commit d59f981cc72ffcadbead8eadc48b88ee312cdd10 Author: ModelHub XC Date: Mon Jul 13 23:21:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: tyang816/MedChatZH Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..efe7785 --- /dev/null +++ b/README.md @@ -0,0 +1,52 @@ +--- +license: apache-2.0 +datasets: +- tyang816/MedChatZH +language: +- zh + +--- + +# MedChatZH + +--- + +## MedChatZH中文微调参数 + +基于Baichuan-7B在中医书籍数据和医疗指令对话数据上训练，使其具备较强的中文医疗对话能力，**能够理解中医问题**。 + +Github：[**MedChatZH-7B**](https://github.com/tyang816/MedChatZH) + +## 🚀 结果 + +| 问题 | 回答 | +| :----------------------------------------------------------- | ------------------------------------------------------------ | +| 中医治脱发有效吗脱发5、6年了，明显比以前少了很多，脱发位置比较均衡，没有突出掉的比较多的地方，我的发质比较硬，头发生长也较快。 | 中药治疗脱发的效果因人而异，但对于您这种头发质量好且生长速度快的患者来说，中药可能是一个不错的选择。一些常用的中药方剂包括六味地黄丸、四物汤等，这些药物可以滋养肝肾，促进血液循环和毛囊营养供应，从而改善脱发问题。此外，还可以通过针灸、艾灸等方式进行辅助治疗。但是需要注意的是，中药治疗需要长期坚持才能见效，同时还需要注意饮食和生活习惯等方面的问题，以达到更好的疗效。建议您咨询专业的中医医生或皮肤科医生，根据个人情况制定个性化的治疗方案。 | +| 脑萎缩中医如何治疗？中医治疗脑萎缩好吗？脑萎缩中医如何治疗？中医治疗脑萎缩好吗？ | 中药、针灸和推拿等。中药可以根据患者的具体情况进行配方，以达到调节身体机能的目的;针灸可以通过刺激穴位来改善血液循环和神经功能;推拿则可以通过按摩头部和颈部肌肉来缓解疼痛和僵硬感。需要注意的是，中医治疗需要长期坚持才能取得良好的效果，同时还需要结合其他康复措施和生活方式改变，如合理饮食、适量运动、保持心情愉悦等等。如果您有任何疑问或不适，请及时咨询医生。 | +| 中药治疗肺癌效果好吗？麻烦医生了中药治疗肺癌效果好吗？我家老人肺癌晚期，听人说中医可以治疗肺癌真的吗？效果怎么样？ | 中药在治疗肺癌方面有一定的作用。但是需要注意的是，中药并不是所有人都适用的，需要根据患者的具体情况来选择合适的药物和剂量。此外，中药的疗效也需要长期观察才能确定。对于您家老人的肺癌晚期，建议及时就医并进行综合治疗，包括手术、放化疗等方法。同时也可以考虑结合中医药辅助治疗，但一定要在专业医师指导下进行。希望您的家人早日康复。 | +| 最近脸上总是冒出小痘痘……为什么呢？我用的是不吃晚饭减肥，其他都正常的。但是大便的情况很不好，我很头疼的，便秘情况太严重了。最近脸上总是冒出痘痘，额头、脸颊、法令纹那一边一个，还有点疼，有白色的浓…… | 你好，根据你的描述，你可能患有痤疮和便秘的问题。长期不吃饭会导致身体缺乏营养物质，从而影响皮肤的健康状况。建议你在饮食方面要注意均衡摄入各种食物，尤其是蛋白质、维生素A、B族以及矿物质等。此外，你可以尝试一些中药调理，如黄连上清丸或龙胆泻肝丸来缓解症状。对于痤疮问题，可以使用外用药膏进行治疗，例如维甲酸类药物或者过氧化苯甲酰凝胶等。如果症状较为严重，也可以考虑口服抗生素。至于便秘问题，可以通过增加膳食纤维摄入量、多喝水等方式改善。同时，避免过度用力排便也是非常重要的。如果你仍然感到不适，请及时就医并咨询专业医生的意见。希望我的回答能对你有所帮助。 | + +## **🔥 引用** + +如果您使用了我们的模型、代码或数据，请引用： + +``` +@article{tan2024medchatzh, + title={MedChatZH: A tuning LLM for traditional Chinese medicine consultations}, + author={Tan, Yang and Zhang, Zhixing and Li, Mingchen and Pan, Fei and Duan, Hao and Huang, Zijie and Deng, Hua and Yu, Zhuohang and Yang, Chen and Shen, Guoyang and others}, + journal={Computers in Biology and Medicine}, + pages={108290}, + year={2024}, + publisher={Elsevier} +} +``` + +也请同时引用BELLE、LLaMA等项目 + +## **🐼 使用限制** + + - **本项目模型与数据集及其衍生物仅用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。** + - **本项目不代表任何一方的立场、利益或想法，无关任何团体的任何类型的主张，因使用本项目模型、数据集等带来的任何损害、纠纷，本项目不承担任何责任。** + - 在涉及事实性的指令上可能会产生违背事实的错误回答。 +- 对于具备危害性的指令无法很好的鉴别，由此会产生危害性言论。 +- 在一些涉及推理、代码等场景下模型的能力仍有待提高。 \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..8c1a2be --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "": 64000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..c9e5d24 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "/data/nvme3/trained_ckpt/saved_models_3.5M/checkpoint-11270", + "architectures": [ + "BaiChuanForCausalLM" + ], + "auto_map": { + "AutoConfig": "configuration_baichuan.BaiChuanConfig", + "AutoModelForCausalLM": "modeling_baichuan.BaiChuanForCausalLM" + }, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "baichuan", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.30.2", + "use_cache": false, + "vocab_size": 64000 +} diff --git a/configuration_baichuan.py b/configuration_baichuan.py new file mode 100644 index 0000000..5057100 --- /dev/null +++ b/configuration_baichuan.py @@ -0,0 +1,66 @@ +# coding=utf-8 +# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. +# +# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX +# and OPT implementations in this library. It has been modified from its +# original forms to accommodate minor architectural differences compared +# to GPT-NeoX and OPT used by the Meta AI team that trained the model. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from transformers.configuration_utils import PretrainedConfig +from transformers.utils import logging + + +logger = logging.get_logger(__name__) + + +class BaiChuanConfig(PretrainedConfig): + model_type = "baichuan" + keys_to_ignore_at_inference = ["past_key_values"] + + def __init__( + self, + vocab_size=64000, + hidden_size=4096, + intermediate_size=11008, + num_hidden_layers=32, + num_attention_heads=32, + hidden_act="silu", + max_position_embeddings=4096, + initializer_range=0.02, + rms_norm_eps=1e-6, + use_cache=True, + pad_token_id=0, + bos_token_id=1, + eos_token_id=2, + tie_word_embeddings=False, + **kwargs, + ): + self.vocab_size = vocab_size + self.max_position_embeddings = max_position_embeddings + self.hidden_size = hidden_size + self.intermediate_size = intermediate_size + self.num_hidden_layers = num_hidden_layers + self.num_attention_heads = num_attention_heads + self.hidden_act = hidden_act + self.initializer_range = initializer_range + self.rms_norm_eps = rms_norm_eps + self.use_cache = use_cache + super().