Added ChatGLM-6B

ptuning/main.py

+#!/usr/bin/env python
+# coding=utf-8
+# Copyright 2021 The HuggingFace Team. All rights reserved.
+#
+# 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.
+"""
+Fine-tuning the library models for sequence to sequence.
+"""
+# You can also adapt this script on your own sequence to sequence task. Pointers for this are left as comments.
+
+import logging
+import os
+import sys
+import json
+import os
+os.environ["WANDB_DISABLED"] = "true"
+import numpy as np
+from datasets import load_dataset
+import jieba 
+from rouge_chinese import Rouge
+from nltk.translate.bleu_score import sentence_bleu, SmoothingFunction
+import torch
+
+import transformers
+from transformers import (
+    AutoConfig,
+    AutoModel,
+    AutoTokenizer,
+    AutoTokenizer,
+    DataCollatorForSeq2Seq,
+    HfArgumentParser,
+    Seq2SeqTrainingArguments,
+    set_seed,
+)
+from trainer_seq2seq import Seq2SeqTrainer
+
+from arguments import ModelArguments, DataTrainingArguments
+
+logger = logging.getLogger(__name__)
+
+def main():
+
+    parser = HfArgumentParser((ModelArguments, DataTrainingArguments, Seq2SeqTrainingArguments))
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
+        # If we pass only one argument to the script and it's the path to a json file,
+        # let's parse it to get our arguments.
+        model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
+    else:
+        model_args, data_args, training_args = parser.parse_args_into_dataclasses()
+
+    # Setup logging
+    logging.basicConfig(
+        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+
+    if training_args.should_log:
+        # The default of training_args.log_level is passive, so we set log level at info here to have that default.
+        transformers.utils.logging.set_verbosity_info()
+
+    log_level = training_args.get_process_log_level()
+    logger.setLevel(log_level)
+    # datasets.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.enable_default_handler()
+    transformers.utils.logging.enable_explicit_format()
+
+    # Log on each process the small summary:
+    logger.warning(
+        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
+        + f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
+    )
+    logger.info(f"Training/evaluation parameters {training_args}")
+
+    # Set seed before initializing model.
+    set_seed(training_args.seed)
+
+    # Load dataset
+    data_files = {}
+    if data_args.train_file is not None:
+        data_files["train"] = data_args.train_file
+        extension = data_args.train_file.split(".")[-1]
+    if data_args.validation_file is not None:
+        data_files["validation"] = data_args.validation_file
+        extension = data_args.validation_file.split(".")[-1]
+    if data_args.test_file is not None:
+        data_files["test"] = data_args.test_file
+        extension = data_args.test_file.split(".")[-1]
+
+    raw_datasets = load_dataset(
+        extension,
+        data_files=data_files,
+        cache_dir=model_args.cache_dir,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+
+    # Load pretrained model and tokenizer
+    config = AutoConfig.from_pretrained(model_args.model_name_or_path, trust_remote_code=True)
+    config.pre_seq_len = model_args.pre_seq_len
+    config.prefix_projection = model_args.prefix_projection
+
+    tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, trust_remote_code=True)
+
+    if model_args.ptuning_checkpoint is not None:
+        # Evaluation
+        # Loading extra state dict of prefix encoder
+        model = AutoModel.from_pretrained(model_args.model_name_or_path, config=config, trust_remote_code=True,empty_init=False)
+        prefix_state_dict = torch.load(os.path.join(model_args.ptuning_checkpoint, "pytorch_model.bin"))
+        new_prefix_state_dict = {}
+        for k, v in prefix_state_dict.items():
+            if k.startswith("transformer.prefix_encoder."):
+                new_prefix_state_dict[k[len("transformer.prefix_encoder."):]] = v
+        model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict)
+    else:
+        model = AutoModel.from_pretrained(model_args.model_name_or_path, config=config, trust_remote_code=True,empty_init=False)
+
+    if model_args.quantization_bit is not None:
+        print(f"Quantized to {model_args.quantization_bit} bit")
+        model = model.quantize(model_args.quantization_bit)
+    if model_args.pre_seq_len is not None:
+        # P-tuning v2
+        model = model.half()
+        model.transformer.prefix_encoder.float()
+    else:
+        # Finetune
+        model = model.float()
+
+    prefix = data_args.source_prefix if data_args.source_prefix is not None else ""
+
+    # Preprocessing the datasets.
+    # We need to tokenize inputs and targets.
+    if training_args.do_train:
+        column_names = raw_datasets["train"].column_names
+    elif training_args.do_eval:
+        column_names = raw_datasets["validation"].column_names
+    elif training_args.do_predict:
+        column_names = raw_datasets["test"].column_names
+    else:
+        logger.info("There is nothing to do. Please pass `do_train`, `do_eval` and/or `do_predict`.")
+        return
+
+    # Get the column names for input/target.
+    prompt_column = data_args.prompt_column
+    response_column = data_args.response_column
+    history_column = data_args.history_column
+    
+    # Temporarily set max_target_length for training.
+    max_target_length = data_args.max_target_length
+
+    def preprocess_function_eval(examples):
+        inputs, targets = [], []
+        for i in range(len(examples[prompt_column])):
+            if examples[prompt_column][i] and examples[response_column][i]:
+                query = examples[prompt_column][i]
+                if history_column is None or len(examples[history_column][i]) == 0:
+                    prompt = query
+                else:
+                    prompt = ""
+                    history = examples[history_column][i]
+                    for turn_idx, (old_query, response) in enumerate(history):
+                        prompt += "[Round {}]\n问：{}\n答：{}\n".format(turn_idx, old_query, response)
+                    prompt += "[Round {}]\n问：{}\n答：".format(len(history), query)
+                inputs.append(prompt)
+                targets.append(examples[response_column][i])
+
+        inputs = [prefix + inp for inp in inputs]
+        model_inputs = tokenizer(inputs, max_length=data_args.max_source_length, truncation=True, padding=True)
+        labels = tokenizer(text_target=targets, max_length=max_target_length, truncation=True)
+
+        if data_args.ignore_pad_token_for_loss:
+            labels["input_ids"] = [
+                [(l if l != tokenizer.pad_token_id else -100) for l in label] for label in labels["input_ids"]
+            ]
+        model_inputs["labels"] = labels["input_ids"]
+
+        return model_inputs
+
+    def preprocess_function_train(examples):
+        max_seq_length = data_args.max_source_length + data_args.max_target_length
+
+        model_inputs = {
+            "input_ids": [],
+            "labels": [],
+        }
+        for i in range(len(examples[prompt_column])):
+            if examples[prompt_column][i] and examples[response_column][i]:
+                query, answer = examples[prompt_column][i], examples[response_column][i]
+
+                if history_column is None:
+                    prompt = query
+                else:
+                    prompt = ""
+                    history = examples[history_column][i]
+                    for turn_idx, (old_query, response) in enumerate(history):
+                        prompt += "[Round {}]\n问：{}\n答：{}\n".format(turn_idx, old_query, response)
+                    prompt += "[Round {}]\n问：{}\n答：".format(len(history), query)
+
+                prompt = prefix + prompt
+                a_ids = tokenizer.encode(text=prompt, add_special_tokens=False)
+                b_ids = tokenizer.encode(text=answer, add_special_tokens=False)
+
+                if len(a_ids) > data_args.max_source_length - 1:
+                    a_ids = a_ids[: data_args.max_source_length - 1]
+
+                if len(b_ids) > data_args.max_target_length - 2:
+                    b_ids = b_ids[: data_args.max_target_length - 2]
+
+                input_ids = tokenizer.build_inputs_with_special_tokens(a_ids, b_ids)
+
+                context_length = input_ids.index(tokenizer.bos_token_id)
+                mask_position = context_length - 1
+                labels = [-100] * context_length + input_ids[mask_position+1:]
+                
+                pad_len = max_seq_length - len(input_ids)
+                input_ids = input_ids + [tokenizer.pad_token_id] * pad_len
+                labels = labels + [tokenizer.pad_token_id] * pad_len
+                if data_args.ignore_pad_token_for_loss:
+                    labels = [(l if l != tokenizer.pad_token_id else -100) for l in labels]
+
+                model_inputs["input_ids"].append(input_ids)
