Cyrilvallez

# BENCHMARK 2
# SECOND BENCHMARK OF ALL GENERATION METHODS

from transformers import AutoTokenizer, AutoModelForCausalLM, PhrasalConstraint
import torch
import time
from tqdm import tqdm
import numpy as np
import json

Cyrilvallez

import numpy as np
import matplotlib.pyplot as plt
import json

def load_json(filename: str) -> dict:
    with open(filename, 'r') as fp:
        data = json.load(fp)
    
    out = {}
    for k1, v1 in data.items():

Cyrilvallez

from transformers import AutoModelForCausalLM, AutoTokenizer, CompileConfig
import torch
import time
import warnings
warnings.filterwarnings("ignore")

device = 1

model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B", torch_dtype=torch.float16).to(device)
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")