Update README.md

README.md

@@ -1,34 +1,37 @@
 ---
 license: other
 base_model: stabilityai/stable-code-3b
-tags:
-- generated_from_trainer
 model-index:
 - name: stable-code-3b
   results: []
+datasets:
+- fasterinnerlooper/lcc_csharp
+library_name: peft
+language:
+- code
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 
 # stable-code-3b
 
-This model is a fine-tuned version of [stabilityai/stable-code-3b](https://huggingface.co/stabilityai/stable-code-3b) on an unknown dataset.
+This model is a fine-tuned (LoRA) version of [stabilityai/stable-code-3b](https://huggingface.co/stabilityai/stable-code-3b) trained on the Microsoft/lcc_csharp dataset.
 
 ## Model description
 
-More information needed
+Stable Code 3B fine-tuned on microsoft/lcc_csharp modified for in-filling
 
 ## Intended uses & limitations
 
-More information needed
+Meant to be used to in-fill C# code
 
 ## Training and evaluation data
 
-More information needed
+[microsoft/lcc_csharp](https://huggingface.co/microsoft/lcc_csharp) modified for in-filling. The dataset is sliced randomly across the entire dataset. One entry in the original dataset maps to one entry in the modified dataset.
 
 ## Training procedure
 
+Trained in a single GPU environment (either A4000 or P5000) with 16GB of RAM.
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -48,4 +51,4 @@ The following hyperparameters were used during training:
 - Transformers 4.36.2
 - Pytorch 2.1.2+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.1
+- Tokenizers 0.15.1