+                model_inputs["labels"].append(labels)
+
+        return model_inputs
+    
+    def print_dataset_example(example):
+        print("input_ids",example["input_ids"])
+        print("inputs", tokenizer.decode(example["input_ids"]))
+        print("label_ids", example["labels"])
+        print("labels", tokenizer.decode(example["labels"]))
+
+    if training_args.do_train:
+        if "train" not in raw_datasets:
+            raise ValueError("--do_train requires a train dataset")
+        train_dataset = raw_datasets["train"]
+        if data_args.max_train_samples is not None:
+            max_train_samples = min(len(train_dataset), data_args.max_train_samples)
+            train_dataset = train_dataset.select(range(max_train_samples))
+        with training_args.main_process_first(desc="train dataset map pre-processing"):
+            train_dataset = train_dataset.map(
+                preprocess_function_train,
+                batched=True,
+                num_proc=data_args.preprocessing_num_workers,
+                remove_columns=column_names,
+                load_from_cache_file=not data_args.overwrite_cache,
+                desc="Running tokenizer on train dataset",
+            )
+        print_dataset_example(train_dataset[0])
+
+    if training_args.do_eval:
+        max_target_length = data_args.val_max_target_length
+        if "validation" not in raw_datasets:
+            raise ValueError("--do_eval requires a validation dataset")
+        eval_dataset = raw_datasets["validation"]
+        if data_args.max_eval_samples is not None:
+            max_eval_samples = min(len(eval_dataset), data_args.max_eval_samples)
+            eval_dataset = eval_dataset.select(range(max_eval_samples))
+        with training_args.main_process_first(desc="validation dataset map pre-processing"):
+            eval_dataset = eval_dataset.map(
+                preprocess_function_eval,
+                batched=True,
+                num_proc=data_args.preprocessing_num_workers,
+                remove_columns=column_names,
+                load_from_cache_file=not data_args.overwrite_cache,
+                desc="Running tokenizer on validation dataset",
+            )
+        print_dataset_example(eval_dataset[0])
+
+    if training_args.do_predict:
+        max_target_length = data_args.val_max_target_length
+        if "test" not in raw_datasets:
+            raise ValueError("--do_predict requires a test dataset")
+        predict_dataset = raw_datasets["test"]
+        if data_args.max_predict_samples is not None:
+            max_predict_samples = min(len(predict_dataset), data_args.max_predict_samples)
+            predict_dataset = predict_dataset.select(range(max_predict_samples))
+        with training_args.main_process_first(desc="prediction dataset map pre-processing"):
+            predict_dataset = predict_dataset.map(
+                preprocess_function_eval,
+                batched=True,
+                num_proc=data_args.preprocessing_num_workers,
+                remove_columns=column_names,
+                load_from_cache_file=not data_args.overwrite_cache,
+                desc="Running tokenizer on prediction dataset",
+            )
+        print_dataset_example(predict_dataset[0])
+
+    # Data collator
+    label_pad_token_id = -100 if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
+    data_collator = DataCollatorForSeq2Seq(
+        tokenizer,
+        model=model,
+        label_pad_token_id=label_pad_token_id,
+        pad_to_multiple_of=None,
+        padding=False
+    )
+
+    # Metric
+    def compute_metrics(eval_preds):
+        preds, labels = eval_preds
+        if isinstance(preds, tuple):
+            preds = preds[0]
+        decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)
+        if data_args.ignore_pad_token_for_loss:
+            # Replace -100 in the labels as we can't decode them.
+            labels = np.where(labels != -100, labels, tokenizer.pad_token_id)
+        decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)
+
+        score_dict = {
+            "rouge-1": [],
+            "rouge-2": [],
+            "rouge-l": [],
+            "bleu-4": []
+        }
+        for pred, label in zip(decoded_preds, decoded_labels):
+            hypothesis = list(jieba.cut(pred))
+            reference = list(jieba.cut(label))
+            rouge = Rouge()
+            scores = rouge.get_scores(' '.join(hypothesis) , ' '.join(reference))
+            result = scores[0]
+            
+            for k, v in result.items():
+                score_dict[k].append(round(v["f"] * 100, 4))
+            bleu_score = sentence_bleu([list(label)], list(pred), smoothing_function=SmoothingFunction().method3)
+            score_dict["bleu-4"].append(round(bleu_score * 100, 4))
+
+        for k, v in score_dict.items():
+            score_dict[k] = float(np.mean(v))
+        return score_dict
+
+    # Override the decoding parameters of Seq2SeqTrainer
+    training_args.generation_max_length = (
+        training_args.generation_max_length
+        if training_args.generation_max_length is not None
+        else data_args.val_max_target_length
+    )
+    training_args.generation_num_beams = (
+        data_args.num_beams if data_args.num_beams is not None else training_args.generation_num_beams
+    )
+    # Initialize our Trainer
+    trainer = Seq2SeqTrainer(
+        model=model,
+        args=training_args,
+        train_dataset=train_dataset if training_args.do_train else None,
+        eval_dataset=eval_dataset if training_args.do_eval else None,
+        tokenizer=tokenizer,
+        data_collator=data_collator,
+        compute_metrics=compute_metrics if training_args.predict_with_generate else None,
+        save_prefixencoder=model_args.pre_seq_len is not None
+    )
+
+    # Training
+    if training_args.do_train:
+        checkpoint = None
+        if training_args.resume_from_checkpoint is not None:
+            checkpoint = training_args.resume_from_checkpoint
+        # elif last_checkpoint is not None:
+        #     checkpoint = last_checkpoint
+        model.gradient_checkpointing_enable()
+        model.enable_input_require_grads()
+        train_result = trainer.train(resume_from_checkpoint=checkpoint)
+        # trainer.save_model()  # Saves the tokenizer too for easy upload
+
+        metrics = train_result.metrics
+        max_train_samples = (
+            data_args.max_train_samples if data_args.max_train_samples is not None else len(train_dataset)
+        )
+        metrics["train_samples"] = min(max_train_samples, len(train_dataset))
+
+        trainer.log_metrics("train", metrics)
+        trainer.save_metrics("train", metrics)
+        trainer.save_state()
+
+    # Evaluation
+    results = {}
+    max_seq_length = data_args.max_source_length + data_args.max_target_length + 1
+    if training_args.do_eval:
+        logger.info("*** Evaluate ***")
+        metrics = trainer.evaluate(metric_key_prefix="eval", do_sample=True, top_p=0.7, max_length=max_seq_length, temperature=0.95)
+        max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
+        metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
+
+        trainer.log_metrics("eval", metrics)
+        trainer.save_metrics("eval", metrics)
+
+    if training_args.do_predict:
+        logger.info("*** Predict ***")
+        predict_results = trainer.predict(predict_dataset, metric_key_prefix="predict", max_length=max_seq_length, do_sample=True, top_p=0.7, temperature=0.95)
+        metrics = predict_results.metrics
+        max_predict_samples = (
+            data_args.max_predict_samples if data_args.max_predict_samples is not None else len(predict_dataset)
+        )
+        metrics["predict_samples"] = min(max_predict_samples, len(predict_dataset))
+
+        trainer.log_metrics("predict", metrics)
+        trainer.save_metrics("predict", metrics)
+
+        if trainer.is_world_process_zero():
+            if training_args.predict_with_generate:
+                predictions = tokenizer.batch_decode(
+                    predict_results.predictions, skip_special_tokens=True, clean_up_tokenization_spaces=True
+                )
+                predictions = [pred.strip() for pred in predictions]
+                labels = tokenizer.batch_decode(
+                    predict_results.label_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
+                )
+                labels = [label.strip() for label in labels]
+                output_prediction_file = os.path.join(training_args.output_dir, "generated_predictions.txt")
+                with open(output_prediction_file, "w", encoding="utf-8") as writer:
+                    for p, l in zip(predictions, labels):
+                        res = json.dumps({"labels": l, "predict": p}, ensure_ascii=False)
+                        writer.write(f"{res}\n")
+    return results
+
+
+def _mp_fn(index):
+    # For xla_spawn (TPUs)
+    main()
+
+
+if __name__ == "__main__":
+    main()

