Update card

README.md

@@ -1,13 +1,12 @@
 ---
 library_name: transformers
-tags: []
+license: mit
+datasets:
+- gsm8k
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
 
 ## Model Details
 
@@ -15,23 +14,22 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+This is the result of 3 iterations of self improvement of the model on a subset of GSM8K problems where the base Phi-2 was less confident. 
+We utilized self consistency evaluation along with execution traces to self-select high quality self-generated samples for training without looking at the ground truth answers.
+This improved the base model Phi-2 accuracy by about 6% on GSM8K dataset - both the test set and the harder to solve subset of the training data.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
+- **Developed by:** Stanford University team: Artyom Shaposhnikov, Roberto Garcia, Shubhra Mishra
 - **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Language(s) (NLP):** Python
+- **License:** MIT
+- **Finetuned from model [optional]:** microsoft/phi-2
 
 ### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** https://github.com/deepbrain/CS224N
+- **Paper [optional]:** "Self-Improvement for Math Problem-Solving in Small Language Models"
 
 ## Uses
 
@@ -196,6 +194,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
-
-
+[More Information Needed]