大语言模型-alpaca-lora

• 微调
  大语言模型-ChatGLM-Tuning
  大语言模型-微调chatglm6b
  大语言模型-中文chatGLM-LLAMA微调
  大语言模型-alpaca-lora

• 本地知识库
  大语言模型2-document ai解读
  大语言模型-DocumentSearch解读
  大语言模型-中文Langchain

本文读的代码为
https://github.com/tloen/alpaca-lora

fine tune

其中fire的用法是: 对Fire进行一次调用即可将任何Python组件转变为命令行界面

• https://github.com/google/python-fire

prompt

• 从保存的template中读取prompt template
• 生成prompt，从输入的instruction，input和label

class Prompter(object):
    __slots__ = ("template", "_verbose")

    def __init__(self, template_name: str = "", verbose: bool = False):
        self._verbose = verbose
        if not template_name:
            # Enforce the default here, so the constructor can be called with '' and will not break.
            template_name = "alpaca"
        file_name = osp.join("templates", f"{template_name}.json")
        if not osp.exists(file_name):
            raise ValueError(f"Can't read {file_name}")
        with open(file_name) as fp:
            self.template = json.load(fp)
        if self._verbose:
            print(
                f"Using prompt template {template_name}: {self.template['description']}"
            )

    def generate_prompt(
        self,
        instruction: str,
        input: Union[None, str] = None,
        label: Union[None, str] = None,
    ) -> str:
        # returns the full prompt from instruction and optional input
        # if a label (=response, =output) is provided, it's also appended.
        if input:
            res = self.template["prompt_input"].format(
                instruction=instruction, input=input
            )
        else:
            res = self.template["prompt_no_input"].format(
                instruction=instruction
            )
        if label:
            res = f"{res}{label}"
        if self._verbose:
            print(res)
        return res

    def get_response(self, output: str) -> str:
        return output.split(self.template["response_split"])[1].strip()

callback

• 主要用于stream流

class Stream(transformers.StoppingCriteria):
    def __init__(self, callback_func=None):
        self.callback_func = callback_func

    def __call__(self, input_ids, scores) -> bool:
        if self.callback_func is not None:
            self.callback_func(input_ids[0])
        return False


class Iteratorize:

    """
    Transforms a function that takes a callback
    into a lazy iterator (generator).
    """

    def __init__(self, func, kwargs={}, callback=None):
        self.mfunc = func
        self.c_callback = callback
        self.q = Queue()
        self.sentinel = object()
        self.kwargs = kwargs
        self.stop_now = False

        def _callback(val):
            if self.stop_now:
                raise ValueError
            self.q.put(val)

        def gentask():
            try:
                ret = self.mfunc(callback=_callback, **self.kwargs)
            except ValueError:
                pass
            except:
                traceback.print_exc()
                pass

            self.q.put(self.sentinel)
            if self.c_callback:
                self.c_callback(ret)

        self.thread = Thread(target=gentask)
        self.thread.start()

    def __iter__(self):
        return self

    def __next__(self):
        obj = self.q.get(True, None)
        if obj is self.sentinel:
            raise StopIteration
        else:
            return obj

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        self.stop_now = True

模型相关

• transformers输入
• peft中的lora训练

model = LlamaForCausalLM.from_pretrained(
        base_model,
        load_in_8bit=True,
        torch_dtype=torch.float16,
        device_map=device_map,
    )
model = prepare_model_for_int8_training(model)

config = LoraConfig(
        r=lora_r,
        lora_alpha=lora_alpha,
        target_modules=lora_target_modules,
        lora_dropout=lora_dropout,
        bias="none",
        task_type="CAUSAL_LM",
    )
    model = get_peft_model(model, config)

tokenizer

tokenizer = LlamaTokenizer.from_pretrained(base_model)

    tokenizer.pad_token_id = (
        0  # unk. we want this to be different from the eos token
    )
    tokenizer.padding_side = "left"  # Allow batched inference

    def tokenize(prompt, add_eos_token=True):
        # there's probably a way to do this with the tokenizer settings
        # but again, gotta move fast
        result = tokenizer(
            prompt,
            truncation=True,
            max_length=cutoff_len,
            padding=False,
            return_tensors=None,
        )
        if (
            result["input_ids"][-1] != tokenizer.eos_token_id
            and len(result["input_ids"]) < cutoff_len
            and add_eos_token
        ):
            result["input_ids"].append(tokenizer.eos_token_id)
            result["attention_mask"].append(1)

        result["labels"] = result["input_ids"].copy()

        return result

    def generate_and_tokenize_prompt(data_point):
        full_prompt = prompter.generate_prompt(
            data_point["instruction"],
            data_point["input"],
            data_point["output"],
        )
        tokenized_full_prompt = tokenize(full_prompt)
        if not train_on_inputs:
            user_prompt = prompter.generate_prompt(
                data_point["instruction"], data_point["input"]
            )
            tokenized_user_prompt = tokenize(
                user_prompt, add_eos_token=add_eos_token
            )
            user_prompt_len = len(tokenized_user_prompt["input_ids"])

            if add_eos_token:
                user_prompt_len -= 1

            tokenized_full_prompt["labels"] = [
                -100
            ] * user_prompt_len + tokenized_full_prompt["labels"][
                user_prompt_len:
            ]  # could be sped up, probably
        return tokenized_full_prompt

训练

if val_set_size > 0:
        train_val = data["train"].train_test_split(
            test_size=val_set_size, shuffle=True, seed=42
        )
        train_data = (
            train_val["train"].shuffle().map(generate_and_tokenize_prompt)
        )
        val_data = (
            train_val["test"].shuffle().map(generate_and_tokenize_prompt)
        )
    else:
        train_data = data["train"].shuffle().map(generate_and_tokenize_prompt)
        val_data = None

    if not ddp and torch.cuda.device_count() > 1:
        # keeps Trainer from trying its own DataParallelism when more than 1 gpu is available
        model.is_parallelizable = True
        model.model_parallel = True

    trainer = transformers.Trainer(
        model=model,
        train_dataset=train_data,
        eval_dataset=val_data,
        args=transformers.TrainingArguments(
            per_device_train_batch_size=micro_batch_size,
            gradient_accumulation_steps=gradient_accumulation_steps,
            warmup_steps=100,
            num_train_epochs=num_epochs,
            learning_rate=learning_rate,
            fp16=True,
            logging_steps=10,
            optim="adamw_torch",
            evaluation_strategy="steps" if val_set_size > 0 else "no",
            save_strategy="steps",
            eval_steps=200 if val_set_size > 0 else None,
            save_steps=200,
            output_dir=output_dir,
            save_total_limit=3,
            load_best_model_at_end=True if val_set_size > 0 else False,
            ddp_find_unused_parameters=False if ddp else None,
            group_by_length=group_by_length,
            report_to="wandb" if use_wandb else None,
            run_name=wandb_run_name if use_wandb else None,
        ),
        data_collator=transformers.DataCollatorForSeq2Seq(
            tokenizer, pad_to_multiple_of=8, return_tensors="pt", padding=True
        ),
    )
    model.config.use_cache = False

    old_state_dict = model.state_dict
    model.state_dict = (
        lambda self, *_, **__: get_peft_model_state_dict(
            self, old_state_dict()
        )
    ).__get__(model, type(model))

    if torch.__version__ >= "2" and sys.platform != "win32":
        model = torch.compile(model)

    trainer.train(resume_from_checkpoint=resume_from_checkpoint)

    model.save_pretrained(output_dir)

    print(
        "\n If there's a warning about missing keys above, please disregard :)"
    )

推理generate

• import gradio as gr作为webui