ptuning/pt_train.sh

+PRE_SEQ_LEN=128
+LR=5e-3
+
+MASTER_PORT=$(shuf -n 1 -i 10000-65535)
+
+CUDA_VISIBLE_DEVICES=0,1,2,3 deepspeed --master_port $MASTER_PORT main.py \
+    --deepspeed deepspeed_p.json \
+    --do_train \
+    --train_file AdvertiseGen/train.json \
+    --test_file AdvertiseGen/dev.json \
+    --prompt_column content \
+    --response_column summary \
+    --overwrite_cache \
+    --model_name_or_path THUDM/chatglm-6b \
+    --output_dir ./output_pt/adgen-chatglm-6b-pt-4c-$LR \
+    --overwrite_output_dir \
+    --max_source_length 64 \
+    --max_target_length 64 \
+    --per_device_train_batch_size 16 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 1 \
+    --predict_with_generate \
+    --max_steps 3000 \
+    --logging_steps 10 \
+    --save_steps 1000 \
+    --learning_rate $LR \
+    --pre_seq_len $PRE_SEQ_LEN \
+    --fp16
+ 
\ No newline at end of file

ptuning/train_chat.sh

+PRE_SEQ_LEN=128
+LR=1e-2
+
+CUDA_VISIBLE_DEVICES=0 python3 main.py \
+    --do_train \
+    --train_file $CHAT_TRAIN_DATA \
+    --validation_file $CHAT_VAL_DATA \
+    --prompt_column prompt \
+    --response_column response \
+    --history_column history \
+    --overwrite_cache \
+    --model_name_or_path THUDM/chatglm-6b \
+    --output_dir $CHECKPOINT_NAME \
+    --overwrite_output_dir \
+    --max_source_length 256 \
+    --max_target_length 256 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 16 \
+    --predict_with_generate \
+    --max_steps 3000 \
+    --logging_steps 10 \
+    --save_steps 1000 \
+    --learning_rate $LR \
+    --pre_seq_len $PRE_SEQ_LEN \
+    --quantization_bit 4
+

