LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911765720203264 |
|---|---|
| author | Wu, Minghao Waheed, Abdul Zhang, Chiyu Abdul-Mageed, Muhammad Aji, Alham Fikri |
| author_facet | Wu, Minghao Waheed, Abdul Zhang, Chiyu Abdul-Mageed, Muhammad Aji, Alham Fikri |
| contents | Large language models (LLMs) with instruction fine-tuning demonstrate superior generative capabilities. However, these models are resource-intensive. To alleviate this issue, we explore distilling knowledge from instruction-tuned LLMs into much smaller ones. To this end, we carefully develop a large set of 2.58M instructions based on both existing and newly-generated instructions. In addition to being sizable, we design our instructions to cover a broad set of topics to ensure diversity. Extensive analysis of our instruction dataset confirms its diversity, and we generate responses for these instructions using gpt-3.5-turbo. Leveraging these instructions, we fine-tune a diverse herd of models, collectively referred to as LaMini-LM, which includes models from both the encoder-decoder and decoder-only families, with varying sizes. We evaluate the performance of our models using automatic metrics on 15 different natural language processing (NLP) benchmarks, as well as through human assessment. The results demonstrate that our proposed LaMini-LM models are comparable to competitive baselines, while being much smaller in size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_14402 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions Wu, Minghao Waheed, Abdul Zhang, Chiyu Abdul-Mageed, Muhammad Aji, Alham Fikri Computation and Language Large language models (LLMs) with instruction fine-tuning demonstrate superior generative capabilities. However, these models are resource-intensive. To alleviate this issue, we explore distilling knowledge from instruction-tuned LLMs into much smaller ones. To this end, we carefully develop a large set of 2.58M instructions based on both existing and newly-generated instructions. In addition to being sizable, we design our instructions to cover a broad set of topics to ensure diversity. Extensive analysis of our instruction dataset confirms its diversity, and we generate responses for these instructions using gpt-3.5-turbo. Leveraging these instructions, we fine-tune a diverse herd of models, collectively referred to as LaMini-LM, which includes models from both the encoder-decoder and decoder-only families, with varying sizes. We evaluate the performance of our models using automatic metrics on 15 different natural language processing (NLP) benchmarks, as well as through human assessment. The results demonstrate that our proposed LaMini-LM models are comparable to competitive baselines, while being much smaller in size. |
| title | LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2304.14402 |