adding in header for loading in model, and then the quick start for inference on RDU

README.md

@@ -75,7 +75,7 @@ Users should be made aware of the risks, biases, limitations, and restrictions o
 <details>
 <summary>Click to expand</summary>
 
-Use the code below to get started with the model.
+### Loading in model with Huggingface
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -84,11 +84,11 @@ tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/BLOOMChat-176B-v1")
 model = AutoModelForCausalLM.from_pretrained("sambanovasystems/BLOOMChat-176B-v1", device_map="auto", torch_dtype="auto")
 ```
 
-### Tutorial on using the model for text generation
+### Quick Start Inference on SambaNova's in-house Reconfigurable Dataflow Unit (RDU)
 
-As this model was trained on SambaNova's Reconfigurable Dataflow Unit (RDU) which is not accessible by everyone, we provided a tutorial on how to use this model on GPU.
+The inference code to run the model can be found our [github repo](https://github.com/sambanova/bloomchat/blob/main/rdu_quick_start/inference.py). This code requires the [SambaFlow](https://docs.sambanova.ai/developer/latest/sambaflow-intro.html) SDK to execute. For those interested in running models on RDUs, [please feel free to get in touch](https://sambanova.ai/getstarted).
 
-For those interested in running models on RDUs, [please contact us](https://sambanova.ai/getstarted).
+### Quick Start Inference on GPU
 
 [This tutorial](https://github.com/huggingface/transformers-bloom-inference) from Huggingface will be the base layer for running our model. The tutorial is intended for BLOOM; however, since our model is based off of BLOOM we can repurpose it.