first

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+.idea

README.md

@@ -1,3 +1,73 @@
----
-license: apache-2.0
----
+## zR-Llama-1B-chatglm2-6b-tokenizer
+
+本模型是基于 [build_MiniLLM_from_scratch 开源框架](https://github.com/Tongjilibo/build_MiniLLM_from_scratch) 自行训练的一个1B模型。
+
+## 模型参数
++ 1B 参数量
++ 训练语料670亿。
++ 模型支持token长度 896
+
+
+## 预训练模型
+
++ 使用 [build_MiniLLM_from_scratch 开源框架](https://github.com/Tongjilibo/build_MiniLLM_from_scratch) 的预训练数据集，自己完成 Tokenize 过程。
++ 使用 8 x 80GB A800 GPU 训练。
++ 训练 1 Epoch，bs=32 (每张卡) , lr=1.5e-4。
++ 共耗时 1 天。
+
+## SFT模型
++ 使用 [build_MiniLLM_from_scratch 开源框架](https://github.com/Tongjilibo/build_MiniLLM_from_scratch) 提供的全部数据集
++ 使用 单卡A800 微调。
++ 微调 5 Epoch, bs=8, lr=2e-5。
++ 共耗时 3 天 12 小时。
+
+## 使用模型
+
+```python
+import os
+import torch
+from transformers import AutoTokenizer, LlamaForCausalLM
+
+max_length = 896
+HUMAN = '<human>'
+ROBOT = '<robot>'
+def build_prompt(query, history) -> str:
+    texts = ''
+    for user_input, response in history:
+        texts += f'{HUMAN}{user_input}{ROBOT}{response}'
+
+    texts += f'{HUMAN}{query}{ROBOT}'
+    return texts
+
+def build_cli_history(history):
+    prompt = ''
+    for query, response in history:
+        prompt += f"\n\nUser：{query.strip()}"
+        prompt += f"\n\nRobot：{response.strip()}"
+    return prompt
+
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+tokenizer = AutoTokenizer.from_pretrained("zRzRzRzRzRzRzR/zR-Llama-1b-ChatGLM2-6b-tokenizer", trust_remote_code=True)
+model = LlamaForCausalLM.from_pretrained("zRzRzRzRzRzRzR/zR-Llama-1b-ChatGLM2-6b-tokenizer").to(device)
+
+history = []
+clear_command = 'cls' if os.name == 'nt' else 'clear'
+while True:
+    query = input('\n输入:')
+    if query.strip() == "stop":
+        break
+    if query.strip() == "clear":
+        history = []
+        os.system(clear_command)
+        continue
+
+    inputs = tokenizer.encode(build_prompt(query, history), return_tensors='pt', add_special_tokens=False).to(device)
+    response = model.generate(inputs)
+    response = tokenizer.decode(response[0].cpu(), skip_special_tokens=True)
+
+    os.system(clear_command)
+    print(build_cli_history(history + [(query, response)]), flush=True)
+```
+
+

config.json

@@ -0,0 +1,21 @@
+{  
+  "architectures": [
+  "LlamaForCausalLM"
+   ],
+  "model_type": "llama",
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_size": 2048,
+  "max_position_embeddings": 896,
+  "intermediate_size": 5632, 
+  "num_attention_heads": 32,
+  "num_key_value_heads": 4,
+  "num_hidden_layers": 22,
+  "hidden_act": "silu",
+  "vocab_size": 64793,
+  "rms_norm_eps": 1e-06,
+  "tie_emb_prj_weight": true,
+  "use_cache": true,
+  "do_sample": true,
+  "max_length": 896 
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e238728a3661fa4c1f213ea815e159de11c6afe579938fdbe2a3042586d5ef42
+size 4406772078

