Modify readme

README.md

@@ -19,6 +19,11 @@ inference: false
 
 # MPT-7B-Instruct-8k
 
+MPT-7B-Instruct-8K but with gradient checkpointing making it easy to train with LoRA/QLoRA. Not tested yet
+
+
+Original card below:
+
 MPT-7B-Instruct-8k is a model for long-form instruction following, especially question-answering on and summarization of longer documents.
 It is built by finetuning [MPT-7B-8k](https://huggingface.co/mosaicml/mpt-7b-8k) on [Dolly HHRLHF](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. It is also trained on [Competition Math](https://huggingface.co/datasets/competition_math), [Duorc](https://huggingface.co/datasets/duorc), [CoT GSM8k](https://huggingface.co/datasets/conceptofmind/cot_submix_original), [Qasper](https://huggingface.co/datasets/allenai/qasper), [Quality](https://huggingface.co/datasets/emozilla/quality), [Summ Screen FD](https://huggingface.co/datasets/tau/scrolls) and [Spider](https://huggingface.co/datasets/spider).
 This is the same dataset that [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct) was trained on.
@@ -195,4 +200,4 @@ for open-source foundation models},
     note      = {Accessed: 2023-06-22},
     urldate   = {2023-06-22}
 }
-```
+```