Update README.md

README.md

@@ -9,4 +9,21 @@ widget:
 # ISHA Call Center QA Model
 
 ## This model was trained on a finetuned version(StableBeluga2) of Llama2-13B from stabilityai : [(StableBeluga2 tops the LLM leaderboard currently)](https://huggingface.co/stabilityai/StableBeluga2)
-### Dataset Used : https://huggingface.co/datasets/nateshmbhat/isha-qa-text
+### Dataset Used : https://huggingface.co/datasets/nateshmbhat/isha-qa-text
+
+
+
+#### Train Params used :
+- Base model : stabilityai/StableBeluga-13B
+- Quantization Used : 4 bit
+- Learning rate : 2e-4
+- Batch Size : 2
+- Epochs : 3
+- Trainer : sft
+- Max token length : 2048 (capable of higher token length)
+
+
+#### Full command :
+```
+!autotrain llm --train --project_name project-isha-qa --model stabilityai/StableBeluga-13B --data_path nateshmbhat/isha-qa-text --use_peft --use_int4 --learning_rate 2e-4 --train_batch_size 2 --num_train_epochs 3 --trainer sft --model_max_length 2048 --push_to_hub --repo_id nateshmbhat/model-isha-qa
+```