Update README.md

Make the model card for descriptions.

README.md

@@ -6,10 +6,30 @@ tags: []
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
-
+This model was a usses LLama3.2-1B-Instruct as a base. It does better **50%** than the same fintuning on ElutherAI/gpt-neo-1.3B on the HellaSwag benchmark for instruction following. 
 
 
 ## Model Details
+# Model Card
+
+## Model Description
+
+This is an ORPO fine-tune of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on a dataset of [mlabonne/orpo-dpo-mix-40k](https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k).
+
+## Evaluation Results
+
+### Hellaswag for this model
+|  Tasks  |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
+|---------|------:|------|-----:|--------|---|-----:|---|-----:|
+|hellaswag|      1|none  |     0|acc     |↑  |0.4501|±  |0.0050|
+|         |       |none  |     0|acc_norm|↑  |0.6072|±  |0.0049|
+ 
+### Hellaswag for same fine-tuning for ElutherAI/gpt-neo-1.3B
+
+|  Tasks  |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
+|---------|------:|------|-----:|--------|---|-----:|---|-----:|
+|hellaswag|      1|none  |     0|acc     |↑  |0.3853|±  |0.0049|
+|         |       |none  |     0|acc_norm|↑  |0.4891|±  |0.0050|
 
 ### Model Description