ptuning/trainer_seq2seq.py

+# Copyright 2020 The HuggingFace Team. All rights reserved.
+#
+# 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 typing import Any, Dict, List, Optional, Tuple, Union
+
+import torch
+from torch import nn
+from torch.utils.data import Dataset
+
+from transformers.deepspeed import is_deepspeed_zero3_enabled
+from trainer import Trainer
+from transformers.trainer_utils import PredictionOutput
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class Seq2SeqTrainer(Trainer):
+    def evaluate(
+        self,
+        eval_dataset: Optional[Dataset] = None,
+        ignore_keys: Optional[List[str]] = None,
+        metric_key_prefix: str = "eval",
+        **gen_kwargs
+    ) -> Dict[str, float]:
+        """
+        Run evaluation and returns metrics.
+
+        The calling script will be responsible for providing a method to compute metrics, as they are task-dependent
+        (pass it to the init `compute_metrics` argument).
+
+        You can also subclass and override this method to inject custom behavior.
+
+        Args:
+            eval_dataset (`Dataset`, *optional*):
+                Pass a dataset if you wish to override `self.eval_dataset`. If it is an [`~datasets.Dataset`], columns
+                not accepted by the `model.forward()` method are automatically removed. It must implement the `__len__`
+                method.
+            ignore_keys (`List[str]`, *optional*):
+                A list of keys in the output of your model (if it is a dictionary) that should be ignored when
+                gathering predictions.
+            metric_key_prefix (`str`, *optional*, defaults to `"eval"`):
+                An optional prefix to be used as the metrics key prefix. For example the metrics "bleu" will be named
+                "eval_bleu" if the prefix is `"eval"` (default)
+            max_length (`int`, *optional*):
+                The maximum target length to use when predicting with the generate method.
+            num_beams (`int`, *optional*):
+                Number of beams for beam search that will be used when predicting with the generate method. 1 means no
+                beam search.
+            gen_kwargs:
+                Additional `generate` specific kwargs.
+
+        Returns:
+            A dictionary containing the evaluation loss and the potential metrics computed from the predictions. The
+            dictionary also contains the epoch number which comes from the training state.
+        """
+
+        gen_kwargs = gen_kwargs.copy()
+        if gen_kwargs.get("max_length") is None and gen_kwargs.get("max_new_tokens") is None:
+            gen_kwargs["max_length"] = self.args.generation_max_length
+        gen_kwargs["num_beams"] = (
+            gen_kwargs["num_beams"] if gen_kwargs.get("num_beams") is not None else self.args.generation_num_beams
+        )
+        self._gen_kwargs = gen_kwargs
+
+        return super().evaluate(eval_dataset, ignore_keys=ignore_keys, metric_key_prefix=metric_key_prefix)
+
+    def predict(
+        self,
+        test_dataset: Dataset,
+        ignore_keys: Optional[List[str]] = None,
+        metric_key_prefix: str = "test",
+        **gen_kwargs
+    ) -> PredictionOutput:
+        """
+        Run prediction and returns predictions and potential metrics.
+
+        Depending on the dataset and your use case, your test dataset may contain labels. In that case, this method
+        will also return metrics, like in `evaluate()`.
+
+        Args:
+            test_dataset (`Dataset`):
+                Dataset to run the predictions on. If it is a [`~datasets.Dataset`], columns not accepted by the
+                `model.forward()` method are automatically removed. Has to implement the method `__len__`
+            ignore_keys (`List[str]`, *optional*):
+                A list of keys in the output of your model (if it is a dictionary) that should be ignored when
+                gathering predictions.
+            metric_key_prefix (`str`, *optional*, defaults to `"eval"`):
+                An optional prefix to be used as the metrics key prefix. For example the metrics "bleu" will be named
+                "eval_bleu" if the prefix is `"eval"` (default)
+            max_length (`int`, *optional*):
+                The maximum target length to use when predicting with the generate method.
+            num_beams (`int`, *optional*):
+                Number of beams for beam search that will be used when predicting with the generate method. 1 means no
+                beam search.
+            gen_kwargs:
+                Additional `generate` specific kwargs.
+
+        <Tip>
+
+        If your predictions or labels have different sequence lengths (for instance because you're doing dynamic
+        padding in a token classification task) the predictions will be padded (on the right) to allow for
+        concatenation into one array. The padding index is -100.
+
+        </Tip>
+
+        Returns: *NamedTuple* A namedtuple with the following keys:
+
+            - predictions (`np.ndarray`): The predictions on `test_dataset`.
+            - label_ids (`np.ndarray`, *optional*): The labels (if the dataset contained some).
+            - metrics (`Dict[str, float]`, *optional*): The potential dictionary of metrics (if the dataset contained
+              labels).
+        """
+
+        gen_kwargs = gen_kwargs.copy()
+        if gen_kwargs.get("max_length") is None and gen_kwargs.get("max_new_tokens") is None:
+            gen_kwargs["max_length"] = self.args.generation_max_length