__init__( + pad_token_id=pad_token_id, + bos_token_id=bos_token_id, + eos_token_id=eos_token_id, + tie_word_embeddings=tie_word_embeddings, + **kwargs, + ) diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..89c31b8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.30.2" +} diff --git a/handler.py b/handler.py new file mode 100644 index 0000000..aabef86 --- /dev/null +++ b/handler.py @@ -0,0 +1,41 @@ +import torch +from typing import Dict, List, Any +from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline + +# get dtype +dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16 + + +class EndpointHandler: + def __init__(self, path=""): + # load the model + tokenizer = AutoTokenizer.from_pretrained( + path, + trust_remote_code=True + ) + model = AutoModelForCausalLM.from_pretrained( + path, + device_map="auto", + torch_dtype=dtype, + trust_remote_code=True, + revision="main" + ) + # create inference pipeline + self.pipeline = pipeline( + "text-generation", + model=model, + tokenizer=tokenizer, + trust_remote_code=True + ) + + def __call__(self, data: Any) -> List[List[Dict[str, float]]]: + inputs = data.pop("inputs", data) + parameters = data.pop("parameters", None) + + # pass inputs with all kwargs in data + if parameters is not None: + prediction = self.pipeline(inputs, **parameters) + else: + prediction = self.pipeline(inputs) + # postprocess the prediction + return prediction \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..8842a90 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8028a2854a313c93a172fc29312bd6ae2e8d71d9252c83279dfd7ee7ce8f569a +size 14001153328 diff --git a/modeling_baichuan.py b/modeling_baichuan.py new file mode 100644 index 0000000..36d6ced --- /dev/null +++ b/modeling_baichuan.py @@ -0,0 +1,834 @@ +# coding=utf-8 +# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. +# +# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX +# and OPT implementations in this library. It has been modified from its +# original forms to accommodate minor architectural differences compared +# to GPT-NeoX and OPT used by the Meta AI team that trained the model. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +from .configuration_baichuan import BaiChuanConfig + +import copy +import warnings +import math +from typing import * +import re +import torch +import torch.utils.checkpoint +from torch import nn +from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss +from transformers import PreTrainedModel, add_start_docstrings +from transformers.activations import ACT2FN +from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, \ + SequenceClassifierOutputWithPast +from transformers.utils import logging, add_start_docstrings_to_model_forward, replace_return_docstrings +from transformers.generation.logits_process import LogitsProcessor +from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput + +logger = logging.get_logger(__name__) + +# copied from https://huggingface.co/THUDM/chatglm-6b-int4/blob/main/modeling_chatglm.py +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 + +def generate_prompt(input_text): + return "Human: \n" + input_text + "\n\nAssistant:\n" + + +# Copied from transformers.models.bart.modeling_bart._make_causal_mask +def _make_causal_mask( + input_ids_shape: torch.Size, dtype: torch.dtype, device: torch.device, past_key_values_length: int = 0 +): + """ + Make causal mask used for bi-directional self-attention. + """ + bsz, tgt_len = input_ids_shape + mask = torch.full((tgt_len, tgt_len), torch.tensor(torch.finfo(dtype).min, device=device), device=device) + mask_cond = torch.arange(mask.size(-1), device=device) + mask.masked_fill_(mask_cond < (mask_cond + 1).view(mask.size(-1), 1), 0) + mask = mask.to(dtype) + + if past_key_values_length > 0: + mask = torch.cat([torch.zeros(tgt_len, past_key_values_length, dtype=dtype, device=device), mask], dim=-1) + return mask[None, None, :, :].expand(bsz, 1, tgt_len, tgt_len + past_key_values_length) + + +# Copied from transformers.models.bart.modeling_bart._expand_mask +def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None): + """ + Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`. + """ + bsz, src_len = mask.size() + tgt_len = tgt_len if tgt_len is not None else src_len + + expanded_mask = mask[:, None, None, :].expand(bsz, 1, tgt_len, src_len).to(dtype) + + inverted_mask = 1.0 - expanded_mask + + return inverted_mask.masked_fill(inverted_mask.to(torch.bool), torch.finfo(dtype).min) + + +class RMSNorm(nn.Module): + def __init__(self, hidden_size, eps=1e-6): + """ + RMSNorm is equivalent to T5LayerNorm + """ + super().__init__() + self.weight = nn.Parameter(torch.ones(hidden_size)) + self.variance_epsilon = eps + + def forward(self, hidden_states): + variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True) + hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon) + + # convert into half-precision if necessary + if self.weight.dtype in [torch.float16, torch.bfloat16]: + hidden_states = hidden_states.to(self.weight.dtype) + + return self.weight * hidden_states + + +class RotaryEmbedding(torch.nn.Module): + def __init__(self, dim, max_position_embeddings=2048, base=10000, device=None): + super().