Update README.md (#2)

- Update README.md (44279721e2370a594bfb4ec576baef6d95dfdc82)


Co-authored-by: Igor Vasiljevic <ivas-tri@users.noreply.huggingface.co>

README.md

@@ -75,8 +75,7 @@ model-index:
 ---
 
 # Mamba-7B
-(insert cool midjourney pic here?)<br>
-This is a 7B parameter model with the [Mamba](https://arxiv.org/abs/2312.00752) architecture, trained on 1.2T tokens of the [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) dataset.
+This is a 7B parameter model with the [Mamba](https://arxiv.org/abs/2312.00752) architecture, trained on multiple epochs (1.2T tokens) of the [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) dataset.
 Mamba is a state-space model that does not use self-attention unlike the standard transformer architecture. It has shown strong performance on various natural language benchmarks. To date, the largest publicly released pure-Mamba pretrain is [Mamba-2.8B](https://huggingface.co/state-spaces/mamba-2.8b). 
 We follow their training recipe and release our version of Mamba-7B.