DiffuCoder-7B-Base

import torch
from transformers import AutoModel, AutoTokenizer

model_path = "apple/DiffuCoder-7B-Base"
model = AutoModel.from_pretrained(model_path, torch_dtype=torch.bfloat16, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = model.to("cuda").eval()

prompt = """
from typing import List

def has_close_elements(numbers: List[float], threshold: float) -> bool:
    \"\"\"
    Check if in given list of numbers, are any two numbers closer to each other than given threshold.
    >>> has_close_elements([1.0, 2.0, 3.0], 0.5)
    False
    >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)
    True
    \"\"\"
"""

TOKEN_PER_STEP = 1 # diffusion timesteps * TOKEN_PER_STEP = total new tokens

inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs.input_ids.to(device="cuda")
attention_mask = inputs.attention_mask.to(device="cuda")

output = model.diffusion_generate(
    input_ids,
    attention_mask=attention_mask,
    max_new_tokens=256,
    output_history=True,
    return_dict_in_generate=True,
    steps=256//TOKEN_PER_STEP,
    temperature=0.2,
    top_p=0.95,
    alg="entropy",
    alg_temp=0.,
)
generations = [
    tokenizer.decode(g[len(p) :].tolist())
    for p, g in zip(input_ids, output.sequences)
]

print(generations[0].split(tokenizer.eos_token)[0])