mindw96
/

code-granite-8b-text-to-sql-ver0.1

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

mindw96 commited on Jan 2

Commit

b01f517

·

verified ·

1 Parent(s): db741cc

Update README.md

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -22,9 +22,9 @@ base_model:
 ### Model Description
 <!-- Provide a longer summary of what this model is. -->
-This model is a 4-bit quantized model.
-It has been fine-tuned using QLoRA.
-The train was done on RTX 3090 24GB * 4.
-- **Developed by:** Dongwook Min (mindw96)
-- **Finetuned from model:** ibm-granite/granite-3.1-8b-instruct

 ### Model Description
 <!-- Provide a longer summary of what this model is. -->
+This model is a 4-bit quantized model.
+It has been fine-tuned using QLoRA.
+The train was done on RTX 3090 24GB * 4.
+- **Developed by:** Dongwook Min (mindw96)
+- **Finetuned from model:** ibm-granite/granite-3.1-8b-instruct