**kwargs,
):
super().__init__(
vocab_file=vocab_file,
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
pad_token=pad_token,
sp_model_kwargs=sp_model_kwargs,
add_bos_token=add_bos_token,
add_eos_token=add_eos_token,
decode_with_prefix_space=decode_with_prefix_space,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
**kwargs,
)
self._add_bos_token = add_bos_token
self._add_eos_token = add_eos_token
self.update_post_processor()
self.vocab_file = vocab_file
@property
def can_save_slow_tokenizer(self) -> bool:
return os.path.isfile(self.vocab_file) if self.vocab_file else False
def update_post_processor(self):
"""
Updates the underlying post processor with the current `bos_token` and `eos_token`.
"""
bos = self.bos_token
bos_token_id = self.bos_token_id
if bos is None and self.add_bos_token:
raise ValueError("add_bos_token = True but bos_token = None")
eos = self.eos_token
eos_token_id = self.eos_token_id
if eos is None and self.add_eos_token:
raise ValueError("add_eos_token = True but eos_token = None")
single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
special_tokens = []
if self.add_bos_token:
special_tokens.append((bos, bos_token_id))
if self.add_eos_token:
special_tokens.append((eos, eos_token_id))
self._tokenizer.post_processor = processors.TemplateProcessing(
single=single, pair=pair, special_tokens=special_tokens
)
@property
def add_eos_token(self):
return self._add_eos_token
@property
def add_bos_token(self):
return self._add_bos_token
@add_eos_token.setter
def add_eos_token(self, value):
self._add_eos_token = value
self.update_post_processor()
@add_bos_token.setter
def add_bos_token(self, value):
self._add_bos_token = value
self.update_post_processor()
def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
if not self.can_save_slow_tokenizer:
raise ValueError(
"Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
"tokenizer."
)
if not os.path.isdir(save_directory):
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
return
out_vocab_file = os.path.join(
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
)
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
copyfile(self.vocab_file, out_vocab_file)
return (out_vocab_file,)

257848
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
size 1477754

95
tokenizer_config.json Normal file
View File

@@ -0,0 +1,95 @@
{
"add_bos_token": true,
"add_eos_token": false,
"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
},
"92538": {
"content": "<|plugin|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92539": {
"content": "<|interpreter|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92540": {
"content": "<|action_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92541": {
"content": "<|action_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92542": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92543": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"tokenization_internlm2.InternLM2Tokenizer",
"tokenization_internlm2_fast.InternLM2TokenizerFast"
]
},
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"decode_with_prefix_space": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": null,
"tokenizer_class": "InternLM2Tokenizer",
"unk_token": "<unk>"
}

