SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.03829 · EMNLP Findings · 2020

Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning

Andrea Madotto, Zhaojiang Lin, Pascale Fung

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 3 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-21; 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/2004.03829.json · badge: /api/ran/2004.03829.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
zlinao/VGLM canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
zlinao/VGLM/pytorch_transformers/modeling_bert.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function swish takes a single parameter 'x' which is used with:
# - torch.sigmoid(x) - requires a tensor
# - x * ... - requires a tensor that supports multiplication
# So x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
build_tf_to_pytorch_map Ran
ran; our contract draft was wrong, not the code
zlinao/VGLM/pytorch_transformers/modeling_transfo_xl.py
code served (permissive licence) · get_code("35ef111fc00c21b4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. 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

torch.manual_seed(0)

class Config:
    def __init__(self):
        self.tie_projs = [False]
        self.tie_weight = True
        self.untie_r = False

class LayerNorm(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.weight = nn.Parameter(torch.randn(dim))
        self.bias = nn.Parameter(torch.randn(dim))

class DecAttn(nn.Module):
    def __init__(self, d_model=4, d_head=2):
        super().__init__()
        self.layer_norm = LayerNorm(d_model)
        self.o_net = nn.Linear(d_model, d_model)
        self.qkv_net = nn.Linear(d_model, 3 * d_model)
        self.r_net = nn.Linear(d_model, d_model)
        self.r_r_bias = nn.Parameter(torch.randn(d_model))
        self.r_w_bias = nn.Parameter(torch.randn(d_model))

class PosFeedForward(nn.Module):
    def __init__(self, d_model=4, d_ff=8):
        super().__init__()
        self.layer_norm = LayerNorm(d_model)
        self.CoreNet = nn.Sequential(
            nn.Linear(d_model, d_ff),
            nn.ReLU(),
            nn.Linear(d_ff, d_ff),
            nn.Linear(d_ff, d_model)
        )

class TransformerLayer(nn.Module):
    def __init__(self, d_model=4):
        super().__init__()
        self.dec_attn = DecAttn(d_model)
        self.pos_ff = PosFeedForward(d_model)

class WordEmb(nn.Module):
    def __init__(self, vocab_size=100, d_model=4, n_cutoffs=1):
        super().__init__()
        self.emb_layers = nn.ModuleList([nn.Embedding(vocab_size, d_model) for _ in range(n_cutoffs)])
        self.emb_projs = nn.ModuleList([nn.Linear(d_model, d_model) for _ in range(n_cutoffs)])

class AdaptiveSoftmax(nn.Module):
    def __init__(self, vocab_size=100, d_model=4, n_cutoffs=1):
        super().__init__()
        self.cluster_weight = nn.Parameter(torch.randn(n_cutoffs, d_model))
        self.cluster_bias = nn.Parameter(torch.randn(n_cutoffs))
        self.out_layers = nn.ModuleList([nn.Linear(d_model, vocab_size) for _ in range(n_cutoffs)])
        self.out_projs = nn.ModuleList([nn.Linear(d_model, d_model) for _ in range(n_cutoffs)])

class Transformer(nn.Module):
    def __init__(self, d_model=4, n_layers=2, n_cutoffs=1):
        super().__init__()
        self.word_emb = WordEmb(vocab_size=100, d_model=d_model, n_cutoffs=n_cutoffs)
        self.layers = nn.ModuleList([TransformerLayer(d_model) for _ in range(n_layers)])
        self.r_r_bias = nn.Parameter(torch.randn(d_model))
        self.r_w_bias = nn.Parameter(torch.randn(d_model))

class Model(nn.Module):
    def __init__(self, d_model=4, n_layers=2, n_cutoffs=1):
        super().__init__()
        self.transformer = Transformer(d_model=d_model, n_layers=n_layers, n_cutoffs=n_cutoffs)
        self.crit = AdaptiveSoftmax(vocab_size=100, d_model=d_model, n_cutoffs=n_cutoffs)

config = Config()
model = Model(d_model=4, n_layers=2, n_cutoffs=1)

ARGS = {
    'model': model,
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
gelu Ran
ran; our contract draft was wrong, not the code
zlinao/VGLM/pytorch_transformers/modeling_gpt2.py
code served (permissive licence) · get_code("8d23fbe2b99b840b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 math

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
gelu Ran
ran, honoured the contract we drafted
zlinao/VGLM/pytorch_transformers/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from tanmay1618/text_to_sql_bert, is pointer only (licence: NONE) · get_code("fdc64f4c72036ae4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tanmay1618/text_to_sql_bert, and GitHub detected no licence in that repository when it was checked. 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. A run is recorded.

gelu Ran
ran; our contract draft was wrong, not the code
zlinao/VGLM/pytorch_transformers/modeling_distilbert.py
code served (permissive licence) · get_code("69c6d14de8190cfb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 math
import torch

torch.manual_seed(0)

# The function gelu takes a single parameter x which is used with:
# - multiplication operator (*)
# - torch.erf() function
# - division operator (/)
# This suggests x should be a torch.Tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
load_tf_weights_in_bert Ran
ran; our contract draft was wrong, not the code
zlinao/VGLM/pytorch_transformers/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from tanmay1618/text_to_sql_bert, is pointer only (licence: NONE) · get_code("0c145728a35789fa")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tanmay1618/text_to_sql_bert, and GitHub detected no licence in that repository when it was checked. 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. A run is recorded.

