Add some snippets to the README

README.md

@@ -32,6 +32,26 @@ and conversations with synthetically generated instructions attached.
 
 This model is freely available for both commercial and non-commercial use, as per the Llama-2 license.
 
+## Model Initialisation
+
+One way to get started with the model is using HuggingFace's [transformers](https://huggingface.co/docs/transformers/index) library:
+
+```python
+import torch
+from transformers import AutoTokenizer, pipeline
+
+# App config
+modelName = "PygmalionAI/pygmalion-2-7b"
+
+# Model Initialisation
+tokenizer = AutoTokenizer.from_pretrained(modelName)
+pipeline = pipeline(
+    "text-generation",
+    model=modelName,
+    torch_dtype=torch.float16,
+	device="cuda", # cuda on a compatible Nvidia GPU is recommended for running this model
+)
+```
 
 ## Prompting
 
@@ -52,6 +72,19 @@ The system prompt has been designed to allow the model to "enter" various modes
 You shall reply to the user while staying in character, and generate long responses.
 ```
 
+Using the pipeline snippet above:
+
+```python
+conversation_with_response = pipeline(
+  "Hi, can you tell me how cool Pygmalion models are?", # Use the tokens described above when prompting
+  do_sample=True,
+  top_k=10,
+  num_return_sequences=1,
+  eos_token_id=tokenizer.eos_token_id,
+  max_new_tokens=128 
+)
+```
+
 ## Dataset
 The dataset used to fine-tune this model includes our own [PIPPA](https://huggingface.co/datasets/PygmalionAI/PIPPA), along with several other instruction
 datasets, and datasets acquired from various RP forums.