Update README.md

README.md

@@ -1,12 +1,16 @@
-# alpaca_orca_open_llama: A Instruction-Following OpeLLaMA Model using Orca approaches on Alpaca dataset
+# alpaca_orca_open_llama: An Open_LLaMA-3B model trained on Alpaca dataset using Orca Research paper approaches
 
 
 # Dataset and Training
 
 We train OpenLLaMa-3B model on the custom Alpaca dataset created using Orca Research Paper approaches. 
+
 Please pay attention how System prompt is added and used for each instruction.
+
 The training configurations are provided in the table below.
+
 The training takes on 4 x A600(50G) GPUs and lasts for around 20 Hours for cost of $66.
+
 We used DeepSpeed with Zero-3 approaches for parallel gpu training.
 
 |||
@@ -62,4 +66,5 @@ with torch.no_grad():
         
 output = rest[0][length:]
 string = tokenizer.decode(output, skip_special_tokens=True)
-print(f'[!] Generation results: {string}')
+print(f'[!] Generation results: {string}')
+```