Update README.md

README.md

@@ -19,21 +19,20 @@ model-index:
         num_few_shot: 25
     metrics:
     - type: acc
-      value: 46.08
+      value: 43.85
       name: accuracy
   - task:
       type: text-generation
       name: Text Generation
     dataset:
-      name: MMLU TR v0.2
-      type: cais/mmlu
-      config: all
-      split: test
+      name: HellaSwag TR
+      type: hellaswag
+      split: validation
       args:
-        num_few_shot: 5
+        num_few_shot: 10
     metrics:
     - type: acc
-      value: 47.02
+      value: 46.64
       name: accuracy
   - task:
       type: text-generation
@@ -48,7 +47,7 @@ model-index:
     metrics:
     - type: acc
       name: accuracy
-      value: 49.38
+      value: 48.66
   - task:
       type: text-generation
       name: Text Generation
@@ -61,7 +60,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 53.71
+      value: 52.84
       name: accuracy
   - task:
       type: text-generation
@@ -75,7 +74,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 53.08
+      value: 59.30
       name: accuracy
 pipeline_tag: text-generation
 ---
@@ -89,17 +88,15 @@ pipeline_tag: text-generation
     <aside>by <a href="https://curiosity.tech">Curiosity Technology</a></aside>
 </div>
 
-MARS is the first iteration of Curiosity Technology models, based on Llama 3 8B.
+MARS-v0.2 is the second iteration of Curiosity Technology models, built on the foundation of Llama 3.1 8B. This version expands upon the initial MARS model by fine-tuning it with a more comprehensive dataset, with an increased emphasis on mathematical data to enhance its reasoning and problem-solving capabilities.
 
-We have trained MARS on in-house Turkish dataset, as well as several open-source datasets and their Turkish
-translations.
-It is our intention to release Turkish translations in near future for community to have their go on them.
+We've continued our commitment to Turkish language processing, utilizing both in-house Turkish datasets and a broader selection of translated open-source datasets. We believe this version will serve the community with even more versatility and depth.
 
 MARS have been trained for 3 days on 4xA100.
 
 ## Model Details
 
-- **Base Model**: Meta Llama 3 8B Instruct
+- **Base Model**: Meta Llama 3.1 8B Instruct
 - **Training Dataset**: In-house & Translated Open Source Turkish Datasets
 - **Training Method**: LoRA Fine Tuning