from transformers import AutoTokenizer, TextGenerationPipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig


pretrained_model_dir = "facebook/opt-125m"
quantized_model_dir = "opt-125m-4bit"


tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
examples = [
    tokenizer(
        "auto-gptq is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm."
    )
]

quantize_config = BaseQuantizeConfig(
    bits=4,  # quantize model to 4-bit
    group_size=128,  # it is recommended to set the value to 128
)

# load un-quantized model, by default, the model will always be loaded into CPU memory
model = AutoGPTQForCausalLM.from_pretrained(pretrained_model_dir, quantize_config)

# quantize model, the examples should be list of dict whose keys can only be "input_ids" and "attention_mask"
model.quantize(examples, use_triton=False)

# save quantized model
model.save_quantized(quantized_model_dir)

# save quantized model using safetensors
model.save_quantized(quantized_model_dir, use_safetensors=True)

# load quantized model to the first GPU
model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device="cuda:0", use_triton=False)

# inference with model.generate
print(tokenizer.decode(model.generate(**tokenizer("auto_gptq is", return_tensors="pt").to("cuda:0"))[0]))

# or you can also use pipeline
pipeline = TextGenerationPipeline(model=model, tokenizer=tokenizer)
print(pipeline("auto-gptq is")[0]["generated_text"])

from auto_gptq.modeling import BaseGPTQForCausalLM


class OPTGPTQForCausalLM(BaseGPTQForCausalLM):
    # chained attribute name of transformer layer block
    layers_block_name = "model.decoder.layers"
    # chained attribute names of other nn modules that in the same level as the transformer layer block
    outside_layer_modules = [
        "model.decoder.embed_tokens", "model.decoder.embed_positions", "model.decoder.project_out",
        "model.decoder.project_in", "model.decoder.final_layer_norm"
    ]
    # chained attribute names of linear layers in transformer layer module
    # normally, there are four sub lists, for each one the modules in it can be seen as one operation, 
    # and the order should be the order when they are truly executed, in this case (and usually in most cases), 
    # they are: attention q_k_v projection, attention output projection, MLP project input, MLP project output
    inside_layer_modules = [
        ["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj"],
        ["self_attn.out_proj"],
        ["fc1"],
        ["fc2"]
    ]

from functools import partial

import datasets
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from auto_gptq.eval_tasks import SequenceClassificationTask


MODEL = "EleutherAI/gpt-j-6b"
DATASET = "cardiffnlp/tweet_sentiment_multilingual"
TEMPLATE = "Question:What's the sentiment of the given text? Choices are {labels}.\nText: {text}\nAnswer:"
ID2LABEL = {
    0: "negative",
    1: "neutral",
    2: "positive"
}
LABELS = list(ID2LABEL.values())


def ds_refactor_fn(samples):
    text_data = samples["text"]
    label_data = samples["label"]

    new_samples = {"prompt": [], "label": []}
    for text, label in zip(text_data, label_data):
        prompt = TEMPLATE.format(labels=LABELS, text=text)
        new_samples["prompt"].append(prompt)
        new_samples["label"].append(ID2LABEL[label])

    return new_samples


#  model = AutoModelForCausalLM.from_pretrained(MODEL).eval().half().to("cuda:0")
model = AutoGPTQForCausalLM.from_pretrained(MODEL, BaseQuantizeConfig())
tokenizer = AutoTokenizer.from_pretrained(MODEL)

task = SequenceClassificationTask(
        model=model,
        tokenizer=tokenizer,
        classes=LABELS,
        data_name_or_path=DATASET,
        prompt_col_name="prompt",
        label_col_name="label",
        **{
            "num_samples": 1000,  # how many samples will be sampled to evaluation
            "sample_max_len": 1024,  # max tokens for each sample
            "block_max_len": 2048,  # max tokens for each data block
            # function to load dataset, one must only accept data_name_or_path as input 
            # and return datasets.Dataset
            "load_fn": partial(datasets.load_dataset, name="english"),  
            # function to preprocess dataset, which is used for datasets.Dataset.map, 
            # must return Dict[str, list] with only two keys: [prompt_col_name, label_col_name]
            "preprocess_fn": ds_refactor_fn,  
            # truncate label when sample's length exceed sample_max_len
            "truncate_prompt": False  
        }
    )

# note that max_new_tokens will be automatically specified internally based on given classes
print(task.run())

# self-consistency
print(
    task.run(
        generation_config=GenerationConfig(
            num_beams=3,
            num_return_sequences=3,
            do_sample=True
        )
    )
)