Update README.md

README.md

@@ -14,12 +14,12 @@ Finetune base model [TinyLlama-1.1B](https://huggingface.co/TinyLlama/TinyLlama-
 ## Model Details
 
 Here are the traning parameters
-- base_model 'TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T'
-- yahma/alpaca-cleaned
-- lora_r 16
-- lora_alpha 16
-- lora_dropout 0.05
-- lora_target_modules '[q_proj, k_proj, v_proj, o_proj]'
+- base_model ='TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T'
+- dataset = yahma/alpaca-cleaned
+- lora_r = 16
+- lora_alpha = 16
+- lora_dropout = 0.05
+- lora_target_modules = '[q_proj, k_proj, v_proj, o_proj]'
 
 
 Took 6-7 hours on a single A5000 GPU (lots of issues arise when trying to use multiple GPUs).