__init__() + inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float().to(device) / dim)) + self.register_buffer("inv_freq", inv_freq) + + # Build here to make `torch.jit.trace` work. + self.max_seq_len_cached = max_position_embeddings + t = torch.arange(self.max_seq_len_cached, device=self.inv_freq.device, dtype=self.inv_freq.dtype) + freqs = torch.einsum("i,j->ij", t, self.inv_freq) + # Different from paper, but it uses a different permutation in order to obtain the same calculation + emb = torch.cat((freqs, freqs), dim=-1) + self.register_buffer("cos_cached", emb.cos()[None, None, :, :], persistent=False) + self.register_buffer("sin_cached", emb.sin()[None, None, :, :], persistent=False) + + def forward(self, x, seq_len=None): + # x: [bs, num_attention_heads, seq_len, head_size] + # This `if` block is unlikely to be run after we build sin/cos in `__init__`. Keep the logic here just in case. + if seq_len > self.max_seq_len_cached: + self.max_seq_len_cached = seq_len + t = torch.arange(self.max_seq_len_cached, device=x.device, dtype=self.inv_freq.dtype) + freqs = torch.einsum("i,j->ij", t, self.inv_freq) + # Different from paper, but it uses a different permutation in order to obtain the same calculation + emb = torch.cat((freqs, freqs), dim=-1).to(x.device) + self.register_buffer("cos_cached", emb.cos()[None, None, :, :], persistent=False) + self.register_buffer("sin_cached", emb.sin()[None, None, :, :], persistent=False) + return ( + self.cos_cached[:, :, :seq_len, ...].to(dtype=x.dtype), + self.sin_cached[:, :, :seq_len, ...].to(dtype=x.dtype), + ) + + +def rotate_half(x): + """Rotates half the hidden dims of the input.""" + x1 = x[..., : x.shape[-1] // 2] + x2 = x[..., x.shape[-1] // 2:] + return torch.cat((-x2, x1), dim=-1) + + +def apply_rotary_pos_emb(q, k, cos, sin, position_ids): + # The first two dimensions of cos and sin are always 1, so we can `squeeze` them. + cos = cos.squeeze(1).squeeze(0) # [seq_len, dim] + sin = sin.squeeze(1).squeeze(0) # [seq_len, dim] + cos = cos[position_ids].unsqueeze(1) # [bs, 1, seq_len, dim] + sin = sin[position_ids].unsqueeze(1) # [bs, 1, seq_len, dim] + q_embed = (q * cos) + (rotate_half(q) * sin) + k_embed = (k * cos) + (rotate_half(k) * sin) + return q_embed, k_embed + + +class MLP(nn.Module): + def __init__( + self, + hidden_size: int, + intermediate_size: int, + hidden_act: str, + ): + super().__init__() + self.gate_proj = nn.Linear(hidden_size, intermediate_size, bias=False) + self.down_proj = nn.Linear(intermediate_size, hidden_size, bias=False) + self.up_proj = nn.Linear(hidden_size, intermediate_size, bias=False) + self.act_fn = ACT2FN[hidden_act] + + def forward(self, x): + return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x)) + + +class Attention(nn.Module): + """Multi-headed attention from 'Attention Is All You Need' paper""" + + def __init__(self, config: BaiChuanConfig): + super().__init__() + self.config = config + self.hidden_size = config.hidden_size + self.num_heads = config.num_attention_heads + self.head_dim = self.hidden_size // self.num_heads + self.max_position_embeddings = config.max_position_embeddings + + if (self.head_dim * self.num_heads) != self.hidden_size: + raise ValueError( + f"hidden_size must be divisible by num_heads (got `hidden_size`: {self.hidden_size}" + f" and `num_heads`: {self.num_heads})." + ) + # self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False) + # self.k_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False) + # self.v_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False) + self.W_pack = nn.Linear(self.hidden_size, 3 * self.hidden_size, bias=False) + self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False) + self.rotary_emb = RotaryEmbedding(self.head_dim, max_position_embeddings=self.max_position_embeddings) + + def _shape(self, tensor: torch.Tensor, seq_len: int, bsz: int): + return tensor.view(bsz, seq_len, self.num_heads, self.head_dim).transpose(1, 2).contiguous() + + def forward( + self, + hidden_states: torch.Tensor, + attention_mask: Optional[torch.Tensor] = None, + position_ids: Optional[torch.LongTensor] = None, + past_key_value: Optional[Tuple[torch.Tensor]] = None, + output_attentions: bool = False, + use_cache: bool = False, + ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: + bsz, q_len, _ = hidden_states.size() + + proj = self.W_pack(hidden_states) + proj = proj.unflatten(-1, (3, self.hidden_size)).unsqueeze(0).transpose(0, -2).squeeze(-2) + query_states = proj[0].view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, + 2) # batch_size x source_len x hidden_size + key_states = proj[1].view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, + 2) # batch_size x target_len x head_size + value_states = proj[2].view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, + 2) # batch_size x source_len x hidden_size + + # query_states = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2) + # key_states = self.k_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2) + # value_states = self.v_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2) + + kv_seq_len = key_states.shape[-2] + if past_key_value is not None: + kv_seq_len += past_key_value[0].shape[-2] + cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len) + query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids) + # [bsz, nh, t, hd] + + if past_key_value is not None: + # reuse k, v, self_attention + key_states = torch.cat([past_key_value[0], key_states], dim=2) + value_states = torch.cat([past_key_value[1], value_states], dim=2) + + past_key_value = (key_states, value_states) if use_cache else None + + attn_weights = torch.matmul(query_states, key_states.transpose(2, 3)) / math.sqrt(self.head_dim) + + if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len): + raise ValueError( + f"Attention weights should be of size {(bsz, self.num_heads, q_len, kv_seq_len)}, but is" + f" {attn_weights.size()}" + ) + + if attention_mask is not None: + if attention_mask.size() != (bsz, 1, q_len, kv_seq_len): + raise ValueError( + f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}" + ) + attn_weights = attn_weights + attention_mask + attn_weights = torch.max(attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min)) + + # upcast attention to fp32 + attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype) + attn_output = torch.matmul(attn_weights, value_states) + + if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim): + raise ValueError( + f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is" + f" {attn_output.size()}" + ) + + attn_output = attn_output.transpose(1, 2) + attn_output = attn_output.reshape(bsz, q_len, self.hidden_size) + + attn_output = self.o_proj(attn_output) + + if not output_attentions: + attn_weights = None + + return attn_output, attn_weights, past_key_value + + +class DecoderLayer(nn.Module): + def __init__(self, config: BaiChuanConfig): + super().__init__() + self.hidden_size = config.hidden_size + self.self_attn = Attention(config=config) + self.mlp = MLP( + hidden_size=self.hidden_size, + intermediate_size=config.intermediate_size, + hidden_act=config.hidden_act, + ) + self.input_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps) + self.post_attention_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps) + + def forward( + self, + hidden_states: torch.Tensor, + attention_mask: Optional[torch.Tensor] = None, + position_ids: Optional[torch.LongTensor] = None, + past_key_value: Optional[Tuple[torch.Tensor]] = None, + output_attentions: Optional[bool] = False, + use_cache: Optional[bool] = False, + ) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]]: + """ + Args: + hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` + attention_mask (`torch.FloatTensor`, *optional*): attention mask of size + `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values. + output_attentions (`bool`, *optional*): + Whether or not to return the attentions tensors of all attention layers. See `attentions` under + returned tensors for more detail. + use_cache (`bool`, *optional*): + If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding + (see `past_key_values`). + past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states + """ + + residual = hidden_states + + hidden_states = self.input_layernorm(hidden_states) + + # Self Attention + hidden_states, self_attn_weights, present_key_value = self.self_attn( + hidden_states=hidden_states, + attention_mask=attention_mask, + position_ids=position_ids, + past_key_value=past_key_value, + output_attentions=output_attentions, + use_cache=use_cache, + ) + hidden_states = residual + hidden_states + + # Fully Connected + residual = hidden_states + hidden_states = self.post_attention_layernorm(hidden_states) + hidden_states = self.mlp(hidden_states) + hidden_states = residual + hidden_states + + outputs = (hidden_states,) + + if output_attentions: + outputs += (self_attn_weights,) + + if use_cache: + outputs += (present_key_value,) + + return outputs + + +class PreTrainedModel(PreTrainedModel): + config_class = BaiChuanConfig + base_model_prefix = "model" + supports_gradient_checkpointing = True + _no_split_modules = ["DecoderLayer"] + _keys_to_ignore_on_load_unexpected = [r"decoder\.version"] + + def _init_weights(self, module): + std = self.config.initializer_range + if isinstance(module, nn.Linear): + module.weight.data.normal_(mean=0.0, std=std) + if module.bias is not None: + module.bias.data.zero_() + elif isinstance(module, nn.Embedding): + module.weight.data.normal_(mean=0.0, std=std) + if module.padding_idx is not None: + module.weight.data[module.padding_idx].zero_() + + def _set_gradient_checkpointing(self, module, value=False): + if isinstance(module, Model): + module.gradient_checkpointing = value + + +class Model(PreTrainedModel): + """ + Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`DecoderLayer`] + + Args: + config: BaiChuanConfig + """ + + def __init__(self, config: BaiChuanConfig): + super().