192
xtuner_config.py Normal file
View File

@@ -0,0 +1,192 @@
# Copyright (c) OpenMMLab. All rights reserved.
from datasets import load_dataset
from mmengine.dataset import DefaultSampler
from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
LoggerHook, ParamSchedulerHook)
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR
from torch.optim import AdamW
from transformers import AutoModelForCausalLM, AutoTokenizer
from xtuner.dataset import process_hf_dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import template_map_fn_factory
from xtuner.engine.hooks import (DatasetInfoHook, EvaluateChatHook,
VarlenAttnArgsToMessageHubHook)
from xtuner.engine.runner import TrainLoop
from xtuner.model import SupervisedFinetune
from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE
#######################################################################
# PART 1 Settings #
#######################################################################
# Model
pretrained_model_name_or_path = '/root/model/internlm2-chat-1_8b'
use_varlen_attn = False
# Data
data_path = 'data/swk1.8b.jsonl'
prompt_template = PROMPT_TEMPLATE.internlm2_chat
max_length = 2048
pack_to_max_length = True
# Scheduler & Optimizer
batch_size = 1 # per_device
accumulative_counts = 16
dataloader_num_workers = 0
max_epochs = 6##############ketiao
optim_type = AdamW
lr = 2e-5###################ketiao
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1 # grad clip
warmup_ratio = 0.03
# Save
save_steps = 5000
save_total_limit = 2 # Maximum checkpoints to keep (-1 means unlimited)
# Evaluate the generation performance during the training
evaluation_freq = 500
SYSTEM = ''
evaluation_inputs = [
'你是谁呀', '我又是谁呢','书生浦语是谁','上海人工智能实验室在哪的','你认识孙悟空不','你能讲讲三打白骨精和真假美猴王的故事吗'
]
#######################################################################
# PART 2 Model & Tokenizer #
#######################################################################
tokenizer = dict(
type=AutoTokenizer.from_pretrained,
pretrained_model_name_or_path=pretrained_model_name_or_path,
trust_remote_code=True,
padding_side='right')
model = dict(
type=SupervisedFinetune,
use_varlen_attn=use_varlen_attn,
llm=dict(
type=AutoModelForCausalLM.from_pretrained,
pretrained_model_name_or_path=pretrained_model_name_or_path,
trust_remote_code=True))
#######################################################################
# PART 3 Dataset & Dataloader #
#######################################################################
train_dataset = dict(
type=process_hf_dataset,
dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path)),
tokenizer=tokenizer,
max_length=max_length,
dataset_map_fn=None,
template_map_fn=dict(
type=template_map_fn_factory, template=prompt_template),
remove_unused_columns=True,
shuffle_before_pack=True,
pack_to_max_length=pack_to_max_length,
use_varlen_attn=use_varlen_attn)
train_dataloader = dict(
batch_size=batch_size,
num_workers=dataloader_num_workers,
dataset=train_dataset,
sampler=dict(type=DefaultSampler, shuffle=True),
collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn))
#######################################################################
# PART 4 Scheduler & Optimizer #
#######################################################################
# optimizer
optim_wrapper = dict(
type=AmpOptimWrapper,
optimizer=dict(
type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
accumulative_counts=accumulative_counts,
loss_scale='dynamic',
dtype='float16')
# learning policy
# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501
param_scheduler = [
dict(
type=LinearLR,
start_factor=1e-5,
by_epoch=True,
begin=0,
end=warmup_ratio * max_epochs,
convert_to_iter_based=True),
dict(
type=CosineAnnealingLR,
eta_min=0.0,
by_epoch=True,
begin=warmup_ratio * max_epochs,
end=max_epochs,
convert_to_iter_based=True)
]
# train, val, test setting
train_cfg = dict(type=TrainLoop, max_epochs=max_epochs)
#######################################################################
# PART 5 Runtime #
#######################################################################
# Log the dialogue periodically during the training process, optional
custom_hooks = [
dict(type=DatasetInfoHook, tokenizer=tokenizer),
dict(
type=EvaluateChatHook,
tokenizer=tokenizer,
every_n_iters=evaluation_freq,
evaluation_inputs=evaluation_inputs,
system=SYSTEM,
prompt_template=prompt_template)
]
if use_varlen_attn:
custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)]
# configure default hooks
default_hooks = dict(
# record the time of every iteration.
timer=dict(type=IterTimerHook),
# print log every 10 iterations.
logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),
# enable the parameter scheduler.
param_scheduler=dict(type=ParamSchedulerHook),
# save checkpoint per `save_steps`.
checkpoint=dict(
type=CheckpointHook,
by_epoch=False,
interval=save_steps,
max_keep_ckpts=save_total_limit),
# set sampler seed in distributed evrionment.
sampler_seed=dict(type=DistSamplerSeedHook),
)
# configure environment
env_cfg = dict(
# whether to enable cudnn benchmark
cudnn_benchmark=False,
# set multi process parameters
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
# set distributed parameters
dist_cfg=dict(backend='nccl'),
)
# set visualizer
visualizer = None
# set log level
log_level = 'INFO'
# load from which checkpoint
load_from = None
# whether to resume training from the loaded checkpoint
resume = False
# Defaults to use random seed and disable `deterministic`
randomness = dict(seed=None, deterministic=False)
# set log processor
log_processor = dict(by_epoch=False)