+        gen_kwargs["num_beams"] = (
+            gen_kwargs["num_beams"] if gen_kwargs.get("num_beams") is not None else self.args.generation_num_beams
+        )
+        self._gen_kwargs = gen_kwargs
+
+
+        return super().predict(test_dataset, ignore_keys=ignore_keys, metric_key_prefix=metric_key_prefix)
+
+    def prediction_step(
+        self,
+        model: nn.Module,
+        inputs: Dict[str, Union[torch.Tensor, Any]],
+        prediction_loss_only: bool,
+        ignore_keys: Optional[List[str]] = None,
+    ) -> Tuple[Optional[float], Optional[torch.Tensor], Optional[torch.Tensor]]:
+        """
+        Perform an evaluation step on `model` using `inputs`.
+
+        Subclass and override to inject custom behavior.
+
+        Args:
+            model (`nn.Module`):
+                The model to evaluate.
+            inputs (`Dict[str, Union[torch.Tensor, Any]]`):
+                The inputs and targets of the model.
+
+                The dictionary will be unpacked before being fed to the model. Most models expect the targets under the
+                argument `labels`. Check your model's documentation for all accepted arguments.
+            prediction_loss_only (`bool`):
+                Whether or not to return the loss only.
+
+        Return:
+            Tuple[Optional[float], Optional[torch.Tensor], Optional[torch.Tensor]]: A tuple with the loss, logits and
+            labels (each being optional).
+        """
+
+        if not self.args.predict_with_generate or prediction_loss_only:
+            return super().prediction_step(
+                model, inputs, prediction_loss_only=prediction_loss_only, ignore_keys=ignore_keys
+            )
+
+        has_labels = "labels" in inputs
+        inputs = self._prepare_inputs(inputs)
+
+        # XXX: adapt synced_gpus for fairscale as well
+        gen_kwargs = self._gen_kwargs.copy()
+        if gen_kwargs.get("max_length") is None and gen_kwargs.get("max_new_tokens") is None:
+            gen_kwargs["max_length"] = self.model.config.max_length
+        gen_kwargs["num_beams"] = (
+            gen_kwargs["num_beams"] if gen_kwargs.get("num_beams") is not None else self.model.config.num_beams
+        )
+        default_synced_gpus = True if is_deepspeed_zero3_enabled() else False
+        gen_kwargs["synced_gpus"] = (
+            gen_kwargs["synced_gpus"] if gen_kwargs.get("synced_gpus") is not None else default_synced_gpus
+        )
+
+        if "attention_mask" in inputs:
+            gen_kwargs["attention_mask"] = inputs.get("attention_mask", None)
+        if "position_ids" in inputs:
+            gen_kwargs["position_ids"] = inputs.get("position_ids", None)
+        if "global_attention_mask" in inputs:
+            gen_kwargs["global_attention_mask"] = inputs.get("global_attention_mask", None)
+
+        # prepare generation inputs
+        # some encoder-decoder models can have varying encoder's and thus
+        # varying model input names
+        if hasattr(self.model, "encoder") and self.model.encoder.main_input_name != self.model.main_input_name:
+            generation_inputs = inputs[self.model.encoder.main_input_name]
+        else:
+            generation_inputs = inputs[self.model.main_input_name]
+
+        gen_kwargs["input_ids"] = generation_inputs
+        generated_tokens = self.model.generate(**gen_kwargs)
+        generated_tokens = generated_tokens[:, generation_inputs.size()[-1]:]
+
+        # in case the batch is shorter than max length, the output should be padded
+        if gen_kwargs.get("max_length") is not None and generated_tokens.shape[-1] < gen_kwargs["max_length"]:
+            generated_tokens = self._pad_tensors_to_max_len(generated_tokens, gen_kwargs["max_length"])
+        elif gen_kwargs.get("max_new_tokens") is not None and generated_tokens.shape[-1] < (
+            gen_kwargs["max_new_tokens"] + 1
+        ):
+            generated_tokens = self._pad_tensors_to_max_len(generated_tokens, gen_kwargs["max_new_tokens"] + 1)
+
+        loss = None
+
+        if self.args.prediction_loss_only:
+            return (loss, None, None)
+
+        if has_labels:
+            labels = inputs["labels"]
+            if gen_kwargs.get("max_length") is not None and labels.shape[-1] < gen_kwargs["max_length"]:
+                labels = self._pad_tensors_to_max_len(labels, gen_kwargs["max_length"])
+            elif gen_kwargs.get("max_new_tokens") is not None and labels.shape[-1] < (
+                gen_kwargs["max_new_tokens"] + 1
+            ):
+                labels = self._pad_tensors_to_max_len(labels, (gen_kwargs["max_new_tokens"] + 1))
+        else:
+            labels = None
+
+        return (loss, generated_tokens, labels)
+
+    def _pad_tensors_to_max_len(self, tensor, max_length):
+        if self.tokenizer is not None and hasattr(self.tokenizer, "pad_token_id"):
+            # If PAD token is not defined at least EOS token has to be defined
+            pad_token_id = (
+                self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id
+            )
+        else:
+            if self.model.config.pad_token_id is not None:
+                pad_token_id = self.model.config.pad_token_id
+            else:
+                raise ValueError("Pad_token_id must be set in the configuration of the model, in order to pad tensors")
+
+        padded_tensor = pad_token_id * torch.ones(
+            (tensor.shape[0], max_length), dtype=tensor.dtype, device=tensor.device
+        )
+        padded_tensor[:, : tensor.shape[-1]] = tensor
+        return padded_tensor

ptuning/web_demo.py

+import os, sys
+
+import gradio as gr
+import mdtex2html
+
+import torch
+import transformers
+from transformers import (
+    AutoConfig,
+    AutoModel,
+    AutoTokenizer,
+    AutoTokenizer,
+    DataCollatorForSeq2Seq,
+    HfArgumentParser,
+    Seq2SeqTrainingArguments,
+    set_seed,
+)
+
+from arguments import ModelArguments, DataTrainingArguments
+
+
+model = None
+tokenizer = None
+
+"""Override Chatbot.postprocess"""
+
+
+def postprocess(self, y):
+    if y is None:
+        return []
+    for i, (message, response) in enumerate(y):
+        y[i] = (
+            None if message is None else mdtex2html.convert((message)),
+            None if response is None else mdtex2html.convert(response),
+        )
+    return y
+
+
+gr.Chatbot.postprocess = postprocess
+
+
+def parse_text(text):
+    """copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/"""
+    lines = text.split("\n")
+    lines = [line for line in lines if line != ""]
+    count = 0
+    for i, line in enumerate(lines):
+        if "```" in line:
+            count += 1
+            items = line.split('`')
+            if count % 2 == 1:
+                lines[i] = f'<pre><code class="language-{items[-1]}">'
+            else:
+                lines[i] = f'<br></code></pre>'
+        else:
+            if i > 0:
+                if count % 2 == 1:
+                    line = line.replace("`", "\`")
+                    line = line.replace("<", "&lt;")
+                    line = line.replace(">", "&gt;")
+                    line = line.replace(" ", "&nbsp;")
+                    line = line.replace("*", "&ast;")
+                    line = line.replace("_", "&lowbar;")
+                    line = line.replace("-", "&#45;")
+                    line = line.replace(".", "&#46;")
+                    line = line.replace("!", "&#33;")
+                    line = line.replace("(", "&#40;")
+                    line = line.replace(")", "&#41;")
+                    line = line.replace("$", "&#36;")
+                lines[i] = "<br>"+line
+    text = "".join(lines)
+    return text
+
+
+def predict(input, chatbot, max_length, top_p, temperature, history):
+    chatbot.append((parse_text(input), ""))
+    for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+        chatbot[-1] = (parse_text(input), parse_text(response))       
+
+        yield chatbot, history
+
+
+def reset_user_input():
+    return gr.update(value='')
+
+
+def reset_state():
+    return [], []
+
+
+with gr.Blocks() as demo:
+    gr.HTML("""<h1 align="center">ChatGLM</h1>""")
+
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        with gr.Column(scale=4):
+            with gr.Column(scale=12):
+                user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style(
+                    container=False)
+            with gr.Column(min_width=32, scale=1):
+                submitBtn = gr.Button("Submit", variant="primary")
+        with gr.Column(scale=1):
+            emptyBtn = gr.Button("Clear History")
+            max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
+            top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
+            temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
+
+    history = gr.State([])
+
+    submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history],
+                    show_progress=True)
+    submitBtn.click(reset_user_input, [], [user_input])
+
+    emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
+
+
+
+def main():
+    global model, tokenizer
+
+    parser = HfArgumentParser((
+        ModelArguments))
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
+        # If we pass only one argument to the script and it's the path to a json file,
+        # let's parse it to get our arguments.
+        model_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))[0]
+    else:
+        model_args = parser.parse_args_into_dataclasses()[0]
+
+    tokenizer = AutoTokenizer.from_pretrained(
+        model_args.model_name_or_path, trust_remote_code=True)
+    config = AutoConfig.from_pretrained(
+        model_args.model_name_or_path, trust_remote_code=True)
+
+    config.pre_seq_len = model_args.pre_seq_len
+    config.prefix_projection = model_args.prefix_projection
+
+    if model_args.ptuning_checkpoint is not None:
+        print(f"Loading prefix_encoder weight from {model_args.ptuning_checkpoint}")
+        model = AutoModel.from_pretrained(model_args.model_name_or_path, config=config, trust_remote_code=True)
+        prefix_state_dict = torch.load(os.path.join(model_args.ptuning_checkpoint, "pytorch_model.bin"))
+        new_prefix_state_dict = {}
+        for k, v in prefix_state_dict.items():
+            if k.startswith("transformer.prefix_encoder."):
+                new_prefix_state_dict[k[len("transformer.prefix_encoder."):]] = v
+        model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict)
+    else:
+        model = AutoModel.from_pretrained(model_args.model_name_or_path, config=config, trust_remote_code=True)
+
+    if model_args.quantization_bit is not None:
+        print(f"Quantized to {model_args.quantization_bit} bit")
+        model = model.quantize(model_args.quantization_bit)
+
+    if model_args.pre_seq_len is not None:
+        # P-tuning v2
+        model = model.half().cuda()
+        model.transformer.prefix_encoder.float().cuda()
+    
+    model = model.eval()
+    demo.queue().launch(share=False, inbrowser=True)
+
+
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file

ptuning/web_demo.sh

+PRE_SEQ_LEN=128
+
+CUDA_VISIBLE_DEVICES=0 python3 web_demo.py \
+    --model_name_or_path THUDM/chatglm-6b \
+    --ptuning_checkpoint output/adgen-chatglm-6b-pt-128-2e-2/checkpoint-3000 \
+    --pre_seq_len $PRE_SEQ_LEN
+

readme.txt

+0、目录
+/zhaoy/ChatGLM-6B/ptuning
+
+1、Ptuning-v2
+bash pt_train_ds.sh
+
+
+2、全参数微调：
+bash ds_train_finetune.sh

requirements.txt

+protobuf
+transformers==4.27.1
+gradio
+mdtex2html
+sentencepiece
+accelerate
\ No newline at end of file