__init__(config) + self.padding_idx = config.pad_token_id + self.vocab_size = config.vocab_size + + self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx) + self.layers = nn.ModuleList([DecoderLayer(config) for _ in range(config.num_hidden_layers)]) + self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps) + + self.gradient_checkpointing = False + # Initialize weights and apply final processing + self.post_init() + + def get_input_embeddings(self): + return self.embed_tokens + + def set_input_embeddings(self, value): + self.embed_tokens = value + + # Copied from transformers.models.bart.modeling_bart.BartDecoder._prepare_decoder_attention_mask + def _prepare_decoder_attention_mask(self, attention_mask, input_shape, inputs_embeds, past_key_values_length): + # create causal mask + # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len] + combined_attention_mask = None + if input_shape[-1] > 1: + combined_attention_mask = _make_causal_mask( + input_shape, + inputs_embeds.dtype, + device=inputs_embeds.device, + past_key_values_length=past_key_values_length, + ) + + if attention_mask is not None: + # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len] + expanded_attn_mask = _expand_mask(attention_mask, inputs_embeds.dtype, tgt_len=input_shape[-1]).to( + inputs_embeds.device + ) + combined_attention_mask = ( + expanded_attn_mask if combined_attention_mask is None else expanded_attn_mask + combined_attention_mask + ) + + return combined_attention_mask + + def forward( + self, + input_ids: torch.LongTensor = None, + attention_mask: Optional[torch.Tensor] = None, + position_ids: Optional[torch.LongTensor] = None, + past_key_values: Optional[List[torch.FloatTensor]] = None, + inputs_embeds: Optional[torch.FloatTensor] = None, + use_cache: Optional[bool] = None, + output_attentions: Optional[bool] = None, + output_hidden_states: Optional[bool] = None, + return_dict: Optional[bool] = None, + ) -> Union[Tuple, BaseModelOutputWithPast]: + output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions + 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 + + # retrieve input_ids and inputs_embeds + if input_ids is not None and inputs_embeds is not None: + raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time") + elif input_ids is not None: + batch_size, seq_length = input_ids.shape + elif inputs_embeds is not None: + batch_size, seq_length, _ = inputs_embeds.shape + else: + raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds") + + seq_length_with_past = seq_length + past_key_values_length = 0 + + if past_key_values is not None: + past_key_values_length = past_key_values[0][0].shape[2] + seq_length_with_past = seq_length_with_past + past_key_values_length + + if position_ids is None: + device = input_ids.device if input_ids is not None else inputs_embeds.device + position_ids = torch.arange( + past_key_values_length, seq_length + past_key_values_length, dtype=torch.long, device=device + ) + position_ids = position_ids.unsqueeze(0).view(-1, seq_length) + else: + position_ids = position_ids.view(-1, seq_length).long() + + if inputs_embeds is None: + inputs_embeds = self.embed_tokens(input_ids) + # embed positions + if attention_mask is None: + attention_mask = torch.ones( + (batch_size, seq_length_with_past), dtype=torch.bool, device=inputs_embeds.device + ) + attention_mask = self._prepare_decoder_attention_mask( + attention_mask, (batch_size, seq_length), inputs_embeds, past_key_values_length + ) + + hidden_states = inputs_embeds + + 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 + + # decoder layers + all_hidden_states = () if output_hidden_states else None + all_self_attns = () if output_attentions else None + next_decoder_cache = () if use_cache else None + + for idx, decoder_layer in enumerate(self.layers): + if output_hidden_states: + all_hidden_states += (hidden_states,) + + past_key_value = past_key_values[idx] if past_key_values is not None else None + + if self.gradient_checkpointing and self.training: + + def create_custom_forward(module): + def custom_forward(*inputs): + # None for past_key_value + return module(*inputs, output_attentions, None) + + return custom_forward + + layer_outputs = torch.utils.checkpoint.checkpoint( + create_custom_forward(decoder_layer), + hidden_states, + attention_mask, + position_ids, + None, + ) + else: + layer_outputs = decoder_layer( + hidden_states, + attention_mask=attention_mask, + position_ids=position_ids, + past_key_value=past_key_value, + output_attentions=output_attentions, + use_cache=use_cache, + ) + + hidden_states = layer_outputs[0] + + if use_cache: + next_decoder_cache += (layer_outputs[2 if output_attentions else 1],) + + if output_attentions: + all_self_attns += (layer_outputs[1],) + + hidden_states = self.norm(hidden_states) + + # add hidden states from the last decoder layer + if output_hidden_states: + all_hidden_states += (hidden_states,) + + next_cache = next_decoder_cache if use_cache else None + if not return_dict: + return tuple(v for v in [hidden_states, next_cache, all_hidden_states, all_self_attns] if v is not None) + return BaseModelOutputWithPast( + last_hidden_state=hidden_states, + past_key_values=next_cache, + hidden_states=all_hidden_states, + attentions=all_self_attns, + ) + + +class BaiChuanForCausalLM(PreTrainedModel): + def __init__(self, config): + super().