OnAnOrange/

Qwen3-0.6B-right-shift-tulu-3-smoltalk-opc-sft-stage1_2-epochs-10-bs-2048-len-1024

import torch
import numpy as np
import torch.nn.functional as F

from transformers import AutoTokenizer, AutoModelForMaskedLM


def add_gumbel_noise(logits, temperature):
    if temperature == 0:
        return logits
    logits = logits.to(torch.float64)
    noise = torch.rand_like(logits, dtype=torch.float64)
    gumbel_noise = (- torch.log(noise)) ** temperature
    return logits.exp() / gumbel_noise


def get_num_transfer_tokens(mask_index, steps):
    mask_num = mask_index.sum(dim=1, keepdim=True)
    base = mask_num // steps
    remainder = mask_num % steps
    num_transfer_tokens = torch.zeros(mask_num.size(0), steps, device=mask_index.device, dtype=torch.int64) + base

    for i in range(mask_num.size(0)):
        num_transfer_tokens[i, :remainder[i]] += 1
    return num_transfer_tokens


@ torch.no_grad()
def generate(model, prompt, steps=128, gen_length=128, block_length=64, temperature=0.0, cfg_scale=0., remasking='random', right_shift_logits=False):
    mask_id = tokenizer.mask_token_id
    x = torch.full((1, prompt.shape[1] + gen_length), mask_id, dtype=torch.long).to(model.device)
    x[:, :prompt.shape[1]] = prompt.clone()
    prompt_index = (x != mask_id)

    assert gen_length % block_length == 0
    num_blocks = gen_length // block_length
    assert steps % num_blocks == 0
    steps = steps // num_blocks

    for num_block in range(num_blocks):
        block_mask_index = (x[:, prompt.shape[1] + num_block * block_length: prompt.shape[1] + (num_block + 1) * block_length:] == mask_id)
        num_transfer_tokens = get_num_transfer_tokens(block_mask_index, steps)
        for i in range(steps):
            mask_index = (x == mask_id)
            if cfg_scale > 0.:
                un_x = x.clone()
                un_x[prompt_index] = mask_id
                x_ = torch.cat([x, un_x], dim=0)
                logits = model(x_).logits
                logits, un_logits = torch.chunk(logits, 2, dim=0)
                logits = un_logits + (cfg_scale + 1) * (logits - un_logits)
            else:
                logits = model(x).logits

            if right_shift_logits:
                    logits = torch.cat([logits[:, :1], logits[:, :-1]], dim=1)
            logits_with_noise = add_gumbel_noise(logits, temperature=temperature)
            x0 = torch.argmax(logits_with_noise, dim=-1) # b, l

            if remasking == 'low_confidence':
                p = F.softmax(logits, dim=-1)
                x0_p = torch.squeeze(
                    torch.gather(p, dim=-1, index=torch.unsqueeze(x0, -1)), -1) # b, l
            elif remasking == 'random':
                x0_p = torch.rand((x0.shape[0], x0.shape[1]), device=x0.device)
            else:
                raise NotImplementedError(remasking)

            x0_p[:, prompt.shape[1] + (num_block + 1) * block_length:] = -np.inf

            x0 = torch.where(mask_index, x0, x)
            confidence = torch.where(mask_index, x0_p, -np.inf)

            transfer_index = torch.zeros_like(x0, dtype=torch.bool, device=x0.device)
            for j in range(confidence.shape[0]):
                _, select_index = torch.topk(confidence[j], k=num_transfer_tokens[j, i])
                transfer_index[j, select_index] = True
            x[transfer_index] = x0[transfer_index]

    return x


device = 'cuda'
model = AutoModelForMaskedLM.from_pretrained('OnAnOrange/Qwen3-0.6B-right-shift-tulu-3-smoltalk-opc-sft-stage1_2-epochs-10-bs-2048-len-1024', dtype=torch.bfloat16, trust_remote_code=True).to(device).eval()
tokenizer = AutoTokenizer.from_pretrained('OnAnOrange/Qwen3-0.6B-right-shift-tulu-3-smoltalk-opc-sft-stage1_2-epochs-10-bs-2048-len-1024')

prompt = "Lily can run 12 kilometers per hour for 4 hours. After that, she runs 6 kilometers per hour. How many kilometers can she run in 8 hours?"
m = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": prompt}
]
prompt = tokenizer.apply_chat_template(m, add_generation_prompt=True, tokenize=False)

input_ids = tokenizer(prompt)['input_ids']
input_ids = torch.tensor(input_ids).to(device).unsqueeze(0)

text = generate(model, input_ids, steps=128, gen_length=128, block_length=64, temperature=0.0, cfg_scale=0.0, remasking='random', right_shift_logits=True)
print(tokenizer.batch_decode(text[:, input_ids.shape[1]:], skip_special_tokens=False)[0])