train_test.json

+{"content": "性感*图案#线条*裤型#阔腿裤#类型#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤#裤*版型#宽松*风格#性感*图案#线条*裤型#阔腿裤", "summary": "毕竟好穿时尚，谁都能穿出腿长2米的效果宽松的裤腿，当然是遮肉小能手啊。上身随性自然不拘束，面料亲肤舒适贴身体验感棒棒哒。系带部分增加设计看点，还让单品的设计感更强。腿部线条若隐若现的，性感撩人。颜色敲温柔的，与裤子本身所呈现的风格有点反差萌。明星时尚达人的心头爱。毕竟好穿时尚，谁都能穿出腿长2米的效果宽松的裤腿，当然是遮肉小能手啊。上身随性自然不拘束，面料亲肤舒适贴身体验感棒棒哒。系带部分增加设计看点，还让单品的设计感更强。腿部线条若隐若现的，性感撩人。颜色敲温柔的，与裤子本身所呈现的风格有点反差萌，明星时尚达人的心头爱。毕竟好穿时尚，谁都能穿出腿长2米的效果宽松的裤腿，当然是遮肉小能手啊。上身随性自然不拘束，面料亲肤舒适贴身体验感棒棒哒。系带部分增加设计看点，还让单品的设计感更强。腿部线条若隐若现的，性感撩人。颜色敲温柔的，与裤子本身所呈现的风格有点反差萌，与裤子本身所呈现的风格有点反差萌，明星时尚达人的心头爱。毕竟好穿时尚，谁都能穿出腿长2米的效果宽松的裤腿，当然是遮肉小能手啊。上身随性自然不拘束，面料亲肤舒适贴身体验感棒棒哒。系带部分增加设计看点，还让单品的设计感更强。腿部线条若隐若现的，性感撩人。颜色敲温柔的，与裤子本身所呈现的风格有点反差萌，与裤子本身所呈现的风格有点反差萌，明星时尚达人的心头爱。毕竟好穿时尚，谁都能穿出腿长2米的效果宽松的裤腿，当然是遮肉小能手啊。上身随性自然不拘束，面料亲肤舒适贴身体验感棒棒哒。系带部分增加设计看点，还让单品的设计感更强。腿部线条若隐若现的，性感撩人。颜色敲温柔的，与裤子本身所呈现的风格有点反差萌。"}
+{"content": "类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖", "summary": "圆形领口修饰脖颈线条，适合各种脸型，耐看有气质。无袖设计，尤显清凉，简约横条纹装饰，使得整身人鱼造型更为生动立体。加之撞色的鱼尾下摆，深邃富有诗意。收腰包臀,修饰女性身体曲线，结合别出心裁的鱼尾裙摆设计，勾勒出自然流畅的身体轮廓，展现了婀娜多姿的迷人姿态。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。圆形领口修饰脖颈线条，适合各种脸型，耐看有气质。无袖设计，尤显清凉，简约横条纹装饰，使得整身人鱼造型更为生动立体。加之撞色的鱼尾下摆，深邃富有诗意。收腰包臀,修饰女性身体曲线，结合别出心裁的鱼尾裙摆设计，勾勒出自然流畅的身体轮廓，展现了婀娜多姿的迷人姿态。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。"}
+{"content": "类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖", "summary": "圆形领口修饰脖颈线条，适合各种脸型，耐看有气质。无袖设计，尤显清凉，简约横条纹装饰，使得整身人鱼造型更为生动立体。加之撞色的鱼尾下摆，深邃富有诗意。收腰包臀,修饰女性身体曲线，结合别出心裁的鱼尾裙摆设计，勾勒出自然流畅的身体轮廓，展现了婀娜多姿的迷人姿态。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。圆形领口修饰脖颈线条，适合各种脸型，耐看有气质。无袖设计，尤显清凉，简约横条纹装饰，使得整身人鱼造型更为生动立体。加之撞色的鱼尾下摆，深邃富有诗意。收腰包臀,修饰女性身体曲线，结合别出心裁的鱼尾裙摆设计，勾勒出自然流畅的身体轮廓，展现了婀娜多姿的迷人姿态。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。"}
+{"content": "类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖类型#裙*风格#简约*图案#条纹*图案#线条*图案#撞色*裙型#鱼尾裙*裙袖长#无袖", "summary": "圆形领口修饰脖颈线条，适合各种脸型，耐看有气质。无袖设计，尤显清凉，简约横条纹装饰，使得整身人鱼造型更为生动立体。加之撞色的鱼尾下摆，深邃富有诗意。收腰包臀,修饰女性身体曲线，结合别出心裁的鱼尾裙摆设计，勾勒出自然流畅的身体轮廓，展现了婀娜多姿的迷人姿态。款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。圆形领口修饰脖颈线条，适合各种脸型，耐看有气质。无袖设计，尤显清凉，简约横条纹装饰，使得整身人鱼造型更为生动立体。加之撞色的鱼尾下摆，深邃富有诗意。收腰包臀,修饰女性身体曲线，结合别出心裁的鱼尾裙摆设计，勾勒出自然流畅的身体轮廓，展现了婀娜多姿的迷人姿态。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。一款温暖柔软又富有弹性的针织衫，不仅可以抵御严寒侵袭，还能更好地进行搭配。v领的设计，能勾勒出迷人的天鹅颈以及衬托出娇小的脸型。宽松又别致的剪裁，能从视觉上显露纤长的下半身，起到显瘦的效果。直筒造型的袖子，修饰出优美的手臂线条，衣身上的方格刺绣，时尚又吸睛。"}

utils.py

+import os
+from typing import Dict, Tuple, Union, Optional
+
+from torch.nn import Module
+from transformers import AutoModel
+
+
+def auto_configure_device_map(num_gpus: int) -> Dict[str, int]:
+    # transformer.word_embeddings 占用1层
+    # transformer.final_layernorm 和 lm_head 占用1层
+    # transformer.layers 占用 28 层
+    # 总共30层分配到num_gpus张卡上
+    num_trans_layers = 28
+    per_gpu_layers = 30 / num_gpus
+
+    # bugfix: 在linux中调用torch.embedding传入的weight,input不在同一device上,导致RuntimeError
+    # windows下 model.device 会被设置成 transformer.word_embeddings.device
+    # linux下 model.device 会被设置成 lm_head.device
+    # 在调用chat或者stream_chat时,input_ids会被放到model.device上
+    # 如果transformer.word_embeddings.device和model.device不同,则会导致RuntimeError
+    # 因此这里将transformer.word_embeddings,transformer.final_layernorm,lm_head都放到第一张卡上
+    device_map = {'transformer.word_embeddings': 0,
+                  'transformer.final_layernorm': 0, 'lm_head': 0}
+
+    used = 2
+    gpu_target = 0
+    for i in range(num_trans_layers):
+        if used >= per_gpu_layers:
+            gpu_target += 1
+            used = 0
+        assert gpu_target < num_gpus
+        device_map[f'transformer.layers.{i}'] = gpu_target
+        used += 1
+
+    return device_map
+
+
+def load_model_on_gpus(checkpoint_path: Union[str, os.PathLike], num_gpus: int = 2,
+                       device_map: Optional[Dict[str, int]] = None, **kwargs) -> Module:
+    if num_gpus < 2 and device_map is None:
+        model = AutoModel.from_pretrained(checkpoint_path, trust_remote_code=True, **kwargs).half().cuda()
+    else:
+        from accelerate import dispatch_model
+
+        model = AutoModel.from_pretrained(checkpoint_path, trust_remote_code=True, **kwargs).half()
+
+        if device_map is None:
+            device_map = auto_configure_device_map(num_gpus)
+
+        model = dispatch_model(model, device_map=device_map)
+
+    return model
+
+