__init__(config) + self.model = Model(config) + + self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False) + + # Initialize weights and apply final processing + self.post_init() + + def get_input_embeddings(self): + return self.model.embed_tokens + + def set_input_embeddings(self, value): + self.model.embed_tokens = value + + def get_output_embeddings(self): + return self.lm_head + + def set_output_embeddings(self, new_embeddings): + self.lm_head = new_embeddings + + def set_decoder(self, decoder): + self.model = decoder + + def get_decoder(self): + return self.model + + def forward( + self, + input_ids: torch.LongTensor = None, + attention_mask: Optional[torch.Tensor] = None, + position_ids: Optional[torch.LongTensor] = None, + past_key_values: Optional[List[torch.FloatTensor]] = None, + inputs_embeds: Optional[torch.FloatTensor] = None, + labels: Optional[torch.LongTensor] = None, + use_cache: Optional[bool] = None, + output_attentions: Optional[bool] = None, + output_hidden_states: Optional[bool] = None, + return_dict: Optional[bool] = None, + ) -> Union[Tuple, CausalLMOutputWithPast]: + r""" + Args: + labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): + Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., + config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored + (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. + + Returns: + + Example: + + ```python + >>> from transformers import AutoTokenizer, ModelForCausalLM + + >>> model = ModelForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS) + >>> tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER) + + >>> prompt = "Hey, are you consciours? Can you talk to me?" + >>> inputs = tokenizer(prompt, return_tensors="pt") + + >>> # Generate + >>> generate_ids = model.generate(inputs.input_ids, max_length=30) + >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] + "Hey, are you consciours? Can you talk to me?\nI'm not consciours, but I can talk to you." + ```""" + + output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions + output_hidden_states = ( + output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states + ) + return_dict = return_dict if return_dict is not None else self.config.use_return_dict + + # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn) + outputs = self.model( + input_ids=input_ids, + attention_mask=attention_mask, + position_ids=position_ids, + past_key_values=past_key_values, + inputs_embeds=inputs_embeds, + use_cache=use_cache, + output_attentions=output_attentions, + output_hidden_states=output_hidden_states, + return_dict=return_dict, + ) + + hidden_states = outputs[0] + logits = self.lm_head(hidden_states) + + loss = None + if labels is not None: + # Shift so that tokens < n predict n + shift_logits = logits[..., :-1, :].contiguous() + shift_labels = labels[..., 1:].contiguous() + # Flatten the tokens + loss_fct = CrossEntropyLoss() + shift_logits = shift_logits.view(-1, self.config.vocab_size) + shift_labels = shift_labels.view(-1) + # Enable model parallelism + shift_labels = shift_labels.to(shift_logits.device) + loss = loss_fct(shift_logits, shift_labels) + + if not return_dict: + output = (logits,) + outputs[1:] + return (loss,) + output if loss is not None else output + + return CausalLMOutputWithPast( + loss=loss, + logits=logits, + past_key_values=outputs.past_key_values, + hidden_states=outputs.hidden_states, + attentions=outputs.attentions, + ) + + def prepare_inputs_for_generation( + self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs + ): + if past_key_values: + input_ids = input_ids[:, -1:] + + position_ids = kwargs.get("position_ids", None) + if attention_mask is not None and position_ids is None: + # create position_ids on the fly for batch generation + position_ids = attention_mask.long().cumsum(-1) - 1 + position_ids.masked_fill_(attention_mask == 0, 1) + if past_key_values: + position_ids = position_ids[:, -1].unsqueeze(-1) + + # if `inputs_embeds` are passed, we only want to use them in the 1st generation step + if inputs_embeds is not None and past_key_values is None: + model_inputs = {"inputs_embeds": inputs_embeds} + else: + model_inputs = {"input_ids": input_ids} + + model_inputs.update( + { + "position_ids": position_ids, + "past_key_values": past_key_values, + "use_cache": kwargs.get("use_cache"), + "attention_mask": attention_mask, + } + ) + return model_inputs + + @staticmethod + def _reorder_cache(past_key_values, beam_idx): + reordered_past = () + for layer_past in past_key_values: + reordered_past += (tuple(past_state.index_select(0, beam_idx) for past_state in layer_past),) + return