Update README.md

README.md

@@ -16,7 +16,7 @@ model = LLaMAForCausalLM.from_pretrained(
     "decapoda-research/llama-7b-hf",
     load_in_8bit=True,
     device_map="auto",
-)
+)\
 model = PeftModel.from_pretrained(model, "patulya/alpaca7B-lora")
 
 PROMPT = """Below is an instruction that describes a task. Write a response that appropriately completes the request.
@@ -31,21 +31,20 @@ inputs = tokenizer(
 
 input_ids = inputs["input_ids"].cuda()
 
-generation_config = GenerationConfig(
-    temperature=0.6,
-    top_p=0.95,
-    repetition_penalty=1.15,
+generation_config = GenerationConfig(\
+    temperature=0.6,\
+    top_p=0.95,\
+    repetition_penalty=1.15,\
 )
 
 print("Generating...")
 
-generation_output = model.generate(
-    input_ids=input_ids,
-    generation_config=generation_config,
-    return_dict_in_generate=True,
-    output_scores=True,
-    max_new_tokens=128,
+generation_output = model.generate(\
+    input_ids=input_ids,\
+    generation_config=generation_config,\
+    return_dict_in_generate=True,\
+    output_scores=True,\
+    max_new_tokens=128,\
 )
 
-for s in generation_output.sequences:
-    print(tokenizer.decode(s))
+for s in generation_output.sequences: print(tokenizer.decode(s))