sample_logits Ran
ran; our contract draft was wrong, not the code
zlinao/VGLM/pytorch_transformers/modeling_transfo_xl_utilities.py
code served (permissive licence) · get_code("93228a3eb5c4d179")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Small embedding layer
n_vocab = 20
n_emb = 4
embedding = nn.Embedding(n_vocab, n_emb)

# Bias vector
bias = torch.randn(n_vocab)

# Labels: [b1, b2] with valid vocab indices
b1, b2 = 2, 3
labels = torch.randint(0, n_vocab, (b1, b2))

# Inputs: [b1, b2, n_emb]
inputs = torch.randn(b1, b2, n_emb)

# Sampler that implements the sample() method
class LogUniformSampler:
    def __init__(self, n_vocab, n_sample=5):
        self.n_vocab = n_vocab
        self.n_sample = n_sample
    
    def sample(self, labels):
        # Sample negative samples
        neg_samples = torch.randint(0, self.n_vocab, (self.n_sample,))
        
        # Log probabilities
        true_log_probs = torch.randn(labels.size(0), labels.size(1))
        samp_log_probs = torch.randn(self.n_sample)
        
        return true_log_probs, samp_log_probs, neg_samples

sampler = LogUniformSampler(n_vocab=n_vocab, n_sample=5)

ARGS = {
    "embedding": embedding,
    "bias": bias,
    "labels": labels,
    "inputs": inputs,
    "sampler": sampler
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 6) — shape (2, 3, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
top_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zlinao/VGLM/evaluate.py
code served (permissive licence) · get_code("695eaa24be6f2a1d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 1, dtype family float, shape (10,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.functional as F

torch.manual_seed(0)

# Create a small logits tensor (vocabulary size of 10)
logits = torch.randn(10)

# Define arguments for the top_filtering function
ARGS = {
    'logits': logits,
    'top_k': 5,
    'top_p': 0.9,
    'threshold': -2.0,
    'filter_value': -float('Inf')
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (10,) — shape (10,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
zlinao/VGLM/pytorch_transformers/modeling_gpt2.py
code served (permissive licence) · get_code("654e91efc679fe84")
How it ran

no invocation recorded.

load_tf_weights_in_openai_gpt Not yet run
unverified (harvested, no recorded run)
zlinao/VGLM/pytorch_transformers/modeling_openai.py
code served (permissive licence) · get_code("42ee168c3ae12e60")
How it ran

no invocation recorded.

load_tf_weights_in_transfo_xl Not yet run
unverified (harvested, no recorded run)
zlinao/VGLM/pytorch_transformers/modeling_transfo_xl.py
code served (permissive licence) · get_code("23d246e59ef9447b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 5 the same month, 11 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
swish 206 other papers
28 dated earlier, 6 the same month, 171 later, 1 same year, order not determinable · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
gelu 198 other papers
38 dated earlier, 8 the same month, 150 later, 2 same year, order not determinable · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
gelu 51 other papers
13 dated earlier, 2 the same month, 36 later · 8 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
and 48 more not named here
load_tf_weights_in_bert 19 other papers
5 dated earlier, 1 the same month, 13 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1902.01069 (2019-02)
A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
and 16 more not named here
gelu 17 other papers
5 dated earlier, 12 later
1905.12790 (2019-05)
A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1909.05311 (2019-09)
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
and 14 more not named here
sample_logits 14 other papers
6 dated earlier, 1 the same month, 7 later · 2 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
and 11 more not named here
build_tf_to_pytorch_map 10 other papers
6 dated earlier, 4 later
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
and 7 more not named here
load_tf_weights_in_openai_gpt 8 other papers
3 dated earlier, 5 later
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1909.05311 (2019-09)
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
2002.01808 (2020-02)
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
and 5 more not named here
top_filtering 7 other papers
5 dated earlier, 2 later
1901.08149 (2019-01)
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
1904.09751 (2019-04)
THE CURIOUS CASE OF NEURAL TEXT DeGENERATION
1911.00536 (2019-11)
DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
and 4 more not named here
load_tf_weights_in_gpt2 6 other papers
1 dated earlier, 5 later
2002.01808 (2020-02)
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
2010.05607 (2020-10)
The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?
2201.06885 (2022-01)
Evidence-aware Fake News Detection with Graph Neural Networks
and 3 more not named here
load_tf_weights_in_transfo_xl 6 other papers
3 dated earlier, 3 later
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1909.05311 (2019-09)
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
2002.01808 (2020-02)
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
and 3 more not named here

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power scenarios (e.g., mobile). In this paper, we propose an effective way to fine-tune multiple down-stream generation tasks simultaneously using a single, large pretrained model. The experiments on five diverse language generation tasks show that by just using an additional 2-3% parameters for each task, our model can maintain or even improve the performance of fine-tuning the whole model 1 . * * Equal contributions. 1 Code available in https://github.com/zlinao/ VGLM

For agents

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

get_harvested_code_for_paper("2004.03829")
get_code_for_paper("2004.03829")
have("2004.03829")

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

curl https://syntology.ai/api/ran/2004.03829.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.03829.svg)](https://syntology.ai/paper/2004.03829)

Connect an agent — have() is free.