reordered_past + + def process_response(self, response): + response = response.strip() + response = response.replace("[[训练时间]]", "2023年") + punkts = [ + [",", "，"], + ["!", "！"], + [":", "："], + [";", "；"], + ["\?", "？"], + ] + for item in punkts: + response = re.sub(r"([\u4e00-\u9fff])%s" % item[0], r"\1%s" % item[1], response) + response = re.sub(r"%s([\u4e00-\u9fff])" % item[0], r"%s\1" % item[1], response) + return response + + # copied from https://huggingface.co/THUDM/chatglm-6b-int4/blob/main/modeling_chatglm.py + @torch.no_grad() + def stream_chat(self, tokenizer, query: str, history: List = None, + gen_kwargs: dict = None, logits_processor=None): + if history is None: + history = [] + if logits_processor is None: + logits_processor = LogitsProcessorList() + logits_processor.append(InvalidScoreLogitsProcessor()) + + if not history: + prompt = generate_prompt(query) + else: + history.append(generate_prompt(query)) + prompt = "".join(history) + + inputs = tokenizer(prompt, return_tensors="pt") + inputs = inputs.to(self.model.device) + for outputs in self.stream_generate(**inputs, **gen_kwargs): + outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):] + response = tokenizer.decode(outputs, skip_special_tokens=True).split("Assistant:")[-1].strip() + response = self.process_response(response) + yield response + + @torch.no_grad() + 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, + **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) + 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()) + + # 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 + yield input_ids diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..b7c0bcd --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e150a0102e16c751b9556c244a398f258e3011fb088c8784ddb54b080f34dce8 +size 14001165628 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..09a3b09 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenization_baichuan.py b/tokenization_baichuan.py new file mode 100644 index 0000000..4189839 --- /dev/null +++ b/tokenization_baichuan.py @@ -0,0 +1,251 @@ +# coding=utf-8 +# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. +# +# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX +# and OPT implementations in this library. It has been modified from its +# original forms to accommodate minor architectural differences compared +# to GPT-NeoX and OPT used by the Meta AI team that trained the model. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import os +from shutil import copyfile +from typing import Any, Dict, List, Optional, Tuple + +import sentencepiece as spm + +from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer +from transformers.utils import logging + + +logger = logging.get_logger(__name__) + +VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"} + +PRETRAINED_VOCAB_FILES_MAP = { + "vocab_file": {}, + "tokenizer_file": {}, +} +PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {} + + +class BaiChuanTokenizer(PreTrainedTokenizer): + """ + Construct a BaiChuan tokenizer. Based on byte-level Byte-Pair-Encoding. + + Args: + vocab_file (`str`): + Path to the vocabulary file. + """ + + vocab_files_names = VOCAB_FILES_NAMES + pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP + max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES + model_input_names = ["input_ids", "attention_mask"] + + def __init__( + self, + vocab_file, + unk_token="", + bos_token="", + eos_token="", + pad_token=None, + sp_model_kwargs: Optional[Dict[str, Any]] = None, + add_bos_token=True, + add_eos_token=False, + clean_up_tokenization_spaces=False, + **kwargs, + ): + self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs + bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token + eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token + unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token + pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token + self.vocab_file = vocab_file + self.add_bos_token = add_bos_token + self.add_eos_token = add_eos_token + self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) + self.sp_model.Load(vocab_file) + super().__init__( + bos_token=bos_token, + eos_token=eos_token, + unk_token=unk_token, + pad_token=pad_token, + add_bos_token=add_bos_token, + add_eos_token=add_eos_token, + sp_model_kwargs=self.sp_model_kwargs, + clean_up_tokenization_spaces=clean_up_tokenization_spaces, + **kwargs, + ) + + + def __getstate__(self): + state = self.__dict__.copy() + state["sp_model"] = None + return state + + def __setstate__(self, d): + self.