You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
39 lines
1.7 KiB
Markdown
39 lines
1.7 KiB
Markdown
## LLaMA: Open and Efficient Foundation Language Models
|
|
|
|
<Callout emoji="⚠️">
|
|
This section is under heavy development.
|
|
</Callout>
|
|
|
|
|
|
import {Screenshot} from 'components/screenshot'
|
|
import { Callout, FileTree } from 'nextra-theme-docs'
|
|
import LLAMA1 from '../../img/llama-1.png'
|
|
|
|
|
|
## What's new?
|
|
|
|
This paper introduces a collection of foundation language models ranging from 7B to 65B parameters.
|
|
|
|
The models are trained on trillion of tokens with publicly available datasets.
|
|
|
|
The work by [(Hoffman et al. 2022)](https://arxiv.org/abs/2203.15556) shows that given a compute budget smaller models trained on a lot more data can achieve better performance than the larger counterparts. This work recommends training 10B models on 200B tokens. However, the LLaMA paper finds that the performance of a 7B model continues to improve even after 1T tokens.
|
|
|
|
<Screenshot src={LLAMA1} alt="LLAMA1" />
|
|
|
|
This work focuses on training models (LLaMA) that achieve the best possible performance at various inference budgets, by training on more tokens.
|
|
|
|
|
|
## Capabilities & Key Results
|
|
|
|
Overall, LLaMA-13B outperform GPT-3(175B) on many benchmarks despite being 10x smaller and possible to run a single GPU. LLaMA 65B is competitive with models like Chinchilla-70B and PaLM-540B.
|
|
|
|
|
|
*Paper:* [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
|
|
|
|
*Code:* https://github.com/facebookresearch/llama
|
|
|
|
## References
|
|
|
|
- [GPT4All](https://github.com/nomic-ai/gpt4all) (March 2023)
|
|
- [ChatDoctor: A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge](https://arxiv.org/abs/2303.14070) (March 2023)
|
|
- [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) (March 2023) |