Update README.md

README.md

@@ -78,16 +78,47 @@ The model is intended for categorizing the arc of conversation texts. It can be
 
 To use this model for inference, you need to load the fine-tuned model and tokenizer. Here is an example of how to do this using the `transformers` library:
 
+Running on CPU
 ```python
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+
+tokenizer = T5Tokenizer.from_pretrained('Falconsai/arc_of_conversation')
+model = T5ForConditionalGeneration.from_pretrained('Falconsai/arc_of_conversation')
+
+input_text = "Your conversation Here"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids
+
+outputs = model.generate(input_ids)
+print(tokenizer.decode(outputs[0]))
+```
+
+Running on GPU
+```python
+# pip install accelerate
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+
+tokenizer = T5Tokenizer.from_pretrained('Falconsai/arc_of_conversation')
+model = T5ForConditionalGeneration.from_pretrained('Falconsai/arc_of_conversation', device_map="auto")
+
+input_text = "Your conversation Here"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
+
+outputs = model.generate(input_ids)
+print(tokenizer.decode(outputs[0]))
+
+```
+
+
+Running Pipeline
+```python
+# Use a pipeline as a high-level helper
 from transformers import pipeline
 
-# Generate the Arc of the conversation
-convo2 = """ Your conversation text Here"""
+pipe = pipeline("summarization", model="Falconsai/arc_of_conversation")
 
-summarizer = pipeline("summarization", model='Falconsai/arc_of_conversation', tokenizer='Falconsai/arc_of_conversation')
-result = summarizer(convo2, max_length=2048, min_length=1024, do_sample=False)
 ```
 
+
 ## Training
 
 The training process involves the following steps:
@@ -125,7 +156,7 @@ If you use this model in your research, please cite it as follows:
 ```
 @misc{conversation_arc_predictor,
   author = {Michael Stattelman},
-  title = {Conversation Arc Predictor},
+  title = {Arc of the Conversation Generator},
   year = {2024},
   publisher = {Falcons.ai},
 }