Update README.md

README.md

@@ -22,8 +22,14 @@ This model converts legalese into short, human-readable summaries, based on data
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("FlamingNeuron/llama381binstruct_summarize_short_merged", device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained("FlamingNeuron/llama381binstruct_summarize_short_merged")
+model = AutoModelForCausalLM.from_pretrained(
+    "FlamingNeuron/llama381binstruct_summarize_short_merged",
+    device_map="auto"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(
+    "FlamingNeuron/llama381binstruct_summarize_short_merged"
+)
 
 prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
 
@@ -31,8 +37,13 @@ Please convert the following legal content into a short human-readable summary<|
 
 [LEGAL_DOC]by using our services you agree to these terms...[END_LEGAL_DOC]<|eot_id|><|start_header_id|>assistant<|end_header_id|>"""
 
+# Tokenize and move to GPU
 inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+
+# Generate model response
 outputs = model.generate(**inputs, max_new_tokens=128)
+
+# Decode and print result
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ```