From 86c97b6759c2836987bb0119ed0624253403efcf Mon Sep 17 00:00:00 2001 From: xxl <505279206@qq.com> Date: Mon, 30 Dec 2024 18:21:26 +0800 Subject: [PATCH] first commit --- README.md | 30 +- characterglm_generation_utils.py | 121 +++ config.json | 42 + configuration.json | 1 + configuration_chatglm.py | 61 ++ generation_config.json | 6 + modeling_characterglm.py | 218 +++++ modeling_chatglm.py | 1285 ++++++++++++++++++++++++++++++ pytorch_model-00001-of-00002.bin | 3 + pytorch_model-00002-of-00002.bin | 3 + pytorch_model.bin.index.json | 207 +++++ quantization.py | 188 +++++ special_tokens_map.json | 1 + tokenization_chatglm.py | 278 +++++++ tokenizer.model | 3 + tokenizer_config.json | 33 + 16 files changed, 2478 insertions(+), 2 deletions(-) create mode 100644 characterglm_generation_utils.py create mode 100644 config.json create mode 100644 configuration.json create mode 100644 configuration_chatglm.py create mode 100644 generation_config.json create mode 100644 modeling_characterglm.py create mode 100644 modeling_chatglm.py create mode 100644 pytorch_model-00001-of-00002.bin create mode 100644 pytorch_model-00002-of-00002.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 quantization.py create mode 100644 special_tokens_map.json create mode 100644 tokenization_chatglm.py create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json diff --git a/README.md b/README.md index 0a990f2..b2d2eaa 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,29 @@ -# CharacterGLM-6B_a14114209229434880147986 +--- +frameworks: +- Pytorch +license: other +tasks: +- text-generation +--- +###### 模型文件和权重，请浏览“模型文件”页面获取。 +###### 当前模型的贡献者未提供更加详细的模型介绍，但是您可以通过如下git clone命令，或者ModelScope SDK来下载模型。 +###### Clone with HTTP +``` +git clone https://www.modelscope.cn/THUCoAI/CharacterGLM-6B.git +``` +###### 如果您是本模型的贡献者，我们邀请您根据[模型贡献文档说明](https://www.modelscope.cn/docs/%E5%A6%82%E4%BD%95%E6%92%B0%E5%86%99%E5%A5%BD%E7%94%A8%E7%9A%84%E6%A8%A1%E5%9E%8B%E5%8D%A1%E7%89%87)，及时完善模型卡片内容。 +###### [huggingface链接](https://huggingface.co/thu-coai/CharacterGLM-6B) -CharacterGLM-6B \ No newline at end of file + +代码示例 + +```python +>>> from transformers import AutoTokenizer, AutoModel +>>> # 假设您通过git将模型下载到了./CharacterGLM-6B目录 +>>> tokenizer = AutoTokenizer.from_pretrained("./CharacterGLM-6B", trust_remote_code=True) +>>> model = AutoModel.from_pretrained("./CharacterGLM-6b", trust_remote_code=True, device='cuda') +>>> model = model.eval() +>>> session_meta = {'user_info': '我是陆星辰，是一个男性，是一位知名导演，也是苏梦远的合作导演。我擅长拍摄音乐题材的电影。苏梦远对我的态度是尊敬的，并视我为良师益友。', 'bot_info': '苏梦远，本名苏远心，是一位当红的国内女歌手及演员。在参加选秀节目后，凭借独特的嗓音及出众的舞台魅力迅速成名，进入娱乐圈。她外表美丽动人，但真正的魅力在于她的才华和勤奋。苏梦远是音乐学院毕业的优秀生，善于创作，拥有多首热门原创歌曲。除了音乐方面的成就，她还热衷于慈善事业，积极参加公益活动，用实际行动传递正能量。在工作中，她对待工作非常敬业，拍戏时总是全身心投入角色，赢得了业内人士的赞誉和粉丝的喜爱。虽然在娱乐圈，但她始终保持低调、谦逊的态度，深得同行尊重。在表达时，苏梦远喜欢使用“我们”和“一起”，强调团队精神。', 'bot_name': '苏梦远', 'user_name': '陆星辰'} +>>> response, history = model.chat(tokenizer, session_meta, "你好", history=[]) +>>>>>>> add model +``` diff --git a/characterglm_generation_utils.py b/characterglm_generation_utils.py new file mode 100644 index 0000000..785d70e --- /dev/null +++ b/characterglm_generation_utils.py @@ -0,0 +1,121 @@ +import torch +from typing import TypedDict, Literal, List, Optional, Tuple, Iterator + + +#### data types ######### +# 下面的数据类型定义与CharacterGLM API一致，但与modeling_chatglm.py的chat方法不一致 +# 参考 https://open.bigmodel.cn/dev/api#characterglm +RoleType = Literal["user", "assistant"] + +class Msg(TypedDict): + role: RoleType + content: str + + +class SessionMeta(TypedDict): + user_name: str + bot_name: str + bot_info: str + user_info: Optional[str] + + +HistoryType = List[Msg] + + +class CharacterGLMGenerationUtils: + @staticmethod + def convert_chatglm_history_to_characterglm_history(user_query: str, history: List[Tuple[str, str]]) -> HistoryType: + characterglm_history: HistoryType = [] + for i, (query, response) in enumerate(history): + if i == 0 and query == '': + # first empty query is an placeholder + pass + else: + characterglm_history.append({ + "role": "user", + "content": query + }) + characterglm_history.append({ + "role": "assistant", + "content": response + }) + + characterglm_history.append({ + "role": "user", + "content": user_query + }) + return characterglm_history + + @staticmethod + def build_inputs(session_meta: SessionMeta, history: HistoryType) -> str: + """ + 注意：这里假设history最后一条消息是用户query + """ + texts = [] + texts.append( + f"以下是一段{session_meta['bot_name']}和{session_meta['user_name']}之间的对话。") + if session_meta.get("bot_info"): + texts.append(f"关于{session_meta['bot_name']}的信息：{session_meta['bot_info']}") + if session_meta.get("user_info"): + texts.append( + f"关于{session_meta['user_name']}的信息：{session_meta['user_info']}") + + assert history and history[-1]['role'] == 'user' + for msg in history: + name = session_meta['user_name'] if msg['role'] == 'user' else session_meta['bot_name'] + texts.append(f"[{name}]" + msg['content'].strip()) + + texts = [text.replace('\n', ' ') for text in texts] + texts.append(f"[{session_meta['bot_name']}]") + return '\n'.join(texts) + + +class CharacterGLMAPI: + @staticmethod + def build_api_arguments(session_meta: SessionMeta, history: HistoryType) -> dict: + return { + "model": "characterglm", + "meta": session_meta, + "prompt": history + } + + @classmethod + def async_invoke(cls, session_meta: SessionMeta, history: HistoryType): + """ + 注意： + 1. 先设置zhipuai.api_key + 2. 建议传入`return_type='text'`，否则返回结果是json字符串 + + 参考： + https://open.bigmodel.cn/dev/api#characterglm + """ + import zhipuai + kwargs = cls.build_api_arguments(session_meta, history) + return zhipuai.model_api.async_invoke(**kwargs, return_type='text') + + @classmethod + def invoke(cls, session_meta: SessionMeta, history: HistoryType): + """ + 注意： + 1. 先设置zhipuai.api_key + 2. 建议传入`return_type='text'`，否则返回结果是json字符串 + 3. 需要再次调用`zhipuai.model_api.query_async_invoke_result`才能获取生成结果 + + 参考： + https://open.bigmodel.cn/dev/api#characterglm + """ + import zhipuai + kwargs = cls.build_api_arguments(session_meta, history) + return zhipuai.model_api.invoke(**kwargs, return_type='text') + + @classmethod + def generate(cls, session_meta: SessionMeta, history: HistoryType) -> str: + result = cls.invoke(session_meta, history) + if not result['success']: + raise RuntimeError(result) + return result['data']['choices'][0]['content'] + + @classmethod + def stream_generate(cls, session_meta: SessionMeta, history: HistoryType) -> Iterator[str]: + # 伪流式生成 + return iter(cls.generate(session_meta, history)) diff --git a/config.json b/config.json new file mode 100644 index 0000000..9032647 --- /dev/null +++ b/config.json @@ -0,0 +1,42 @@ +{ + "_name_or_path": "thu-coai/CharacterGLM-6B", + "model_type": "chatglm", + "architectures": [ + "ChatGLMModel" + ], + "auto_map": { + "AutoConfig": "configuration_chatglm.ChatGLMConfig", + "AutoModel": "modeling_characterglm.CharacterGLMForConditionalGeneration", + "AutoModelForCausalLM": "modeling_characterglm.CharacterGLMForConditionalGeneration", + "AutoModelForSeq2SeqLM": "modeling_characterglm.CharacterGLMForConditionalGeneration", + "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification" + }, + "add_bias_linear": false, + "add_qkv_bias": true, + "apply_query_key_layer_scaling": true, + "apply_residual_connection_post_layernorm": false, + "attention_dropout": 0.0, + "attention_softmax_in_fp32": true, + "bias_dropout_fusion": true, + "ffn_hidden_size": 13696, + "fp32_residual_connection": false, + "hidden_dropout": 0.0, + "hidden_size": 4096, + "kv_channels": 128, + "layernorm_epsilon": 1e-05, + "multi_query_attention": true, + "multi_query_group_num": 2, + "num_attention_heads": 32, + "num_layers": 28, + "original_rope": true, + "padded_vocab_size": 65024, + "post_layer_norm": true, + "rmsnorm": true, + "seq_length": 32768, + "use_cache": true, + "torch_dtype": "float16", + "transformers_version": "4.27.1", + "tie_word_embeddings": false, + "eos_token_id": 2, + "pad_token_id": 0 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..f9291c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/configuration_chatglm.py b/configuration_chatglm.py new file mode 100644 index 0000000..3560018 --- /dev/null +++ b/configuration_chatglm.py @@ -0,0 +1,61 @@ +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, + classifier_dropout=None, + 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, + 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.classifier_dropout = classifier_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) \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9658f31 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.31.0" +} diff --git a/modeling_characterglm.py b/modeling_characterglm.py new file mode 100644 index 0000000..30a1f73 --- /dev/null +++ b/modeling_characterglm.py @@ -0,0 +1,218 @@ +import copy +import warnings +import logging +from typing import List, Tuple, Optional, Callable + +import torch +from torch import nn +from transformers.utils import logging +from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig + +from .modeling_chatglm import ChatGLMForConditionalGeneration, InvalidScoreLogitsProcessor +from .characterglm_generation_utils import CharacterGLMGenerationUtils, SessionMeta + + +logger = logging.get_logger(__name__) +default_generation_config = { + "do_sample": True, + "top_k": 100, + "top_p": 0.9, + "no_repeat_ngram_size": 0, + "temperature": 0.9, + "num_beams": 1, + "length_penalty": 1.6, + "repetition_penalty": 1.3, + "eos_token_id": 13 +} + + +class CharacterGLMForConditionalGeneration(ChatGLMForConditionalGeneration): + """ + CharacterGLM的prompt格式与chatglm有差异。 + CharacterGLMForConditionalGeneration复用了ChatGLMForConditionalGeneration的forward方法， + 重新实现了`build_inputs`和`build_stream_inputs`, + 调整了`chat`和`stream_chat`方法的函数签名，增加session_meta参数，并修改解码参数的默认值。 + """ + + def build_inputs(self, tokenizer, session_meta: SessionMeta, query: str, history: Optional[List[Tuple[str, str]]] = None): + character_glm_history = CharacterGLMGenerationUtils.convert_chatglm_history_to_characterglm_history(query, history or []) + prompt = CharacterGLMGenerationUtils.build_inputs(session_meta, character_glm_history) + inputs = tokenizer([prompt], return_tensors="pt") + inputs = inputs.to(self.device) + return inputs + + def build_stream_inputs(self, tokenizer, session_meta: SessionMeta, query: str, history: Optional[List[Tuple[str, str]]] = None): + prompt = "\n[{}]{}\n[{}]".format( + session_meta['user_name'], + query.replace('\n', ' '), + session_meta['bot_name'] + ) + input_ids = tokenizer.encode(prompt, add_special_tokens=False) + input_ids = input_ids[1:] + inputs = tokenizer.batch_encode_plus([(input_ids, None)], return_tensors="pt", add_special_tokens=False) + inputs = inputs.to(self.device) + return inputs + + @torch.inference_mode() + def chat(self, tokenizer, session_meta: SessionMeta, query: str, history: List[Tuple[str, str]] = None, max_length: int = 8192, num_beams=1, + do_sample=True, top_p=0.9, temperature=0.9, repetition_penalty=1.6, logits_processor=None, **kwargs): + if history is None: + history = [] + if logits_processor is None: + logits_processor = LogitsProcessorList() + logits_processor.append(InvalidScoreLogitsProcessor()) + gen_kwargs = {"max_length": max_length, "num_beams": num_beams, "do_sample": do_sample, "top_p": top_p, + "temperature": temperature, "logits_processor": logits_processor, "repetition_penalty": repetition_penalty, **kwargs} + gen_kwargs.update({k: v for k, v in default_generation_config.items() if k not in gen_kwargs}) + inputs = self.build_inputs(tokenizer, session_meta, query, history=history) + outputs = self.generate(**inputs, **gen_kwargs) + outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):] + response = tokenizer.decode(outputs) + response = self.process_response(response) + history = history + [(query, response)] + return response, history + + @torch.inference_mode() + def stream_chat(self, tokenizer, session_meta: SessionMeta, query: str, history: List[Tuple[str, str]] = None, past_key_values=None, + max_length: int = 8192, do_sample=True, top_p=0.9, temperature=0.9, repetition_penalty=1.0, logits_processor=None, + return_past_key_values=False, **kwargs): + if history is None: + history = [] + if logits_processor is None: + logits_processor = LogitsProcessorList() + logits_processor.append(InvalidScoreLogitsProcessor()) + gen_kwargs = {"max_length": max_length, "do_sample": do_sample, "top_p": top_p, + "temperature": temperature, "logits_processor": logits_processor, "repetition_penalty": repetition_penalty, **kwargs} + gen_kwargs.update({k: v for k, v in default_generation_config.items() if k not in gen_kwargs}) + gen_kwargs.pop('repetition_penalty', None) + if past_key_values is None: + inputs = self.build_inputs(tokenizer, session_meta, query, history=history) + else: + inputs = self.build_stream_inputs(tokenizer, session_meta, query, history=history) + if past_key_values is not None: + past_length = past_key_values[0][0].shape[0] + if self.transformer.pre_seq_len is not None: + past_length -= self.transformer.pre_seq_len + inputs.position_ids += past_length + attention_mask = inputs.attention_mask + attention_mask = torch.cat((attention_mask.new_ones(1, past_length), attention_mask), dim=1) + inputs['attention_mask'] = attention_mask + for outputs in self.stream_generate(**inputs, past_key_values=past_key_values, + return_past_key_values=return_past_key_values, **gen_kwargs): + if return_past_key_values: + outputs, past_key_values = outputs + outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):] + response = tokenizer.decode(outputs) + if response and response[-1] != "�": + response = self.process_response(response) + new_history = history + [(query, response)] + if return_past_key_values: + yield response, new_history, past_key_values + else: + yield response, new_history + + @torch.inference_mode() + def stream_generate( + self, + input_ids, + generation_config: Optional[GenerationConfig] = None, + logits_processor: Optional[LogitsProcessorList] = None, + stopping_criteria: Optional[StoppingCriteriaList] = None, + prefix_allowed_tokens_fn: Optional[Callable[[int, torch.Tensor], List[int]]] = None, + return_past_key_values=False, + **kwargs, + ): + batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1] + + if generation_config is None: + generation_config = self.generation_config + generation_config = copy.deepcopy(generation_config) + model_kwargs = generation_config.update(**kwargs) + model_kwargs["use_cache"] = generation_config.use_cache + bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id + + if isinstance(eos_token_id, int): + eos_token_id = [eos_token_id] + + has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None + if has_default_max_length and generation_config.max_new_tokens is None: + warnings.warn( + f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. " + "This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we" + " recommend using `max_new_tokens` to control the maximum length of the generation.", + UserWarning, + ) + elif generation_config.max_new_tokens is not None: + generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length + if not has_default_max_length: + logger.warn( + f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(=" + f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. " + "Please refer to the documentation for more information. " + "(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)", + UserWarning, + ) + + if input_ids_seq_length >= generation_config.max_length: + input_ids_string = "decoder_input_ids" if self.config.is_encoder_decoder else "input_ids" + logger.warning( + f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to" + f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider" + " increasing `max_new_tokens`." + ) + + # 2. Set generation parameters if not already defined + logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList() + stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList() + + logits_processor = self._get_logits_processor( + generation_config=generation_config, + input_ids_seq_length=input_ids_seq_length, + encoder_input_ids=input_ids, + prefix_allowed_tokens_fn=prefix_allowed_tokens_fn, + logits_processor=logits_processor, + ) + + stopping_criteria = self._get_stopping_criteria( + generation_config=generation_config, stopping_criteria=stopping_criteria + ) + logits_warper = self._get_logits_warper(generation_config) + + unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1) + scores = None + while True: + model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs) + # forward pass to get next token + outputs = self( + **model_inputs, + return_dict=True, + output_attentions=False, + output_hidden_states=False, + ) + + next_token_logits = outputs.logits[:, -1, :] + + # pre-process distribution + next_token_scores = logits_processor(input_ids, next_token_logits) + next_token_scores = logits_warper(input_ids, next_token_scores) + + # sample + probs = nn.functional.softmax(next_token_scores, dim=-1) + if generation_config.do_sample: + next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1) + else: + next_tokens = torch.argmax(probs, dim=-1) + + # update generated ids, model inputs, and length for next step + input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1) + model_kwargs = self._update_model_kwargs_for_generation( + outputs, model_kwargs, is_encoder_decoder=self.config.is_encoder_decoder + ) + unfinished_sequences = unfinished_sequences.mul((sum(next_tokens != i for i in eos_token_id)).long()) + if return_past_key_values: + yield input_ids, outputs.past_key_values + else: + yield input_ids + # stop when each sentence is finished, or if we exceed the maximum length + if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores): + break diff --git a/modeling_chatglm.py b/modeling_chatglm.py new file mode 100644 index 0000000..d3fb395 --- /dev/null +++ b/modeling_chatglm.py @@ -0,0 +1,1285 @@ +""" PyTorch ChatGLM model. """ + +import math +import copy +import warnings +import re +import sys + +import torch +import torch.utils.checkpoint +import torch.nn.functional as F +from torch import nn +from torch.nn import CrossEntropyLoss, LayerNorm +from torch.nn import CrossEntropyLoss, LayerNorm, MSELoss, BCEWithLogitsLoss +from torch.nn.utils import skip_init +from typing import Optional, Tuple, Union, List, Callable, Dict, Any + +from transformers.modeling_outputs import ( + BaseModelOutputWithPast, + CausalLMOutputWithPast, + SequenceClassifierOutputWithPast, +) +from transformers.modeling_utils import PreTrainedModel +from transformers.utils import logging +from transformers.generation.logits_process import LogitsProcessor +from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput + +from .configuration_chatglm import ChatGLMConfig + +# flags required to enable jit fusion kernels + +if sys.platform != 'darwin': + torch._C._jit_set_profiling_mode(False) + torch._C._jit_set_profiling_executor(False) + torch._C._jit_override_can_fuse_on_cpu(True) + torch._C._jit_override_can_fuse_on_gpu(True) + +logger = logging.get_logger(__name__) + +_CHECKPOINT_FOR_DOC = "THUDM/ChatGLM2-6B" +_CONFIG_FOR_DOC = "ChatGLM6BConfig" + +CHATGLM_6B_PRETRAINED_MODEL_ARCHIVE_LIST = [ + "THUDM/chatglm2-6b", + # See all ChatGLM models at https://huggingface.co/models?filter=chatglm +] + + +def default_init(cls, *args, **kwargs): + return cls(*args, **kwargs) + + +class InvalidScoreLogitsProcessor(LogitsProcessor): + def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor: + if torch.isnan(scores).any() or torch.isinf(scores).any(): + scores.zero_() + scores[..., 5] = 5e4 + return scores + + +class PrefixEncoder(torch.nn.Module): + """ + The torch.nn model to encode the prefix + Input shape: (batch-size, prefix-length) + Output shape: (batch-size, prefix-length, 2*layers*hidden) + """ + + def __init__(self, config: ChatGLMConfig): + super().__init__() + self.prefix_projection = config.prefix_projection + if self.prefix_projection: + # Use a two-layer MLP to encode the prefix + kv_size = config.num_layers * config.kv_channels * config.multi_query_group_num * 2 + self.embedding = torch.nn.Embedding(config.pre_seq_len, kv_size) + self.trans = torch.nn.Sequential( + torch.nn.Linear(kv_size, config.hidden_size), + torch.nn.Tanh(), + torch.nn.Linear(config.hidden_size, kv_size) + ) + else: + self.embedding = torch.nn.Embedding(config.pre_seq_len, + config.num_layers * config.kv_channels * config.multi_query_group_num * 2) + + def forward(self, prefix: torch.Tensor): + if self.prefix_projection: + prefix_tokens = self.embedding(prefix) + past_key_values = self.trans(prefix_tokens) + else: + past_key_values = self.embedding(prefix) + return past_key_values + + +def split_tensor_along_last_dim( + tensor: torch.Tensor, + num_partitions: int, + contiguous_split_chunks: bool = False, +) -> List[torch.Tensor]: + """Split a tensor along its last dimension. + + Arguments: + tensor: input tensor. + num_partitions: number of partitions to split the tensor + contiguous_split_chunks: If True, make each chunk contiguous + in memory. + + Returns: + A list of Tensors + """ + # Get the size and dimension. + last_dim = tensor.dim() - 1 + last_dim_size = tensor.size()[last_dim] // num_partitions + # Split. + tensor_list = torch.split(tensor, last_dim_size, dim=last_dim) + # Note: torch.split does not create contiguous tensors by default. + if contiguous_split_chunks: + return tuple(chunk.contiguous() for chunk in tensor_list) + + return tensor_list + + +class RotaryEmbedding(nn.Module): + def __init__(self, dim, original_impl=False, device=None, dtype=None): + super().__init__() + inv_freq = 1.0 / (10000 ** (torch.arange(0, dim, 2, device=device).to(dtype=dtype) / dim)) + self.register_buffer("inv_freq", inv_freq) + self.dim = dim + self.original_impl = original_impl + + def forward_impl( + self, seq_len: int, n_elem: int, dtype: torch.dtype, device: torch.device, base: int = 10000 + ): + """Enhanced Transformer with Rotary Position Embedding. + + Derived from: https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/ + transformers/rope/__init__.py. MIT License: + https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/license. + """ + # $\Theta = {\theta_i = 10000^{\frac{2(i-1)}{d}}, i \in [1, 2, ..., \frac{d}{2}]}$ + theta = 1.0 / (base ** (torch.arange(0, n_elem, 2, dtype=dtype, device=device) / n_elem)) + + # Create position indexes `[0, 1, ..., seq_len - 1]` + seq_idx = torch.arange(seq_len, dtype=dtype, device=device) + + # Calculate the product of position index and $\theta_i$ + idx_theta = torch.outer(seq_idx, theta).float() + + cache = torch.stack([torch.cos(idx_theta), torch.sin(idx_theta)], dim=-1) + + # this is to mimic the behaviour of complex32, else we will get different results + if dtype in (torch.float16, torch.bfloat16, torch.int8): + cache = cache.bfloat16() if dtype == torch.bfloat16 else cache.half() + return cache + + def forward(self, max_seq_len, offset=0): + return self.forward_impl( + max_seq_len, self.dim, dtype=self.inv_freq.dtype, device=self.inv_freq.device + ) + + +@torch.jit.script +def apply_rotary_pos_emb(x: torch.Tensor, rope_cache: torch.Tensor) -> torch.Tensor: + # x: [sq, b, np, hn] + sq, b, np, hn = x.size(0), x.size(1), x.size(2), x.size(3) + rot_dim = rope_cache.shape[-2] * 2 + x, x_pass = x[..., :rot_dim], x[..., rot_dim:] + # truncate to support variable sizes + rope_cache = rope_cache[:sq] + xshaped = x.reshape(sq, -1, np, rot_dim // 2, 2) + rope_cache = rope_cache.view(sq, -1, 1, xshaped.size(3), 2) + x_out2 = torch.stack( + [ + xshaped[..., 0] * rope_cache[..., 0] - xshaped[..., 1] * rope_cache[..., 1], + xshaped[..., 1] * rope_cache[..., 0] + xshaped[..., 0] * rope_cache[..., 1], + ], + -1, + ) + x_out2 = x_out2.flatten(3) + return torch.cat((x_out2, x_pass), dim=-1) + + +class RMSNorm(torch.nn.Module): + def __init__(self, normalized_shape, eps=1e-5, device=None, dtype=None, **kwargs): + super().__init__() + self.weight = torch.nn.Parameter(torch.empty(normalized_shape, device=device, dtype=dtype)) + self.eps = eps + + def forward(self, hidden_states: torch.Tensor): + input_dtype = hidden_states.dtype + variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True) + hidden_states = hidden_states * torch.rsqrt(variance + self.eps) + + return (self.weight * hidden_states).to(input_dtype) + + +class CoreAttention(torch.nn.Module): + def __init__(self, config: ChatGLMConfig, layer_number): + super(CoreAttention, self).__init__() + + self.apply_query_key_layer_scaling = config.apply_query_key_layer_scaling + self.attention_softmax_in_fp32 = config.attention_softmax_in_fp32 + if self.apply_query_key_layer_scaling: + self.attention_softmax_in_fp32 = True + self.layer_number = max(1, layer_number) + + projection_size = config.kv_channels * config.num_attention_heads + + # Per attention head and per partition values. + self.hidden_size_per_partition = projection_size + self.hidden_size_per_attention_head = projection_size // config.num_attention_heads + self.num_attention_heads_per_partition = config.num_attention_heads + + coeff = None + self.norm_factor = math.sqrt(self.hidden_size_per_attention_head) + if self.apply_query_key_layer_scaling: + coeff = self.layer_number + self.norm_factor *= coeff + self.coeff = coeff + + self.attention_dropout = torch.nn.Dropout(config.attention_dropout) + + def forward(self, query_layer, key_layer, value_layer, attention_mask): + pytorch_major_version = int(torch.__version__.split('.')[0]) + if pytorch_major_version >= 2: + query_layer, key_layer, value_layer = [k.permute(1, 2, 0, 3) for k in [query_layer, key_layer, value_layer]] + if attention_mask is None and query_layer.shape[2] == key_layer.shape[2]: + context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer, + is_causal=True) + else: + if attention_mask is not None: + attention_mask = ~attention_mask + context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer, + attention_mask) + context_layer = context_layer.permute(2, 0, 1, 3) + new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,) + context_layer = context_layer.reshape(*new_context_layer_shape) + else: + # Raw attention scores + + # [b, np, sq, sk] + output_size = (query_layer.size(1), query_layer.size(2), query_layer.size(0), key_layer.size(0)) + + # [sq, b, np, hn] -> [sq, b * np, hn] + query_layer = query_layer.view(output_size[2], output_size[0] * output_size[1], -1) + # [sk, b, np, hn] -> [sk, b * np, hn] + key_layer = key_layer.view(output_size[3], output_size[0] * output_size[1], -1) + + # preallocting input tensor: [b * np, sq, sk] + matmul_input_buffer = torch.empty( + output_size[0] * output_size[1], output_size[2], output_size[3], dtype=query_layer.dtype, + device=query_layer.device + ) + + # Raw attention scores. [b * np, sq, sk] + matmul_result = torch.baddbmm( + matmul_input_buffer, + query_layer.transpose(0, 1), # [b * np, sq, hn] + key_layer.transpose(0, 1).transpose(1, 2), # [b * np, hn, sk] + beta=0.0, + alpha=(1.0 / self.norm_factor), + ) + + # change view to [b, np, sq, sk] + attention_scores = matmul_result.view(*output_size) + + # =========================== + # Attention probs and dropout + # =========================== + + # attention scores and attention mask [b, np, sq, sk] + if self.attention_softmax_in_fp32: + attention_scores = attention_scores.float() + if self.coeff is not None: + attention_scores = attention_scores * self.coeff + if attention_mask is None and attention_scores.shape[2] == attention_scores.shape[3]: + attention_mask = torch.ones(output_size[0], 1, output_size[2], output_size[3], + device=attention_scores.device, dtype=torch.bool) + attention_mask.tril_() + attention_mask = ~attention_mask + if attention_mask is not None: + attention_scores = attention_scores.masked_fill(attention_mask, float("-inf")) + attention_probs = F.softmax(attention_scores, dim=-1) + attention_probs = attention_probs.type_as(value_layer) + + # This is actually dropping out entire tokens to attend to, which might + # seem a bit unusual, but is taken from the original Transformer paper. + attention_probs = self.attention_dropout(attention_probs) + # ========================= + # Context layer. [sq, b, hp] + # ========================= + + # value_layer -> context layer. + # [sk, b, np, hn] --> [b, np, sq, hn] + + # context layer shape: [b, np, sq, hn] + output_size = (value_layer.size(1), value_layer.size(2), query_layer.size(0), value_layer.size(3)) + # change view [sk, b * np, hn] + value_layer = value_layer.view(value_layer.size(0), output_size[0] * output_size[1], -1) + # change view [b * np, sq, sk] + attention_probs = attention_probs.view(output_size[0] * output_size[1], output_size[2], -1) + # matmul: [b * np, sq, hn] + context_layer = torch.bmm(attention_probs, value_layer.transpose(0, 1)) + # change view [b, np, sq, hn] + context_layer = context_layer.view(*output_size) + # [b, np, sq, hn] --> [sq, b, np, hn] + context_layer = context_layer.permute(2, 0, 1, 3).contiguous() + # [sq, b, np, hn] --> [sq, b, hp] + new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,) + context_layer = context_layer.view(*new_context_layer_shape) + + return context_layer + + +class SelfAttention(torch.nn.Module): + """Parallel self-attention layer abstract class. + + Self-attention layer takes input with size [s, b, h] + and returns output of the same size. + """ + + def __init__(self, config: ChatGLMConfig, layer_number, device=None): + super(SelfAttention, self).__init__() + self.layer_number = max(1, layer_number) + + self.projection_size = config.kv_channels * config.num_attention_heads + + # Per attention head and per partition values. + self.hidden_size_per_attention_head = self.projection_size // config.num_attention_heads + self.num_attention_heads_per_partition = config.num_attention_heads + + self.multi_query_attention = config.multi_query_attention + self.qkv_hidden_size = 3 * self.projection_size + if self.multi_query_attention: + self.num_multi_query_groups_per_partition = config.multi_query_group_num + self.qkv_hidden_size = ( + self.projection_size + 2 * self.hidden_size_per_attention_head * config.multi_query_group_num + ) + self.query_key_value = nn.Linear(config.hidden_size, self.qkv_hidden_size, + bias=config.add_bias_linear or config.add_qkv_bias, + device=device, **_config_to_kwargs(config) + ) + + self.core_attention = CoreAttention(config, self.layer_number) + + # Output. + self.dense = nn.Linear(self.projection_size, config.hidden_size, bias=config.add_bias_linear, + device=device, **_config_to_kwargs(config) + ) + + def _allocate_memory(self, inference_max_sequence_len, batch_size, device=None, dtype=None): + if self.multi_query_attention: + num_attention_heads = self.num_multi_query_groups_per_partition + else: + num_attention_heads = self.num_attention_heads_per_partition + return torch.empty( + inference_max_sequence_len, + batch_size, + num_attention_heads, + self.hidden_size_per_attention_head, + dtype=dtype, + device=device, + ) + + def forward( + self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True + ): + # hidden_states: [sq, b, h] + + # ================================================= + # Pre-allocate memory for key-values for inference. + # ================================================= + # ===================== + # Query, Key, and Value + # ===================== + + # Attention heads [sq, b, h] --> [sq, b, (np * 3 * hn)] + mixed_x_layer = self.query_key_value(hidden_states) + + if self.multi_query_attention: + (query_layer, key_layer, value_layer) = mixed_x_layer.split( + [ + self.num_attention_heads_per_partition * self.hidden_size_per_attention_head, + self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head, + self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head, + ], + dim=-1, + ) + query_layer = query_layer.view( + query_layer.size()[:-1] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head) + ) + key_layer = key_layer.view( + key_layer.size()[:-1] + (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head) + ) + value_layer = value_layer.view( + value_layer.size()[:-1] + + (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head) + ) + else: + new_tensor_shape = mixed_x_layer.size()[:-1] + \ + (self.num_attention_heads_per_partition, + 3 * self.hidden_size_per_attention_head) + mixed_x_layer = mixed_x_layer.view(*new_tensor_shape) + + # [sq, b, np, 3 * hn] --> 3 [sq, b, np, hn] + (query_layer, key_layer, value_layer) = split_tensor_along_last_dim(mixed_x_layer, 3) + + # apply relative positional encoding (rotary embedding) + if rotary_pos_emb is not None: + query_layer = apply_rotary_pos_emb(query_layer, rotary_pos_emb) + key_layer = apply_rotary_pos_emb(key_layer, rotary_pos_emb) + + # adjust key and value for inference + if kv_cache is not None: + cache_k, cache_v = kv_cache + key_layer = torch.cat((cache_k, key_layer), dim=0) + value_layer = torch.cat((cache_v, value_layer), dim=0) + if use_cache: + kv_cache = (key_layer, value_layer) + else: + kv_cache = None + + if self.multi_query_attention: + key_layer = key_layer.unsqueeze(-2) + key_layer = key_layer.expand( + -1, -1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1 + ) + key_layer = key_layer.contiguous().view( + key_layer.size()[:2] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head) + ) + value_layer = value_layer.unsqueeze(-2) + value_layer = value_layer.expand( + -1, -1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1 + ) + value_layer = value_layer.contiguous().view( + value_layer.size()[:2] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head) + ) + + # ================================== + # core attention computation + # ================================== + + context_layer = self.core_attention(query_layer, key_layer, value_layer, attention_mask) + + # ================= + # Output. [sq, b, h] + # ================= + + output = self.dense(context_layer) + + return output, kv_cache + + +def _config_to_kwargs(args): + common_kwargs = { + "dtype": args.torch_dtype, + } + return common_kwargs + + +class MLP(torch.nn.Module): + """MLP. + + MLP will take the input with h hidden state, project it to 4*h + hidden dimension, perform nonlinear transformation, and project the + state back into h hidden dimension. + """ + + def __init__(self, config: ChatGLMConfig, device=None): + super(MLP, self).__init__() + + self.add_bias = config.add_bias_linear + + # Project to 4h. If using swiglu double the output width, see https://arxiv.org/pdf/2002.05202.pdf + self.dense_h_to_4h = nn.Linear( + config.hidden_size, + config.ffn_hidden_size * 2, + bias=self.add_bias, + device=device, + **_config_to_kwargs(config) + ) + + def swiglu(x): + x = torch.chunk(x, 2, dim=-1) + return F.silu(x[0]) * x[1] + + self.activation_func = swiglu + + # Project back to h. + self.dense_4h_to_h = nn.Linear( + config.ffn_hidden_size, + config.hidden_size, + bias=self.add_bias, + device=device, + **_config_to_kwargs(config) + ) + + def forward(self, hidden_states): + # [s, b, 4hp] + intermediate_parallel = self.dense_h_to_4h(hidden_states) + intermediate_parallel = self.activation_func(intermediate_parallel) + # [s, b, h] + output = self.dense_4h_to_h(intermediate_parallel) + return output + + +class GLMBlock(torch.nn.Module): + """A single transformer layer. + + Transformer layer takes input with size [s, b, h] and returns an + output of the same size. + """ + + def __init__(self, config: ChatGLMConfig, layer_number, device=None): + super(GLMBlock, self).__init__() + self.layer_number = layer_number + + self.apply_residual_connection_post_layernorm = config.apply_residual_connection_post_layernorm + + self.fp32_residual_connection = config.fp32_residual_connection + + LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm + # Layernorm on the input data. + self.input_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device, + dtype=config.torch_dtype) + + # Self attention. + self.self_attention = SelfAttention(config, layer_number, device=device) + self.hidden_dropout = config.hidden_dropout + + # Layernorm on the attention output + self.post_attention_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device, + dtype=config.torch_dtype) + + # MLP + self.mlp = MLP(config, device=device) + + def forward( + self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True, + ): + # hidden_states: [s, b, h] + + # Layer norm at the beginning of the transformer layer. + layernorm_output = self.input_layernorm(hidden_states) + # Self attention. + attention_output, kv_cache = self.self_attention( + layernorm_output, + attention_mask, + rotary_pos_emb, + kv_cache=kv_cache, + use_cache=use_cache + ) + + # Residual connection. + if self.apply_residual_connection_post_layernorm: + residual = layernorm_output + else: + residual = hidden_states + + layernorm_input = torch.nn.functional.dropout(attention_output, p=self.hidden_dropout, training=self.training) + layernorm_input = residual + layernorm_input + + # Layer norm post the self attention. + layernorm_output = self.post_attention_layernorm(layernorm_input) + + # MLP. + mlp_output = self.mlp(layernorm_output) + + # Second residual connection. + if self.apply_residual_connection_post_layernorm: + residual = layernorm_output + else: + residual = layernorm_input + + output = torch.nn.functional.dropout(mlp_output, p=self.hidden_dropout, training=self.training) + output = residual + output + + return output, kv_cache + + +class GLMTransformer(torch.nn.Module): + """Transformer class.""" + + def __init__(self, config: ChatGLMConfig, device=None): + super(GLMTransformer, self).__init__() + + self.fp32_residual_connection = config.fp32_residual_connection + self.post_layer_norm = config.post_layer_norm + + # Number of layers. + self.num_layers = config.num_layers + + # Transformer layers. + def build_layer(layer_number): + return GLMBlock(config, layer_number, device=device) + + self.layers = torch.nn.ModuleList([build_layer(i + 1) for i in range(self.num_layers)]) + + if self.post_layer_norm: + LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm + # Final layer norm before output. + self.final_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device, + dtype=config.torch_dtype) + + self.gradient_checkpointing = False + + def _get_layer(self, layer_number): + return self.layers[layer_number] + + def forward( + self, hidden_states, attention_mask, rotary_pos_emb, kv_caches=None, + use_cache: Optional[bool] = True, + output_hidden_states: Optional[bool] = False, + ): + if not kv_caches: + kv_caches = [None for _ in range(self.num_layers)] + presents = () if use_cache else None + if self.gradient_checkpointing and self.training: + if use_cache: + logger.warning_once( + "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..." + ) + use_cache = False + + all_self_attentions = None + all_hidden_states = () if output_hidden_states else None + for index in range(self.num_layers): + if output_hidden_states: + all_hidden_states = all_hidden_states + (hidden_states,) + + layer = self._get_layer(index) + if self.gradient_checkpointing and self.training: + layer_ret = torch.utils.checkpoint.checkpoint( + layer, + hidden_states, + attention_mask, + rotary_pos_emb, + kv_caches[index], + use_cache + ) + else: + layer_ret = layer( + hidden_states, + attention_mask, + rotary_pos_emb, + kv_cache=kv_caches[index], + use_cache=use_cache + ) + hidden_states, kv_cache = layer_ret + if use_cache: + presents = presents + (kv_cache,) + + if output_hidden_states: + all_hidden_states = all_hidden_states + (hidden_states,) + + # Final layer norm. + if self.post_layer_norm: + hidden_states = self.final_layernorm(hidden_states) + + return hidden_states, presents, all_hidden_states, all_self_attentions + + +class ChatGLMPreTrainedModel(PreTrainedModel): + """ + An abstract class to handle weights initialization and + a simple interface for downloading and loading pretrained models. + """ + + is_parallelizable = False + supports_gradient_checkpointing = True + config_class = ChatGLMConfig + base_model_prefix = "transformer" + _no_split_modules = ["GLMBlock"] + + def _init_weights(self, module: nn.Module): + """Initialize the weights.""" + return + + def get_masks(self, input_ids, past_key_values, padding_mask=None): + batch_size, seq_length = input_ids.shape + full_attention_mask = torch.ones(batch_size, seq_length, seq_length, device=input_ids.device) + full_attention_mask.tril_() + past_length = 0 + if past_key_values: + past_length = past_key_values[0][0].shape[0] + if past_length: + full_attention_mask = torch.cat((torch.ones(batch_size, seq_length, past_length, + device=input_ids.device), full_attention_mask), dim=-1) + if padding_mask is not None: + full_attention_mask = full_attention_mask * padding_mask.unsqueeze(1) + if not past_length and padding_mask is not None: + full_attention_mask -= padding_mask.unsqueeze(-1) - 1 + full_attention_mask = (full_attention_mask < 0.5).bool() + full_attention_mask.unsqueeze_(1) + return full_attention_mask + + def get_position_ids(self, input_ids, device): + batch_size, seq_length = input_ids.shape + position_ids = torch.arange(seq_length, dtype=torch.long, device=device).unsqueeze(0).repeat(batch_size, 1) + return position_ids + + def _set_gradient_checkpointing(self, module, value=False): + if isinstance(module, GLMTransformer): + module.gradient_checkpointing = value + + +class Embedding(torch.nn.Module): + """Language model embeddings.""" + + def __init__(self, config: ChatGLMConfig, device=None): + super(Embedding, self).__init__() + + self.hidden_size = config.hidden_size + # Word embeddings (parallel). + self.word_embeddings = nn.Embedding( + config.padded_vocab_size, + self.hidden_size, + dtype=config.torch_dtype, + device=device + ) + self.fp32_residual_connection = config.fp32_residual_connection + + def forward(self, input_ids): + # Embeddings. + words_embeddings = self.word_embeddings(input_ids) + embeddings = words_embeddings + # Data format change to avoid explicit tranposes : [b s h] --> [s b h]. + embeddings = embeddings.transpose(0, 1).contiguous() + # If the input flag for fp32 residual connection is set, convert for float. + if self.fp32_residual_connection: + embeddings = embeddings.float() + return embeddings + + +class ChatGLMModel(ChatGLMPreTrainedModel): + def __init__(self, config: ChatGLMConfig, device=None, empty_init=True): + super().__init__(config) + if empty_init: + init_method = skip_init + else: + init_method = default_init + init_kwargs = {} + if device is not None: + init_kwargs["device"] = device + self.embedding = init_method(Embedding, config, **init_kwargs) + self.num_layers = config.num_layers + self.multi_query_group_num = config.multi_query_group_num + self.kv_channels = config.kv_channels + + # Rotary positional embeddings + self.seq_length = config.seq_length + rotary_dim = ( + config.hidden_size // config.num_attention_heads if config.kv_channels is None else config.kv_channels + ) + + self.rotary_pos_emb = RotaryEmbedding(rotary_dim // 2, original_impl=config.original_rope, device=device, + dtype=config.torch_dtype) + self.encoder = init_method(GLMTransformer, config, **init_kwargs) + self.output_layer = init_method(nn.Linear, config.hidden_size, config.padded_vocab_size, bias=False, + dtype=config.torch_dtype, **init_kwargs) + self.pre_seq_len = config.pre_seq_len + self.prefix_projection = config.prefix_projection + if self.pre_seq_len is not None: + for param in self.parameters(): + param.requires_grad = False + self.prefix_tokens = torch.arange(self.pre_seq_len).long() + self.prefix_encoder = PrefixEncoder(config) + self.dropout = torch.nn.Dropout(0.1) + + def get_input_embeddings(self): + return self.embedding.word_embeddings + + def get_prompt(self, batch_size, device, dtype=torch.half): + prefix_tokens = self.prefix_tokens.unsqueeze(0).expand(batch_size, -1).to(device) + past_key_values = self.prefix_encoder(prefix_tokens).type(dtype) + past_key_values = past_key_values.view( + batch_size, + self.pre_seq_len, + self.num_layers * 2, + self.multi_query_group_num, + self.kv_channels + ) + # seq_len, b, nh, hidden_size + past_key_values = self.dropout(past_key_values) + past_key_values = past_key_values.permute([2, 1, 0, 3, 4]).split(2) + return past_key_values + + def forward( + self, + input_ids, + position_ids: Optional[torch.Tensor] = None, + attention_mask: Optional[torch.BoolTensor] = None, + full_attention_mask: Optional[torch.BoolTensor] = None, + past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None, + inputs_embeds: Optional[torch.Tensor] = None, + use_cache: Optional[bool] = None, + output_hidden_states: Optional[bool] = None, + return_dict: Optional[bool] = None, + ): + output_hidden_states = ( + output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states + ) + use_cache = use_cache if use_cache is not None else self.config.use_cache + return_dict = return_dict if return_dict is not None else self.config.use_return_dict + + batch_size, seq_length = input_ids.shape + + if inputs_embeds is None: + inputs_embeds = self.embedding(input_ids) + + if self.pre_seq_len is not None: + if past_key_values is None: + past_key_values = self.get_prompt(batch_size=batch_size, device=input_ids.device, + dtype=inputs_embeds.dtype) + if attention_mask is not None: + attention_mask = torch.cat([attention_mask.new_ones((batch_size, self.pre_seq_len)), + attention_mask], dim=-1) + + if full_attention_mask is None: + if (attention_mask is not None and not attention_mask.all()) or (past_key_values and seq_length != 1): + full_attention_mask = self.get_masks(input_ids, past_key_values, padding_mask=attention_mask) + + # Rotary positional embeddings + rotary_pos_emb = self.rotary_pos_emb(self.seq_length) + if position_ids is not None: + rotary_pos_emb = rotary_pos_emb[position_ids] + else: + rotary_pos_emb = rotary_pos_emb[None, :seq_length] + rotary_pos_emb = rotary_pos_emb.transpose(0, 1).contiguous() + + # Run encoder. + hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder( + inputs_embeds, full_attention_mask, rotary_pos_emb=rotary_pos_emb, + kv_caches=past_key_values, use_cache=use_cache, output_hidden_states=output_hidden_states + ) + + if not return_dict: + return tuple(v for v in [hidden_states, presents, all_hidden_states, all_self_attentions] if v is not None) + + return BaseModelOutputWithPast( + last_hidden_state=hidden_states, + past_key_values=presents, + hidden_states=all_hidden_states, + attentions=all_self_attentions, + ) + + def quantize(self, weight_bit_width: int): + from .quantization import quantize + quantize(self.encoder, weight_bit_width) + return self + + +class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel): + def __init__(self, config: ChatGLMConfig, empty_init=True, device=None): + super().__init__(config) + + self.max_sequence_length = config.max_length + self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device) + self.config = config + self.quantized = False + + if self.config.quantization_bit: + self.quantize(self.config.quantization_bit, empty_init=True) + + def _update_model_kwargs_for_generation( + self, + outputs: ModelOutput, + model_kwargs: Dict[str, Any], + is_encoder_decoder: bool = False, + standardize_cache_format: bool = False, + ) -> Dict[str, Any]: + # update past_key_values + model_kwargs["past_key_values"] = self._extract_past_from_model_output( + outputs, standardize_cache_format=standardize_cache_format + ) + + # update attention mask + if "attention_mask" in model_kwargs: + attention_mask = model_kwargs["attention_mask"] + model_kwargs["attention_mask"] = torch.cat( + [attention_mask, attention_mask.new_ones((attention_mask.shape[0], 1))], dim=-1 + ) + + # update position ids + if "position_ids" in model_kwargs: + position_ids = model_kwargs["position_ids"] + new_position_id = position_ids[..., -1:].clone() + new_position_id += 1 + model_kwargs["position_ids"] = torch.cat( + [position_ids, new_position_id], dim=-1 + ) + + model_kwargs["is_first_forward"] = False + return model_kwargs + + def prepare_inputs_for_generation( + self, + input_ids: torch.LongTensor, + past_key_values: Optional[torch.Tensor] = None, + attention_mask: Optional[torch.Tensor] = None, + position_ids: Optional[torch.Tensor] = None, + use_cache: Optional[bool] = None, + is_first_forward: bool = True, + **kwargs + ) -> dict: + # only last token for input_ids if past is not None + if position_ids is None: + position_ids = self.get_position_ids(input_ids, device=input_ids.device) + if not is_first_forward: + if past_key_values is not None: + position_ids = position_ids[..., -1:] + input_ids = input_ids[:, -1:] + return { + "input_ids": input_ids, + "past_key_values": past_key_values, + "position_ids": position_ids, + "attention_mask": attention_mask, + "return_last_logit": True, + "use_cache": use_cache + } + + def forward( + self, + input_ids: Optional[torch.Tensor] = None, + position_ids: Optional[torch.Tensor] = None, + attention_mask: Optional[torch.Tensor] = None, + past_key_values: Optional[Tuple[torch.FloatTensor]] = None, + inputs_embeds: Optional[torch.Tensor] = None, + labels: Optional[torch.Tensor] = None, + use_cache: Optional[bool] = None, + output_attentions: Optional[bool] = None, + output_hidden_states: Optional[bool] = None, + return_dict: Optional[bool] = None, + return_last_logit: Optional[bool] = False, + ): + use_cache = use_cache if use_cache is not None else self.config.use_cache + return_dict = return_dict if return_dict is not None else self.config.use_return_dict + + transformer_outputs = self.transformer( + input_ids=input_ids, + position_ids=position_ids, + attention_mask=attention_mask, + past_key_values=past_key_values, + inputs_embeds=inputs_embeds, + use_cache=use_cache, + output_hidden_states=output_hidden_states, + return_dict=return_dict, + ) + + hidden_states = transformer_outputs[0] + if return_last_logit: + hidden_states = hidden_states[-1:] + lm_logits = self.transformer.output_layer(hidden_states) + lm_logits = lm_logits.transpose(0, 1).contiguous() + + loss = None + if labels is not None: + lm_logits = lm_logits.to(torch.float32) + + # Shift so that tokens < n predict n + shift_logits = lm_logits[..., :-1, :].contiguous() + shift_labels = labels[..., 1:].contiguous() + # Flatten the tokens + loss_fct = CrossEntropyLoss(ignore_index=-100) + loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1)) + + lm_logits = lm_logits.to(hidden_states.dtype) + loss = loss.to(hidden_states.dtype) + + if not return_dict: + output = (lm_logits,) + transformer_outputs[1:] + return ((loss,) + output) if loss is not None else output + + return CausalLMOutputWithPast( + loss=loss, + logits=lm_logits, + past_key_values=transformer_outputs.past_key_values, + hidden_states=transformer_outputs.hidden_states, + attentions=transformer_outputs.attentions, + ) + + @staticmethod + def _reorder_cache( + past: Tuple[Tuple[torch.Tensor, torch.Tensor], ...], beam_idx: torch.LongTensor + ) -> Tuple[Tuple[torch.Tensor, torch.Tensor], ...]: + """ + This function is used to re-order the `past_key_values` cache if [`~PreTrainedModel.beam_search`] or + [`~PreTrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct + beam_idx at every generation step. + + Output shares the same memory storage as `past`. + """ + return tuple( + ( + layer_past[0].index_select(1, beam_idx.to(layer_past[0].device)), + layer_past[1].index_select(1, beam_idx.to(layer_past[1].device)), + ) + for layer_past in past + ) + + def process_response(self, response): + response = response.strip() + response = response.replace("[[训练时间]]", "2023年") + return response + + def build_inputs(self, tokenizer, query: str, history: List[Tuple[str, str]] = None): + prompt = tokenizer.build_prompt(query, history=history) + inputs = tokenizer([prompt], return_tensors="pt") + inputs = inputs.to(self.device) + return inputs + + def build_stream_inputs(self, tokenizer, query: str, history: List[Tuple[str, str]] = None): + if history: + prompt = "\n\n[Round {}]\n\n问：{}\n\n答：".format(len(history) + 1, query) + input_ids = tokenizer.encode(prompt, add_special_tokens=False) + input_ids = input_ids[1:] + inputs = tokenizer.batch_encode_plus([(input_ids, None)], return_tensors="pt", add_special_tokens=False) + else: + prompt = "[Round {}]\n\n问：{}\n\n答：".format(len(history) + 1, query) + inputs = tokenizer([prompt], return_tensors="pt") + inputs = inputs.to(self.device) + return inputs + + @torch.inference_mode() + def chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, max_length: int = 8192, num_beams=1, + do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None, **kwargs): + if history is None: + history = [] + if logits_processor is None: + logits_processor = LogitsProcessorList() + logits_processor.append(InvalidScoreLogitsProcessor()) + gen_kwargs = {"max_length": max_length, "num_beams": num_beams, "do_sample": do_sample, "top_p": top_p, + "temperature": temperature, "logits_processor": logits_processor, **kwargs} + inputs = self.build_inputs(tokenizer, query, history=history) + outputs = self.generate(**inputs, **gen_kwargs) + outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):] + response = tokenizer.decode(outputs) + response = self.process_response(response) + history = history + [(query, response)] + return response, history + + @torch.inference_mode() + def stream_chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, past_key_values=None, + max_length: int = 8192, do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None, + return_past_key_values=False, **kwargs): + if history is None: + history = [] + if logits_processor is None: + logits_processor = LogitsProcessorList() + logits_processor.append(InvalidScoreLogitsProcessor()) + gen_kwargs = {"max_length": max_length, "do_sample": do_sample, "top_p": top_p, + "temperature": temperature, "logits_processor": logits_processor, **kwargs} + if past_key_values is None and not return_past_key_values: + inputs = self.build_inputs(tokenizer, query, history=history) + else: + inputs = self.build_stream_inputs(tokenizer, query, history=history) + if past_key_values is not None: + past_length = past_key_values[0][0].shape[0] + if self.transformer.pre_seq_len is not None: + past_length -= self.transformer.pre_seq_len + inputs.position_ids += past_length + attention_mask = inputs.attention_mask + attention_mask = torch.cat((attention_mask.new_ones(1, past_length), attention_mask), dim=1) + inputs['attention_mask'] = attention_mask + for outputs in self.stream_generate(**inputs, past_key_values=past_key_values, + return_past_key_values=return_past_key_values, **gen_kwargs): + if return_past_key_values: + outputs, past_key_values = outputs + outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):] + response = tokenizer.decode(outputs) + if response and response[-1] != "�": + response = self.process_response(response) + new_history = history + [(query, response)] + if return_past_key_values: + yield response, new_history, past_key_values + else: + yield response, new_history + + @torch.inference_mode() + def stream_generate( + self, + input_ids, + generation_config: Optional[GenerationConfig] = None, + logits_processor: Optional[LogitsProcessorList] = None, + stopping_criteria: Optional[StoppingCriteriaList] = None, + prefix_allowed_tokens_fn: