SeungyounShin/SPIN

Unofficial implementation of Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

7

stars

2

commits

Python

primary language

Jan 17, 2024

updated

README

Unofficial implementation of Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

working in progress

Contributors

2 commits

Similar repos

Pruthwik/finetuning_and_inferencing_using_indictrans2_models

finetuning_and_inferencing_using_indictrans2_models

0

B-Trindade/FineTuned-PaliGemma1

A PaliGemma implementation for improving model performance on lexically similar yet semantically…

0

MTamon/WhisperFinetuning

For Whisper Fine-tuning by Original Data

0

NVIDIA/NeMo-Skills

A project to improve skills of large language models

1,034

s-nlp/skipclm

Official implementation of NAACL 2025 SRW paper "SkipCLM: Enhancing Crosslingual Alignment of…

0

VietHoang1512/PSR

Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection (EMNLP 2025 Findings)

5

muthuka/sample-llm-finetuning

0

hjx620/paddlenlp

0

Languages

Python

100.0%

SeungyounShin/SPIN

Unofficial implementation of Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

7

stars

2

commits

Python

primary language

Jan 17, 2024

updated

README

Unofficial implementation of Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

working in progress

Similar repos

Pruthwik/finetuning_and_inferencing_using_indictrans2_models

finetuning_and_inferencing_using_indictrans2_models

0

B-Trindade/FineTuned-PaliGemma1

A PaliGemma implementation for improving model performance on lexically similar yet semantically…

0

MTamon/WhisperFinetuning

For Whisper Fine-tuning by Original Data

0

NVIDIA/NeMo-Skills

A project to improve skills of large language models

1,034

s-nlp/skipclm

Official implementation of NAACL 2025 SRW paper "SkipCLM: Enhancing Crosslingual Alignment of…

0

VietHoang1512/PSR

Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection (EMNLP 2025 Findings)

5

muthuka/sample-llm-finetuning

0

hjx620/paddlenlp

0

Contributors

2 commits

Languages

Python

100.0%