web_demo.py

+from transformers import AutoModel, AutoTokenizer
+import gradio as gr
+import mdtex2html
+
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+model = model.eval()
+
+"""Override Chatbot.postprocess"""
+
+
+def postprocess(self, y):
+    if y is None:
+        return []
+    for i, (message, response) in enumerate(y):
+        y[i] = (
+            None if message is None else mdtex2html.convert((message)),
+            None if response is None else mdtex2html.convert(response),
+        )
+    return y
+
+
+gr.Chatbot.postprocess = postprocess
+
+
+def parse_text(text):
+    """copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/"""
+    lines = text.split("\n")
+    lines = [line for line in lines if line != ""]
+    count = 0
+    for i, line in enumerate(lines):
+        if "```" in line:
+            count += 1
+            items = line.split('`')
+            if count % 2 == 1:
+                lines[i] = f'<pre><code class="language-{items[-1]}">'
+            else:
+                lines[i] = f'<br></code></pre>'
+        else:
+            if i > 0:
+                if count % 2 == 1:
+                    line = line.replace("`", "\`")
+                    line = line.replace("<", "&lt;")
+                    line = line.replace(">", "&gt;")
+                    line = line.replace(" ", "&nbsp;")
+                    line = line.replace("*", "&ast;")
+                    line = line.replace("_", "&lowbar;")
+                    line = line.replace("-", "&#45;")
+                    line = line.replace(".", "&#46;")
+                    line = line.replace("!", "&#33;")
+                    line = line.replace("(", "&#40;")
+                    line = line.replace(")", "&#41;")
+                    line = line.replace("$", "&#36;")
+                lines[i] = "<br>"+line
+    text = "".join(lines)
+    return text
+
+
+def predict(input, chatbot, max_length, top_p, temperature, history):
+    chatbot.append((parse_text(input), ""))
+    for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+        chatbot[-1] = (parse_text(input), parse_text(response))       
+
+        yield chatbot, history
+
+
+def reset_user_input():
+    return gr.update(value='')
+
+
+def reset_state():
+    return [], []
+
+
+with gr.Blocks() as demo:
+    gr.HTML("""<h1 align="center">ChatGLM</h1>""")
+
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        with gr.Column(scale=4):
+            with gr.Column(scale=12):
+                user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style(
+                    container=False)
+            with gr.Column(min_width=32, scale=1):
+                submitBtn = gr.Button("Submit", variant="primary")
+        with gr.Column(scale=1):
+            emptyBtn = gr.Button("Clear History")
+            max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
+            top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
+            temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
+
+    history = gr.State([])
+
+    submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history],
+                    show_progress=True)
+    submitBtn.click(reset_user_input, [], [user_input])
+
+    emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
+
+demo.queue().launch(share=False, inbrowser=True)

web_demo2.py

+from transformers import AutoModel, AutoTokenizer
+import streamlit as st
+from streamlit_chat import message
+
+
+st.set_page_config(
+    page_title="ChatGLM-6b 演示",
+    page_icon=":robot:"
+)
+
+
+@st.cache_resource
+def get_model():
+    tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+    model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+    model = model.eval()
+    return tokenizer, model
+
+
+MAX_TURNS = 20
+MAX_BOXES = MAX_TURNS * 2
+
+
+def predict(input, max_length, top_p, temperature, history=None):
+    tokenizer, model = get_model()
+    if history is None:
+        history = []
+
+    with container:
+        if len(history) > 0:
+            if len(history)>MAX_BOXES:
+                history = history[-MAX_TURNS:]
+            for i, (query, response) in enumerate(history):
+                message(query, avatar_style="big-smile", key=str(i) + "_user")
+                message(response, avatar_style="bottts", key=str(i))
+
+        message(input, avatar_style="big-smile", key=str(len(history)) + "_user")
+        st.write("AI正在回复:")
+        with st.empty():
+            for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+                query, response = history[-1]
+                st.write(response)
+
+    return history
+
+
+container = st.container()
+
+# create a prompt text for the text generation
+prompt_text = st.text_area(label="用户命令输入",
+            height = 100,
+            placeholder="请在这儿输入您的命令")
+
+max_length = st.sidebar.slider(
+    'max_length', 0, 4096, 2048, step=1
+)
+top_p = st.sidebar.slider(
+    'top_p', 0.0, 1.0, 0.6, step=0.01
+)
+temperature = st.sidebar.slider(
+    'temperature', 0.0, 1.0, 0.95, step=0.01
+)
+
+if 'state' not in st.session_state:
+    st.session_state['state'] = []
+
+if st.button("发送", key="predict"):
+    with st.spinner("AI正在思考，请稍等........"):
+        # text generation
+        st.session_state["state"] = predict(prompt_text, max_length, top_p, temperature, st.session_state["state"])

web_demo_old.py

+from transformers import AutoModel, AutoTokenizer
+import gradio as gr
+
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+model = model.eval()
+
+MAX_TURNS = 20
+MAX_BOXES = MAX_TURNS * 2
+
+
+def predict(input, max_length, top_p, temperature, history=None):
+    if history is None:
+        history = []
+    for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+        updates = []
+        for query, response in history:
+            updates.append(gr.update(visible=True, value="用户：" + query))
+            updates.append(gr.update(visible=True, value="ChatGLM-6B：" + response))
+        if len(updates) < MAX_BOXES:
+            updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates))
+        yield [history] + updates
+
+
+with gr.Blocks() as demo:
+    state = gr.State([])
+    text_boxes = []
+    for i in range(MAX_BOXES):
+        if i % 2 == 0:
+            text_boxes.append(gr.Markdown(visible=False, label="提问："))
+        else:
+            text_boxes.append(gr.Markdown(visible=False, label="回复："))
+
+    with gr.Row():
+        with gr.Column(scale=4):
+            txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter", lines=11).style(
+                container=False)
+        with gr.Column(scale=1):
+            max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
+            top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
+            temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
+            button = gr.Button("Generate")
+    button.click(predict, [txt, max_length, top_p, temperature, state], [state] + text_boxes)
+demo.queue().launch(share=False, inbrowser=True)