tokenization_chatglm.py

@@ -0,0 +1,249 @@
+import os
+import torch
+from typing import List, Optional, Union, Dict
+from sentencepiece import SentencePieceProcessor
+from transformers import PreTrainedTokenizer
+from transformers.utils import logging, PaddingStrategy
+from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
+
+
+class SPTokenizer:
+    def __init__(self, model_path: str):
+        # reload tokenizer
+        assert os.path.isfile(model_path), model_path
+        self.sp_model = SentencePieceProcessor(model_file=model_path)
+
+        # BOS / EOS token IDs
+        self.n_words: int = self.sp_model.vocab_size()
+        self.bos_id: int = self.sp_model.bos_id()
+        self.eos_id: int = self.sp_model.eos_id()
+        self.pad_id: int = self.sp_model.unk_id()
+        assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
+
+        special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"]
+        self.special_tokens = {}
+        self.index_special_tokens = {}
+        for token in special_tokens:
+            self.special_tokens[token] = self.n_words
+            self.index_special_tokens[self.n_words] = token
+            self.n_words += 1
+
+    def tokenize(self, s: str):
+        return self.sp_model.EncodeAsPieces(s)
+
+    def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
+        assert type(s) is str
+        t = self.sp_model.encode(s)
+        if bos:
+            t = [self.bos_id] + t
+        if eos:
+            t = t + [self.eos_id]
+        return t
+
+    def decode(self, t: List[int]) -> str:
+        return self.sp_model.decode(t)
+
+    def decode_tokens(self, tokens: List[str]) -> str:
+        text = self.sp_model.DecodePieces(tokens)
+        return text
+
+    def convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        return self.sp_model.PieceToId(token)
+
+    def convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        if index in self.index_special_tokens or index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
+            return ""
+        return self.sp_model.IdToPiece(index)
+
+
+class ChatGLMTokenizer(PreTrainedTokenizer):
+    vocab_files_names = {"vocab_file": "tokenizer.model"}
+
+    model_input_names = ["input_ids", "attention_mask", "position_ids"]
+
+    def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, **kwargs):
+        self.name = "GLMTokenizer"
+
+        self.vocab_file = vocab_file
+        self.tokenizer = SPTokenizer(vocab_file)
+        self.special_tokens = {
+            "<bos>": self.tokenizer.bos_id,
+            "<eos>": self.tokenizer.eos_id,
+            "<pad>": self.tokenizer.pad_id
+        }
+        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 unk_token(self) -> str:
+        return "<unk>"
+
+    @property
+    def pad_token(self) -> str:
+        return "<unk>"
+
+    @property
+    def pad_token_id(self):
+        return self.get_command("<pad>")
+
+    @property
+    def eos_token(self) -> str:
+        return "</s>"
+
+    @property
+    def eos_token_id(self):
+        return self.get_command("<eos>")
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_words
+
+    def get_vocab(self):
+        """ Returns vocab as a dict """
+        vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def _tokenize(self, text, **kwargs):
+        return self.tokenizer.tokenize(text)
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.tokenizer.convert_token_to_id(token)
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.tokenizer.convert_id_to_token(index)
+
+    def convert_tokens_to_string(self, tokens: List[str]) -> str:
+        return self.tokenizer.decode_tokens(tokens)
+
+    def save_vocabulary(self, save_directory, filename_prefix=None):
+        """
+        Save the vocabulary and special tokens file to a directory.
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+            filename_prefix (`str`, *optional*):
+                An optional prefix to add to the named of the saved files.
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if os.path.isdir(save_directory):
+            vocab_file = os.path.join(
+                save_directory, self.vocab_files_names["vocab_file"]
+            )
+        else:
+            vocab_file = save_directory
+
+        with open(self.vocab_file, 'rb') as fin:
+            proto_str = fin.read()
+
+        with open(vocab_file, "wb") as writer:
+            writer.write(proto_str)
+
+        return (vocab_file,)
+
+    def get_prefix_tokens(self):
+        prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
+        return prefix_tokens
+
+    def build_prompt(self, query, history=None):
+        if history is None:
+            history = []
+        prompt = ""
+        for i, (old_query, response) in enumerate(history):
+            prompt += "[Round {}]\n\n问：{}\n\n答：{}\n\n".format(i + 1, old_query, response)
+        prompt += "[Round {}]\n\n问：{}\n\n答：".format(len(history) + 1, query)
+        return prompt
+
+    def build_inputs_with_special_tokens(
+            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A BERT sequence has the following format:
+        - single sequence: `[CLS] X [SEP]`
+        - pair of sequences: `[CLS] A [SEP] B [SEP]`
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+        prefix_tokens = self.get_prefix_tokens()
+        token_ids_0 = prefix_tokens + token_ids_0
+        if token_ids_1 is not None:
+            token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
+        return token_ids_0
+
+    def _pad(
+            self,
+            encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
+            max_length: Optional[int] = None,
+            padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
+            pad_to_multiple_of: Optional[int] = None,
+            return_attention_mask: Optional[bool] = None,
+    ) -> dict:
+        """
+        Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
+        Args:
+            encoded_inputs:
+                Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
+            max_length: maximum length of the returned list and optionally padding length (see below).
+                Will truncate by taking into account the special tokens.
+            padding_strategy: PaddingStrategy to use for padding.
+                - PaddingStrategy.LONGEST Pad to the longest sequence in the batch
+                - PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
+                - PaddingStrategy.DO_NOT_PAD: Do not pad
+                The tokenizer padding sides are defined in self.padding_side:
+                    - 'left': pads on the left of the sequences
+                    - 'right': pads on the right of the sequences
+            pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
+                This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
+                `>= 7.5` (Volta).
+            return_attention_mask:
+                (optional) Set to False to avoid returning attention mask (default: set to model specifics)
+        """
+        # Load from model defaults
+        assert self.padding_side == "left"
+
+        required_input = encoded_inputs[self.model_input_names[0]]
+        seq_length = len(required_input)
+
+        if padding_strategy == PaddingStrategy.LONGEST:
+            max_length = len(required_input)
+
+        if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
+            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
+
+        needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
+
+        # Initialize attention mask if not present.
+        if "attention_mask" not in encoded_inputs:
+            encoded_inputs["attention_mask"] = [1] * seq_length
+
+        if "position_ids" not in encoded_inputs:
+            encoded_inputs["position_ids"] = list(range(seq_length))
+
+        if needs_to_be_padded:
+            difference = max_length - len(required_input)
+
+            if "attention_mask" in encoded_inputs:
+                encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
+            if "position_ids" in encoded_inputs:
+                encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
+            encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
+
+        return encoded_inputs

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
+size 1018370

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "name_or_path": "THUDM/chatglm2-6b",
+  "remove_space": false,
+  "do_lower_case": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLMTokenizer",
+      null
+      ]
+  }
+}