Optional[Callable[[int, torch.Tensor], List[int]]] = None, + return_past_key_values=False, + **kwargs, + ): + batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1] + + if generation_config is None: + generation_config = self.generation_config + generation_config = copy.deepcopy(generation_config) + model_kwargs = generation_config.update(**kwargs) + model_kwargs["use_cache"] = generation_config.use_cache + bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id + + if isinstance(eos_token_id, int): + eos_token_id = [eos_token_id] + + has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None + if has_default_max_length and generation_config.max_new_tokens is None: + warnings.warn( + f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. " + "This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we" + " recommend using `max_new_tokens` to control the maximum length of the generation.", + UserWarning, + ) + elif generation_config.max_new_tokens is not None: + generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length + if not has_default_max_length: + logger.warn( + f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(=" + f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. " + "Please refer to the documentation for more information. " + "(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)", + UserWarning, + ) + + if input_ids_seq_length >= generation_config.max_length: + input_ids_string = "decoder_input_ids" if self.config.is_encoder_decoder else "input_ids" + logger.warning( + f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to" + f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider" + " increasing `max_new_tokens`." + ) + + # 2. Set generation parameters if not already defined + logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList() + stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList() + + logits_processor = self._get_logits_processor( + generation_config=generation_config, + input_ids_seq_length=input_ids_seq_length, + encoder_input_ids=input_ids, + prefix_allowed_tokens_fn=prefix_allowed_tokens_fn, + logits_processor=logits_processor, + ) + + stopping_criteria = self._get_stopping_criteria( + generation_config=generation_config, stopping_criteria=stopping_criteria + ) + logits_warper = self._get_logits_warper(generation_config) + + unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1) + scores = None + while True: + model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs) + # forward pass to get next token + outputs = self( + **model_inputs, + return_dict=True, + output_attentions=False, + output_hidden_states=False, + ) + + next_token_logits = outputs.logits[:, -1, :] + + # pre-process distribution + next_token_scores = logits_processor(input_ids, next_token_logits) + next_token_scores = logits_warper(input_ids, next_token_scores) + + # sample + probs = nn.functional.softmax(next_token_scores, dim=-1) + if generation_config.do_sample: + next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1) + else: + next_tokens = torch.argmax(probs, dim=-1) + + # update generated ids, model inputs, and length for next step + input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1) + model_kwargs = self._update_model_kwargs_for_generation( + outputs, model_kwargs, is_encoder_decoder=self.config.is_encoder_decoder + ) + unfinished_sequences = unfinished_sequences.mul((sum(next_tokens != i for i in eos_token_id)).long()) + if return_past_key_values: + yield input_ids, outputs.past_key_values + else: + yield input_ids + # stop when each sentence is finished, or if we exceed the maximum length + if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores): + break + + def quantize(self, bits: int, empty_init=False, device=None, **kwargs): + if bits == 0: + return + + from .quantization import quantize + + if self.quantized: + logger.info("Already quantized.") + return self + + self.quantized = True + + self.config.quantization_bit = bits + + self.transformer.encoder = quantize(self.transformer.encoder, bits, empty_init=empty_init, device=device, + **kwargs) + return self + + +class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel): + def __init__(self, config: ChatGLMConfig, empty_init=True, device=None): + super().__init__(config) + + self.num_labels = config.num_labels + self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device) + + self.classifier_head = nn.Linear(config.hidden_size, config.num_labels, bias=True, dtype=torch.half) + if config.classifier_dropout is not None: + self.dropout = nn.Dropout(config.classifier_dropout) + else: + self.dropout = None + self.config = config + + if self.config.quantization_bit: + self.quantize(self.config.quantization_bit, empty_init=True) + + def forward( + self, + input_ids: Optional[torch.LongTensor] = None, + position_ids: Optional[torch.LongTensor] = None, + attention_mask: Optional[torch.Tensor] = None, + full_attention_mask: Optional[torch.Tensor] = None, + past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None, + inputs_embeds: Optional[torch.LongTensor] = None, + labels: Optional[torch.LongTensor] = None, + use_cache: Optional[bool] = None, + output_hidden_states: Optional[bool] = None, + return_dict: Optional[bool] = None, + ) -> Union[Tuple[torch.Tensor, ...], SequenceClassifierOutputWithPast]: + return_dict = return_dict if return_dict is not None else self.config.use_return_dict + + transformer_outputs = self.transformer( + input_ids=input_ids, + position_ids=position_ids, + attention_mask=attention_mask, + full_attention_mask=full_attention_mask, + past_key_values=past_key_values, + inputs_embeds=inputs_embeds, + use_cache=use_cache, + output_hidden_states=output_hidden_states, + return_dict=return_dict, + ) + + hidden_states = transformer_outputs[0] + pooled_hidden_states = hidden_states[-1] + if self.dropout is not None: + pooled_hidden_states = self.dropout(pooled_hidden_states) + logits = self.classifier_head(pooled_hidden_states) + + loss = None + if labels is not None: + if self.config.problem_type is None: + if self.num_labels == 1: + self.config.problem_type = "regression" + elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int): + self.config.problem_type = "single_label_classification" + else: + self.config.problem_type = "multi_label_classification" + + if self.config.problem_type == "regression": + loss_fct = MSELoss() + if self.num_labels == 1: + loss = loss_fct(logits.squeeze().float(), labels.squeeze()) + else: + loss = loss_fct(logits.float(), labels) + elif self.config.problem_type == "single_label_classification": + loss_fct = CrossEntropyLoss() + loss = loss_fct(logits.view(-1, self.num_labels).float(), labels.view(-1)) + elif self.config.problem_type == "multi_label_classification": + loss_fct = BCEWithLogitsLoss() + loss = loss_fct(logits.float(), labels.view(-1, self.num_labels)) + + if not return_dict: + output = (logits,) + transformer_outputs[1:] + return ((loss,) + output) if loss is not None else output + + return SequenceClassifierOutputWithPast( + loss=loss, + logits=logits, + past_key_values=transformer_outputs.past_key_values, + hidden_states=transformer_outputs.hidden_states, + attentions=transformer_outputs.attentions, + ) diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..d2510f3 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a455d80479b771e8579dd9628bbafbfa573198e70698c0ed9fdaf9eae22c9b7 +size 9986264643 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..c2bc0e8 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:603c5280e429908980c7ef6534657f2dfe9514a8385e73556e8b5566ff5844f7 +size 2500975567 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..ab25cbc --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,207 @@ +{ + "metadata": { + "total_size": 12487168064 + }, + "weight_map": { + "transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.final_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "transformer.output_layer.weight": "pytorch_model-00002-of-00002.bin", + "transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00002.bin" + } +} diff --git a/quantization.py b/quantization.py new file mode 100644 index 0000000..cb95bfe --- /dev/null +++ b/quantization.py @@ -0,0 +1,188 @@ +from torch.nn import Linear +from torch.nn.parameter import Parameter + +import bz2 +import torch +import base64 +import ctypes +from transformers.utils import logging + +from typing import List +from functools import partial + +logger = logging.get_logger(__name__) + +try: + from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up + + class Kernel: + def __init__(self, code: bytes, function_names: List[str]): + self.code = code + self._function_names = function_names + self._cmodule = LazyKernelCModule(self.code) + + for name in self._function_names: + setattr(self, name, KernelFunction(self._cmodule, name)) + + quantization_code = "$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" + + kernels = Kernel( + bz2.decompress(base64.b64decode(quantization_code)), + [ + "int4WeightCompression", + "int4WeightExtractionFloat", + "int4WeightExtractionHalf", + "int8WeightExtractionFloat", + "int8WeightExtractionHalf", + ], + ) +except Exception as exception: + kernels = None + logger.warning("Failed to load cpm_kernels:" + str(exception)) + + +class W8A16Linear(torch.autograd.Function): + @staticmethod + def forward(ctx, inp: torch.Tensor, quant_w: torch.Tensor, scale_w: torch.Tensor, weight_bit_width): + ctx.inp_shape = inp.size() + ctx.weight_bit_width = weight_bit_width + out_features = quant_w.size(0) + inp = inp.contiguous().view(-1, inp.size(-1)) + weight = extract_weight_to_half(quant_w, scale_w, weight_bit_width) + ctx.weight_shape = weight.size() + output = inp.mm(weight.t()) + ctx.save_for_backward(inp, quant_w, scale_w) + return output.view(*(ctx.inp_shape[:-1] + (out_features,))) + + @staticmethod + def backward(ctx, grad_output: torch.Tensor): + inp, quant_w, scale_w = ctx.saved_tensors + weight = extract_weight_to_half(quant_w, scale_w, ctx.weight_bit_width) + grad_output = grad_output.contiguous().view(-1, weight.size(0)) + grad_input = grad_output.mm(weight) + grad_weight = grad_output.t().mm(inp) + return grad_input.view(ctx.inp_shape), grad_weight.view(ctx.weight_shape), None, None + + +def compress_int4_weight(weight: torch.Tensor): # (n, m) + with torch.cuda.device(weight.device): + n, m = weight.size(0), weight.size(1) + assert m % 2 == 0 + m = m // 2 + out = torch.empty(n, m, dtype=torch.int8, device="cuda") + stream = torch.cuda.current_stream() + + gridDim = (n, 1, 1) + blockDim = (min(round_up(m, 32), 1024), 1, 1) + + kernels.int4WeightCompression( + gridDim, + blockDim, + 0, + stream, + [ctypes.c_void_p(weight.data_ptr()), ctypes.c_void_p(out.data_ptr()), ctypes.c_int32(n), ctypes.c_int32(m)], + ) + return out + + +def extract_weight_to_half(weight: torch.Tensor, scale_list: torch.Tensor, source_bit_width: int): + assert scale_list.dtype in [torch.half, torch.bfloat16] + assert weight.dtype in [torch.int8] + if source_bit_width == 8: + return weight.to(scale_list.dtype) * scale_list[:, None] + elif source_bit_width == 4: + func = ( + kernels.int4WeightExtractionHalf if scale_list.dtype == torch.half else kernels.int4WeightExtractionBFloat16 + ) + else: + assert False, "Unsupported bit-width" + + with torch.cuda.device(weight.device): + n, m = weight.size(0), weight.size(1) + out = torch.empty(n, m * (8 // source_bit_width), dtype=scale_list.dtype, device="cuda") + stream = torch.cuda.current_stream() + + gridDim = (n, 1, 1) + blockDim = (min(round_up(m, 32), 1024), 1, 1) + + func( + gridDim, + blockDim, + 0, + stream, + [ + ctypes.c_void_p(weight.data_ptr()), + ctypes.c_void_p(scale_list.data_ptr()), + ctypes.c_void_p(out.data_ptr()), + ctypes.c_int32(n), + ctypes.c_int32(m), + ], + ) + return out + + +class QuantizedLinear(torch.nn.Module): + def __init__(self, weight_bit_width: int, weight, bias=None, device="cpu", dtype=None, empty_init=False, *args, + **kwargs): + super().__init__() + self.weight_bit_width = weight_bit_width + + shape = weight.shape + + if weight is None or empty_init: + self.weight = torch.empty(shape[0], shape[1] * weight_bit_width // 8, dtype=torch.int8, device=device) + self.weight_scale = torch.empty(shape[0], dtype=dtype, device=device) + else: + self.weight_scale = weight.abs().max(dim=-1).values / ((2 ** (weight_bit_width - 1)) - 1) + self.weight = torch.round(weight / self.weight_scale[:, None]).to(torch.int8) + if weight_bit_width == 4: + self.weight = compress_int4_weight(self.weight) + + self.weight = Parameter(self.weight.to(device), requires_grad=False) + self.weight_scale = Parameter(self.weight_scale.to(device), requires_grad=False) + self.bias = Parameter(bias.to(device), requires_grad=False) if bias is not None else None + + def forward(self, input): + output = W8A16Linear.apply(input, self.weight, self.weight_scale, self.weight_bit_width) + if self.bias is not None: + output = output + self.bias + return output + + +def quantize(model, weight_bit_width, empty_init=False, device=None): + """Replace fp16 linear with quantized linear""" + for layer in model.layers: + layer.self_attention.query_key_value = QuantizedLinear( + weight_bit_width=weight_bit_width, + weight=layer.self_attention.query_key_value.weight.to(torch.cuda.current_device()), + bias=layer.self_attention.query_key_value.bias, + dtype=layer.self_attention.query_key_value.weight.dtype, + device=layer.self_attention.query_key_value.weight.device if device is None else device, + empty_init=empty_init + ) + layer.self_attention.dense = QuantizedLinear( + weight_bit_width=weight_bit_width, + weight=layer.self_attention.dense.weight.to(torch.cuda.current_device()), + bias=layer.self_attention.dense.bias, + dtype=layer.self_attention.dense.weight.dtype, + device=layer.self_attention.dense.weight.device if device is None else device, + empty_init=empty_init + ) + layer.mlp.dense_h_to_4h = QuantizedLinear( + weight_bit_width=weight_bit_width, + weight=layer.mlp.dense_h_to_4h.weight.to(torch.cuda.current_device()), + bias=layer.mlp.dense_h_to_4h.bias, + dtype=layer.mlp.dense_h_to_4h.weight.dtype, + device=layer.mlp.dense_h_to_4h.weight.device if device is None else device, + empty_init=empty_init + ) + layer.mlp.dense_4h_to_h = QuantizedLinear( + weight_bit_width=weight_bit_width, + weight=layer.mlp.dense_4h_to_h.weight.to(torch.cuda.current_device()), + bias=layer.mlp.dense_4h_to_h.bias, + dtype=layer.mlp.dense_4h_to_h.weight.dtype, + device=layer.mlp.dense_4h_to_h.weight.device if device is None else device, + empty_init=empty_init + ) + + return model diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..0967ef4 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{} diff --git a/tokenization_chatglm.py b/tokenization_chatglm.py new file mode 100644 index 0000000..50b61e2 --- /dev/null +++ b/tokenization_chatglm.py @@ -0,0 +1,278 @@ +import os +import re +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 + self.role_special_token_expression = "|".join([re.escape(token) for token in special_tokens]) # for apply_chat_template + + def tokenize(self, s: str, encode_special_tokens=False): + if encode_special_tokens: + last_index = 0 + t = [] + for match in re.finditer(self.role_special_token_expression, s): + if last_index < match.start(): + t.extend(self.sp_model.EncodeAsPieces(s[last_index:match.start()])) + t.append(s[match.start():match.end()]) + last_index = match.end() + if last_index < len(s): + t.extend(self.sp_model.EncodeAsPieces(s[last_index:])) + return t + else: + 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: + text, buffer = "", [] + for token in t: + if token in self.index_special_tokens: + if buffer: + text += self.sp_model.decode(buffer) + buffer = [] + text += self.index_special_tokens[token] + else: + buffer.append(token) + if buffer: + text += self.sp_model.decode(buffer) + return text + + 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", clean_up_tokenization_spaces=False, encode_special_tokens=False, **kwargs): + self.name = "GLMTokenizer" + + self.vocab_file = vocab_file + self.tokenizer = SPTokenizer(vocab_file) + self.special_tokens = { + "": self.tokenizer.bos_id, + "": self.tokenizer.eos_id, + "": self.tokenizer.pad_id + } + self.encode_special_tokens = encode_special_tokens + super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces, **kwargs) + + 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 "" + + @property + def pad_token_id(self): + return self.get_command("") + + @property + def eos_token(self) -> str: + return "" + + @property + def eos_token_id(self): + return self.get_command("") + + @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, encode_special_tokens=self.encode_special_tokens) + + 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("")] + 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 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8a80076 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2 +size 1018370 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..1d3c668 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "added_tokens_decoder": { + "64790": { + "content": "[gMASK]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "64792": { + "content": "sop", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "auto_map": { + "AutoTokenizer": [ + "tokenization_chatglm.ChatGLMTokenizer", + null + ] + }, + "chat_template": "{% set ns = namespace() %}[gMASK]sop{% for message in messages %}{% if loop.first %}{% set ns.bot_name = message['bot_name'] %}{% set ns.user_name = message['user_name'] %}以下是一段{{ message['bot_name'] }}和{{ message['user_name'] }}之间的对话。{%+ if message['bot_profile'] is defined and message['bot_profile']|length +%}\n关于{{ message['bot_name'] }}的信息：{{ message['bot_profile']|replace('\n', ' ') }}{% endif %}{%+ if message['user_profile'] is defined and message['user_profile']|length +%}\n关于{{ message['user_name'] }}的信息：{{ message['user_profile']|replace('\n', ' ') }}{% endif %}{%+ else +%}\n[{% if message['role'] == 'user' %}{{ ns.user_name }}{% else %}{{ ns.bot_name }}{% endif %}]{{ message['content']|replace('\n', ' ') }}{% endif %}{% endfor %}{%+ if add_generation_prompt +%}\n[{{ ns.bot_name }}]{% endif %}", + "clean_up_tokenization_spaces": true, + "do_lower_case": false, + "model_max_length": 1000000000000000019884624838656, + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "ChatGLMTokenizer" +}