AdaptLLM commited on
Commit
2c183f9
β€’
1 Parent(s): e560845

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ This repo contains the domain-specific base model developed from **LLaMA-1-7B**,
19
 
20
  We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**.
21
 
22
- ### πŸ€— We are currently working hard on developing models across different domains, scales and architectures! Please stay tuned! πŸ€—
23
 
24
  **************************** **Updates** ****************************
25
  * 2024/6/21: πŸ‘πŸ» Released the 2nd version of AdaptLLM at [Instruction-Pretrain](https://huggingface.co/instruction-pretrain) πŸ‘πŸ»
 
19
 
20
  We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**.
21
 
22
+ ### πŸ€— [2024/6/21] We release the 2nd version of AdaptLLM at [Instruction-Pretrain](https://huggingface.co/instruction-pretrain), effective for both general pre-training from scratch and domain-adaptive continual pre-training!!! πŸ€—
23
 
24
  **************************** **Updates** ****************************
25
  * 2024/6/21: πŸ‘πŸ» Released the 2nd version of AdaptLLM at [Instruction-Pretrain](https://huggingface.co/instruction-pretrain) πŸ‘πŸ»