transformers==4.45.1
numpy==1.24.4
gguf==0.10.0
accelerate
openmind-hub
einops

from openmind import AutoModelForCausalLM, AutoTokenizer
from openmind import is_torch_npu_available
import torch
import argparse
import torch.nn.functional as F
import time

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="huangjingwang/NuExtract-1.5-tiny-GGUF",
    )
    args = parser.parse_args()
    return args

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"  
    #device = "cpu"  
    start_time = time.time()
    filename = "NuExtract-1.5-tiny.Q3_K_L.gguf"
    tokenizer = AutoTokenizer.from_pretrained(model_path, gguf_file=filename, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(
        model_path, torch_dtype=torch.float16, gguf_file=filename, device_map=device
    )

    
    prompt = "Q: What is the largest animal?\nA:"
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids
    input_ids = input_ids.to(model.device)
    generation_output = model.generate(input_ids=input_ids, max_new_tokens=32)

    print(tokenizer.decode(generation_output[0]))
    end_time = time.time()
    print(f"硬件环境：{device},推理执行时间：{end_time - start_time}秒")


if __name__ == "__main__":
    main()

import json
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

def predict_NuExtract(model, tokenizer, texts, template, batch_size=1, max_length=10_000, max_new_tokens=4_000):
    template = json.dumps(json.loads(template), indent=4)
    prompts = [f"""<|input|>\n### Template:\n{template}\n### Text:\n{text}\n\n<|output|>""" for text in texts]
    
    outputs = []
    with torch.no_grad():
        for i in range(0, len(prompts), batch_size):
            batch_prompts = prompts[i:i+batch_size]
            batch_encodings = tokenizer(batch_prompts, return_tensors="pt", truncation=True, padding=True, max_length=max_length).to(model.device)

            pred_ids = model.generate(**batch_encodings, max_new_tokens=max_new_tokens)
            outputs += tokenizer.batch_decode(pred_ids, skip_special_tokens=True)

    return [output.split("<|output|>")[1] for output in outputs]

model_name = "numind/NuExtract-tiny-v1.5"
device = "cuda"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True).to(device).eval()
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

text = """We introduce Mistral 7B, a 7–billion-parameter language model engineered for
superior performance and efficiency. Mistral 7B outperforms the best open 13B
model (Llama 2) across all evaluated benchmarks, and the best released 34B
model (Llama 1) in reasoning, mathematics, and code generation. Our model
leverages grouped-query attention (GQA) for faster inference, coupled with sliding
window attention (SWA) to effectively handle sequences of arbitrary length with a
reduced inference cost. We also provide a model fine-tuned to follow instructions,
Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and
automated benchmarks. Our models are released under the Apache 2.0 license.
Code: <https://github.com/mistralai/mistral-src>
Webpage: <https://mistral.ai/news/announcing-mistral-7b/>"""

template = """{
    "Model": {
        "Name": "",
        "Number of parameters": "",
        "Number of max token": "",
        "Architecture": []
    },
    "Usage": {
        "Use case": [],
        "Licence": ""
    }
}"""

prediction = predict_NuExtract(model, tokenizer, [text], template)[0]
print(prediction)

import json

MAX_INPUT_SIZE = 20_000
MAX_NEW_TOKENS = 6000

def clean_json_text(text):
    text = text.strip()
    text = text.replace("\#", "#").replace("\&", "&")
    return text

def predict_chunk(text, template, current, model, tokenizer):
    current = clean_json_text(current)

    input_llm =  f"<|input|>\n### Template:\n{template}\n### Current:\n{current}\n### Text:\n{text}\n\n<|output|>" + "{"
    input_ids = tokenizer(input_llm, return_tensors="pt", truncation=True, max_length=MAX_INPUT_SIZE).to("cuda")
    output = tokenizer.decode(model.generate(**input_ids, max_new_tokens=MAX_NEW_TOKENS)[0], skip_special_tokens=True)

    return clean_json_text(output.split("<|output|>")[1])

def split_document(document, window_size, overlap):
    tokens = tokenizer.tokenize(document)
    print(f"\tLength of document: {len(tokens)} tokens")

    chunks = []
    if len(tokens) > window_size:
        for i in range(0, len(tokens), window_size-overlap):
            print(f"\t{i} to {i + len(tokens[i:i + window_size])}")
            chunk = tokenizer.convert_tokens_to_string(tokens[i:i + window_size])
            chunks.append(chunk)

            if i + len(tokens[i:i + window_size]) >= len(tokens):
                break
    else:
        chunks.append(document)
    print(f"\tSplit into {len(chunks)} chunks")

    return chunks

def handle_broken_output(pred, prev):
    try:
        if all([(v in ["", []]) for v in json.loads(pred).values()]):
            # if empty json, return previous
            pred = prev
    except:
        # if broken json, return previous
        pred = prev

    return pred

def sliding_window_prediction(text, template, model, tokenizer, window_size=4000, overlap=128):
    # split text into chunks of n tokens
    tokens = tokenizer.tokenize(text)
    chunks = split_document(text, window_size, overlap)

    # iterate over text chunks
    prev = template
    for i, chunk in enumerate(chunks):
        print(f"Processing chunk {i}...")
        pred = predict_chunk(chunk, template, prev, model, tokenizer)

        # handle broken output
        pred = handle_broken_output(pred, prev)
            
        # iterate
        prev = pred

    return pred