Update README.md

README.md

@@ -1,13 +1,20 @@
 ---
 library_name: transformers
 tags:
-  - dolly-v2
-  - instruction-tuning
-  - peft
-  - lora
+- dolly-v2
+- instruction-tuning
+- peft
+- lora
+license: apache-2.0
+datasets:
+- MBZUAI/LaMini-instruction
+language:
+- en
+base_model:
+- databricks/dolly-v2-3b
 ---
 
-# Model Card for dolly-3b-lora
+# dolly-3b-lora(Finetuned)
 
 This model is a fine-tuned version of the Dolly V2 3B language model, enhanced with Parameter-Efficient Fine-Tuning (PEFT) using Low-Rank Adaptation (LoRA). It was fine-tuned on the LaMini-instruction dataset to improve its ability to follow instructions and generate coherent responses for various tasks.
 
@@ -18,12 +25,11 @@ This model is a fine-tuned version of the Dolly V2 3B language model, enhanced w
 This is a fine-tuned version of the `databricks/dolly-v2-3b` model, adapted using LoRA on the LaMini-instruction dataset. The model is designed for instruction-following tasks, leveraging the efficiency of LoRA to fine-tune approximately 2.93% of the total parameters while maintaining performance. It supports text generation tasks and has been optimized for use on GPU hardware with 8-bit quantization, with a fallback to CPU if needed.
 
 - **Developed by:** avinashhm
-- **Funded by [optional]:** Not specified
-- **Shared by [optional]:** avinashhm
+- **Shared by :** avinashhm
 - **Model type:** Causal Language Model
 - **Language(s) (NLP):** English
 - **License:** Apache-2.0
-- **Finetuned from model [optional]:** databricks/dolly-v2-3b
+- **Finetuned from model :** databricks/dolly-v2-3b
 
 ### Model Sources