본문 바로가기

Llama2

(5)
[Kosy🍵llama] - Noisy embedding 방식을 활용한 llama2 fine-tuning Github: https://github.com/Marker-Inc-Korea/KoNEFTune GitHub - Marker-Inc-Korea/KoNEFTune: Random Noisy Embeddings with fine-tuning 방법론을 한국어 LLM에 간단히 적용할 Random Noisy Embeddings with fine-tuning 방법론을 한국어 LLM에 간단히 적용할 수 있는 Kosy🍵llama - GitHub - Marker-Inc-Korea/KoNEFTune: Random Noisy Embeddings with fine-tuning 방법론을 한국어 LLM에 간단히 적용할 수 있는 github.com Huggingface: https://huggingface.co/kyujinpy/Ko..
[🐳KO-LLM 첫 50 돌파🥮] 안녕하세요! 최근 Ko-platypus와 Ko-openorca로 인사드렸던 kyujin 입니다😊 KoR-Orca-Platypus-13B 모델이 Open KO-LLM 리더보드에서 처음으로 average 점수 50을 돌파하였습니다🎉🎉 Ko-platypus와 Korean-OpenOrca를 훈련시키고 리더보드에 올리면서 많은 걸 느끼고 경험할 수 있었던 것 같습니다 ㅎㅎ 해당 모델에 관심 있으신 분들은 밑에 github 링크를 통해서 상세한 정보를 확인하실 수 있습니다! 감사합니다🤗🤗 Ko-platypus: https://github.com/Marker-Inc-Korea/KO-Platypus Ko-OpenOrca: https://github.com/Marker-Inc-Korea/Korean-OpenOrca
[🐳Korean-OpenOrca Model 등장🐳] 🐳Github🐳: https://github.com/Marker-Inc-Korea/Korean-OpenOrca GitHub - Marker-Inc-Korea/Korean-OpenOrca: OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca - GitHub - Marker-Inc-Korea/Korean-OpenOrca: OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca github.com 🐳HuggingFace🐳: https://huggingface.co/kyujinpy/K..
[KoT-platypus2] - CoT + KO-platypus2 HuggingFace: https://huggingface.co/kyujinpy/KoT-platypus2-7B kyujinpy/KoT-platypus2-7B · Hugging Face KoT-platypus2 CoT + KO-platypus2 = KoT-platypus2 Model Details Model Developers Kyujin Han (kyujinpy) Input Models input text only. Output Models generate text only. Model Architecture KoT-platypus2-7B is an auto-regressive language model based on the LLaM huggingface.co Github: https://github...
[CoT-llama2] - Chain-of-thought 방식을 활용하여 llama2-ko를 fine-tuning HuggingFace: https://huggingface.co/kyujinpy/CoT-llama-2k-7b kyujinpy/CoT-llama-2k-7b · Hugging Face CoT-llama2-7B More detail repo(Github): CoT-llama2 Model Details Model Developers Kyujin Han (kyujinpy) Input Models input text only. Output Models generate text only. Model Architecture CoT-llama2 is an auto-regressive language model based on the LLaMA2 t huggingface.co Dataset: https://huggingf..

반응형