__dict__ = d + self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) + self.sp_model.Load(self.vocab_file) + + @property + def vocab_size(self): + """Returns vocab size""" + return self.sp_model.get_piece_size() + + def get_vocab(self): + """Returns vocab as a dict""" + vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)} + vocab.update(self.added_tokens_encoder) + return vocab + + def _tokenize(self, text): + """Returns a tokenized string.""" + return self.sp_model.encode(text, out_type=str) + + def _convert_token_to_id(self, token): + """Converts a token (str) in an id using the vocab.""" + return self.sp_model.piece_to_id(token) + + def _convert_id_to_token(self, index): + """Converts an index (integer) in a token (str) using the vocab.""" + token = self.sp_model.IdToPiece(index) + return token + + def convert_tokens_to_string(self, tokens): + """Converts a sequence of tokens (string) in a single string.""" + current_sub_tokens = [] + out_string = "" + prev_is_special = False + for i, token in enumerate(tokens): + # make sure that special tokens are not decoded using sentencepiece model + if token in self.all_special_tokens: + if not prev_is_special and i != 0: + out_string += " " + out_string += self.sp_model.decode(current_sub_tokens) + token + prev_is_special = True + current_sub_tokens = [] + else: + current_sub_tokens.append(token) + prev_is_special = False + out_string += self.sp_model.decode(current_sub_tokens) + return out_string + + def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]: + """ + Save the vocabulary and special tokens file to a directory. + + Args: + save_directory (`str`): + The directory in which to save the vocabulary. + + Returns: + `Tuple(str)`: Paths to the files saved. + """ + if not os.path.isdir(save_directory): + logger.error(f"Vocabulary path ({save_directory}) should be a directory") + return + out_vocab_file = os.path.join( + save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"] + ) + + if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file): + copyfile(self.vocab_file, out_vocab_file) + elif not os.path.isfile(self.vocab_file): + with open(out_vocab_file, "wb") as fi: + content_spiece_model = self.sp_model.serialized_model_proto() + fi.write(content_spiece_model) + + return (out_vocab_file,) + + def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None): + bos_token_id = [self.bos_token_id] if self.add_bos_token else [] + eos_token_id = [self.eos_token_id] if self.add_eos_token else [] + + output = bos_token_id + token_ids_0 + eos_token_id + + if token_ids_1 is not None: + output = output + bos_token_id + token_ids_1 + eos_token_id + + return output + + def get_special_tokens_mask( + self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False + ) -> List[int]: + """ + Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding + special tokens using the tokenizer `prepare_for_model` method. + + Args: + token_ids_0 (`List[int]`): + List of IDs. + token_ids_1 (`List[int]`, *optional*): + Optional second list of IDs for sequence pairs. + already_has_special_tokens (`bool`, *optional*, defaults to `False`): + Whether or not the token list is already formatted with special tokens for the model. + + Returns: + `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. + """ + if already_has_special_tokens: + return super().get_special_tokens_mask( + token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True + ) + + bos_token_id = [1] if self.add_bos_token else [] + eos_token_id = [1] if self.add_eos_token else [] + + if token_ids_1 is None: + return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id + return ( + bos_token_id + + ([0] * len(token_ids_0)) + + eos_token_id + + bos_token_id + + ([0] * len(token_ids_1)) + + eos_token_id + ) + + def create_token_type_ids_from_sequences( + self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None + ) -> List[int]: + """ + Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT + sequence pair mask has the following format: + + ``` + 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 + | first sequence | second sequence | + ``` + + if token_ids_1 is None, only returns the first portion of the mask (0s). + + Args: + token_ids_0 (`List[int]`): + List of ids. + token_ids_1 (`List[int]`, *optional*): + Optional second list of IDs for sequence pairs. + + Returns: + `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s). + """ + bos_token_id = [self.bos_token_id] if self.add_bos_token else [] + eos_token_id = [self.eos_token_id] if self.add_eos_token else [] + + output = [0] * len(bos_token_id + token_ids_0 + eos_token_id) + + if token_ids_1 is not None: + output += [1] * len(bos_token_id + token_ids_1 + eos_token_id) + + return output \ No newline at end of file diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..9d991e0 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ea06a6726b6d518808fbc0d0d6bc3f0e899ea9e1656b2ab9716fa674e024f4 +size 2095253 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..852f5db --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "auto_map": { + "AutoTokenizer": ["tokenization_baichuan.BaiChuanTokenizer", null] + }, + "add_bos_token": false, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 1000000000000000019884624838656, + "pad_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "sp_model_kwargs": {}, + "tokenizer_class": "BaiChuanTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}