SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04650 · EMNLP · 2021

What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers

Jung-Woo Ha, Sunghyun Park, Jinuk Kim, Minsub Kim, Sungjae Lee, Min Lee, Jinseong Park, Min Kang, Yoo, Sang-Woo Lee, Minsuk Chang, Dongju Park, and 26 more

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2109.04650.json · badge: /api/ran/2109.04650.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
naver-ai/hypermix community
Papers with Code archive
1 ran · 1 no recorded run
kakaobrain/kogpt community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
TMixBertModel Ran
ran on a synthesized input
naver-ai/hypermix/models/tmix.py
code served (permissive licence) · get_code("12e3c05aa5de866a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import transformers
from transformers import BertConfig

# Create a minimal BertConfig
config = BertConfig(
    vocab_size=100,
    hidden_size=4,
    num_hidden_layers=2,
    num_attention_heads=2,
    intermediate_size=8,
    hidden_act="gelu",
    hidden_dropout_prob=0.1,
    attention_probs_dropout_prob=0.1,
    max_position_embeddings=512,
    type_vocab_size=2,
    initializer_range=0.02,
    layer_norm_eps=1e-12,
    output_attentions=True,
    output_hidden_states=True,
)

INIT_ARGS = {
    "config": config,
}

# Create tensors for forward pass
batch_size = 2
seq_length = 3
input_ids = torch.randint(0, 100, (batch_size, seq_length))
mix_idx = torch.tensor([1, 0])
l = torch.tensor([0.5, 0.3])
attention_mask = torch.ones((batch_size, seq_length))
token_type_ids = torch.zeros((batch_size, seq_length), dtype=torch.long)
position_ids = torch.arange(seq_length).unsqueeze(0).expand(batch_size, -1)

# Create head_mask: shape (num_hidden_layers, num_attention_heads)
head_mask = torch.ones((config.num_hidden_layers, config.num_attention_heads))

ARGS = {
    "input_ids": input_ids,
    "mix_idx": mix_idx,
    "l": l,
    "mix_layer": 1,
    "attention_mask": attention_mask,
    "token_type_ids": token_type_ids,
    "position_ids": position_ids,
    "head_mask": head_mask,
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
BertEncoder4Mix Not yet run
unverified (harvested, no recorded run)
naver-ai/hypermix/models/tmix.py
code served (permissive licence) · get_code("4619a31b371ea239")
How it ran

no invocation recorded.

KoGPTInference Not yet run
unverified (harvested, no recorded run)
kakaobrain/kogpt/kogpt/inference.py
pointer only (licence: NOASSERTION) · get_code("d62eabcffff15fb3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, kakaobrain/kogpt (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

GPT-3 shows remarkable in-context learning ability of large-scale language models (LMs) trained on hundreds of billion scale data. Here we address some remaining issues less reported by the GPT-3 paper, such as a non-English LM, the performances of different sized models, and the effect of recently introduced prompt optimization on in-context learning. To achieve this, we introduce Hy-perCLOVA, a Korean variant of 82B GPT-3 trained on a Korean-centric corpus of 560B tokens. Enhanced by our Korean-specific tokenization, HyperCLOVA with our training configuration shows state-of-the-art in-context zero-shot and few-shot learning performances on various downstream tasks in Korean. Also, we show the performance benefits of promptbased learning and demonstrate how it can be integrated into the prompt engineering pipeline. Then we discuss the possibility of materializing the No Code AI paradigm by providing AI prototyping capabilities to nonexperts of ML by introducing HyperCLOVA studio, an interactive prompt engineering interface. Lastly, we demonstrate the potential of our methods with three successful in-house applications.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.04650")
get_code_for_paper("2109.04650")
have("2109.04650")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.04650.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.04650.svg)](https://syntology.ai/paper/2109.04650)

Connect an agent — have() is free.