updated readme

README.md

@@ -28,17 +28,25 @@ Evaluating how well the Fine tuned model works as a psychology assistant
 evaluating simply on different fine-tuned models how the same phrase performs on different fine-tuned models
 
 Models:
+
 oskaralf/tiny_merged
+
 TinyLlama (4bit)
     - Fine-tuned on FineTome-100k
+
 Llama3.2_1B_4bit
+
 Llama 3.2-1B-Instruct (4bit)
+
     - Fine-tuned on FineTome-100k
+
 Llama1B_psych_v2_merged
+
     - Llama 3.2-1B-Instruct (4bit)
     - Fine-tuned on samhog/psychology10K
     - Lora r=8
 Llama1B_psych_v3_merged
+
     - Llama 3.2-1B-Instruct (4bit)
     - Fine-tuned on samhog/psychology10K
     - Lora r=16
@@ -47,14 +55,26 @@ Llama1B_psych_v3_merged
     - 4 epochs
 
 To improve:
+
 Model centric approach
+
 change r=16 to higher dimension, for more complex LORA matrices, capturing more complex patterns
+
 Using bigger model
+
 Training more epochs
+
 limited due to RAM and time constraint
+
 Change learning rate
 
 
+
+
+
+
+
+
 Comparison between different responses on a question:
 
 “I have anxiety, what can I do?”