instruction-pretrain
/

InstructLM-1.3B

Text Generation

text-generation-inference

Model card Files Files and versions

instruction-pretrain commited on Jul 15, 2024

Commit

28552d7

·

verified ·

1 Parent(s): 610a4cd

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ We explore supervised multitask pre-training by proposing ***Instruction Pre-Tra
 **************************** **Updates** ****************************
 * 2024/7/15: We scaled up the pre-trained tokens from 100B to 250B, with the number of synthesized instruction-response pairs reaching 500M! Below, we show the performance trend on downstream tasks throughout the pre-training process:
 <p align='center'>
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/66711d2ee12fa6cc5f5dfc89/mURjiDTzX5V9DhNuniQHr.png" width="1100">
 </p>
 * 2024/6/21: Released the [paper](https://huggingface.co/papers/2406.14491), [code](https://github.com/microsoft/LMOps), and [resources](https://huggingface.co/instruction-pretrain)

 **************************** **Updates** ****************************
 * 2024/7/15: We scaled up the pre-trained tokens from 100B to 250B, with the number of synthesized instruction-response pairs reaching 500M! Below, we show the performance trend on downstream tasks throughout the pre-training process:
 <p align='center'>
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/66711d2ee12fa6cc5f5dfc89/0okCfRkC6uALTfuNxt0Fa.png" width="700">
 </p>
 * 2024/6/21: Released the [paper](https://huggingface.co/papers/2406.14491), [code](https://github.com/microsoft/LMOps), and [resources](https://huggingface.co/instruction-pretrain)