SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.08072 · 2023

Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 2 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/2307.08072.json · badge: /api/ran/2307.08072.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
rucaibox/quantizedempirical canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rucaibox/quantizedempirical/models/modeling_llama2.py
pointer only (licence: NONE) · get_code("30d7eec482ebf6b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rucaibox/quantizedempirical/models/modeling_llama2.py
pointer only (licence: NONE) · get_code("f725bc2d76076485")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

apply_rotary_pos_emb Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/models/modeling_llama.py
pointer only (licence: NONE); the stored copy get_code serves, from shiqichen17/AdaptVis, is pointer only (licence: NONE) · get_code("373a7df152e5a1a5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

compute_intermediate_size Ran
ran, honoured the contract we drafted
rucaibox/quantizedempirical/convert_llama_weights_to_hf.py
pointer only (licence: NONE) · get_code("507f475feb734647")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

compute_intermediate_size Ran
ran, honoured the contract we drafted
rucaibox/quantizedempirical/models/convert_llama_weights_to_hf.py
pointer only (licence: NONE) · get_code("0c540da8d3df6b6e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

cpu_offload Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/models/bigmodeling.py
pointer only (licence: NONE) · get_code("7c76c83fca14fe69")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

cpu_offload_with_hook Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/models/bigmodeling.py
pointer only (licence: NONE) · get_code("d697b8d42cbb73ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

generate_prompt Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/finetune.py
pointer only (licence: NONE) · get_code("56e674752db00649")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

get_llama Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/models/llama.py
pointer only (licence: NONE); the stored copy get_code serves, from shawnricecake/agile-quant, is pointer only (licence: NONE) · get_code("2c201f017173954b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

init_on_device Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/models/bigmodeling.py
pointer only (licence: NONE) · get_code("77981ab8dcab7d60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

read_json Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/convert_llama_weights_to_hf.py
pointer only (licence: NONE) · get_code("c5bcf01d18bba63d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

rotate_half Ran
ran; our contract draft was wrong, not the code
rucaibox/quantizedempirical/models/modeling_llama.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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.

write_model Not yet run
unverified (harvested, no recorded run)
rucaibox/quantizedempirical/convert_llama_weights_to_hf.py
pointer only (licence: NONE) · get_code("25ab7cdc2eb3c237")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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. No invocation recorded.

write_model Not yet run
unverified (harvested, no recorded run)
rucaibox/quantizedempirical/models/convert_llama_weights_to_hf.py
pointer only (licence: NONE) · get_code("57f5bf024e9e6eb0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical 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. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 11 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 4 the same month, 11 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.

FunctionAlso present inEarliest-datedOthers named
rotate_half 360 other papers
10 dated earlier, 5 the same month, 342 later, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv 243 other papers
3 dated earlier, 2 the same month, 236 later, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
apply_rotary_pos_emb 83 other papers
1 dated earlier, 3 the same month, 79 later · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here
read_json 21 other papers
5 dated earlier, 1 the same month, 15 later
2210.07316 (2022-10)
MTEB: Massive Text Embedding Benchmark
2304.08177 (2023-04)
Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
2304.14454 (2023-04)
PMC-LLaMA: Towards Building Open-source Language Models for Medicine
and 18 more not named here
generate_prompt 15 other papers
1 dated earlier, 14 later
2304.01933 (2023-04)
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
2024.naacl-long.132 (2024 (year only))
LLM-based Medical Assistant Personalization with Short-and Long-Term Memory Coordination
2401.00788 (2024-01)
Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models
and 12 more not named here
compute_intermediate_size 13 other papers
1 dated earlier, 12 later
2305.13718 (2023-05)
Exploring Self-supervised Logic-enhanced Training for Large Language Models
2308.16137 (2023-08)
LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
2401.06706 (2024-01)
Multi-Candidate Speculative Decoding
and 10 more not named here
get_llama 4 other papers
1 dated earlier, 3 later
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
2310.01382 (2023-10)
Compressing LLMs: The Truth is Rarely Pure and Never Simple
2312.05693 (2023-12)
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
and 1 more not named here
apply_rotary_pos_emb 3 other papers
3 later
2310.19785 (2023-10)
What's "up" with vision-language models? Investigating their struggle with spatial reasoning
2404.04722 (2024-04)
PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
2503.01773 (2025-03)
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
compute_intermediate_size 3 other papers
3 later
2402.01618 (2024-02)
Style Vectors for Steering Generative Large Language Models
2402.16061 (2024-02)
How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
2405.19298 (2024-05)
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
write_model 2 other papers
2 later
2308.16137 (2023-08)
LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
2025.findings-emnlp.435 (2025 (year only))
Distributional Surgery for Language Model Activations
init_on_device 1 other paper
1 later
2402.18376 (2024-02)
Tokenization Is More Than Compression

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

Despite the superior performance, Large Language Models~(LLMs) require significant computational resources for deployment and use. To overcome this issue, quantization methods have been widely applied to reduce the memory footprint of LLMs as well as increasing the inference rate. However, a major challenge is that low-bit quantization methods often lead to performance degradation. It is important to understand how quantization impacts the capacity of LLMs. Different from previous studies focused on overall performance, this work aims to investigate the impact of quantization on \emph{emergent abilities}, which are important characteristics that distinguish LLMs from small language models. Specially, we examine the abilities of in-context learning, chain-of-thought reasoning, and instruction-following in quantized LLMs. Our empirical experiments show that these emergent abilities still exist in 4-bit quantization models, while 2-bit models encounter severe performance degradation on the test of these abilities. To improve the performance of low-bit models, we conduct two special experiments: (1) fine-gained impact analysis that studies which components (or substructures) are more sensitive to quantization, and (2) performance compensation through model fine-tuning. Our work derives a series of important findings to understand the impact of quantization on emergent abilities, and sheds lights on the possibilities of extremely low-bit quantization for LLMs.

For agents

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

get_harvested_code_for_paper("2307.08072")
get_code_for_paper("2307.08072")
have("2307.08072")

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

curl https://syntology.ai/api/ran/2307.08072.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.08072.svg)](https://syntology.ai/paper/2307.08072)

Connect an agent — have() is free.