@librarian-bot\n\t \n","updatedAt":"2024-02-06T18:32:14.227Z","author":{"_id":"62481c93a263b67dc1c52088","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62481c93a263b67dc1c52088/htJfKhx_Wu5ZvB0Bz0ldw.jpeg","fullname":"Raphael Kalandadze","name":"RaphaelKalandadze","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8227800726890564},"editors":["RaphaelKalandadze"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/62481c93a263b67dc1c52088/htJfKhx_Wu5ZvB0Bz0ldw.jpeg"],"reactions":[],"isReport":false}},{"id":"65c349852a023e7ea98edf67","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2024-02-07T09:12:37.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling](https://huggingface.co/papers/2401.16380) (2024)\n* [OMPGPT: A Generative Pre-trained Transformer Model for OpenMP](https://huggingface.co/papers/2401.16445) (2024)\n* [Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4](https://huggingface.co/papers/2312.16171) (2023)\n* [Language Resources for Dutch Large Language Modelling](https://huggingface.co/papers/2312.12852) (2023)\n* [TinyGSM: achieving >80% on GSM8k with small language models](https://huggingface.co/papers/2312.09241) (2023)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\nThe following papers were recommended by the Semantic Scholar API
\n- \n
- Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling (2024) \n
- OMPGPT: A Generative Pre-trained Transformer Model for OpenMP (2024) \n
- Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4 (2023) \n
- Language Resources for Dutch Large Language Modelling (2023) \n
- TinyGSM: achieving >80% on GSM8k with small language models (2023) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Abstract
A new 1.3 billion parameter Transformer-based language model, phi-1.5, demonstrates comparable performance to much larger models on common sense reasoning and complex tasks despite the absence of web data.
AI-generated summary
We continue the investigation into the power of smaller Transformer-based language models as initiated by TinyStories -- a 10 million parameter model that can produce coherent English -- and the follow-up work on phi-1, a 1.3 billion parameter model with Python coding performance close to the state-of-the-art. The latter work proposed to use existing Large Language Models (LLMs) to generate ``textbook quality" data as a way to enhance the learning process compared to traditional web data. We follow the ``Textbooks Are All You Need" approach, focusing this time on common sense reasoning in natural language, and create a new 1.3 billion parameter model named phi-1.5, with performance on natural language tasks comparable to models 5x larger, and surpassing most non-frontier LLMs on more complex reasoning tasks such as grade-school mathematics and basic coding. More generally, phi-1.5 exhibits many of the traits of much larger LLMs, both good -- such as the ability to ``think step by step" or perform some rudimentary in-context learning -- and bad, including hallucinations and the potential for toxic and biased generations -- encouragingly though, we are seeing improvement on that front thanks to the absence of web data. We open-source phi-1.5 to promote further research on these urgent topics.
Community
Whats the size of this model on device?
Any special device requirements?
๐
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling (2024)
- OMPGPT: A Generative Pre-trained Transformer Model for OpenMP (2024)
- Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4 (2023)
- Language Resources for Dutch Large Language Modelling (2023)
- TinyGSM: achieving >80% on GSM8k with small language models (2023)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend