Update README.md

README.md

@@ -9,7 +9,8 @@ tags:
 - presentation-templates
 - information-retrieval
 - gemma
-base_model: unsloth/gemma-3-4b-it
+base_model:
+- unsloth/gemma-3-4b-it-unsloth-bnb-4bit
 datasets:
 - cyberagent/crello
 language:
@@ -21,7 +22,7 @@ language:
 ## Model Details
 
 ### Model Description
-A fine-tuned text generation model for query generation from presentation template metadata. This model uses LoRA adapters to efficiently fine-tune Google Gemma-3-4B-IT for generating diverse and relevant search queries as part of the Field-Adaptive Dense Retrieval framework.
+A fine-tuned text generation model for query generation from presentation template metadata. This model uses LoRA adapters to efficiently fine-tune Google Gemma-3-4B for generating diverse and relevant search queries as part of the Field-Adaptive Dense Retrieval framework.
 
 **Developed by:** Mudasir Syed (mudasir13cs)
 
@@ -31,14 +32,14 @@ A fine-tuned text generation model for query generation from presentation templa
 
 **License:** Apache 2.0
 
-**Finetuned from model:** unsloth/gemma-3-4b-it
+**Finetuned from model:** unsloth/gemma-3-4b-it-unsloth-bnb-4bit
 
 **Paper:** [Field-Adaptive Dense Retrieval of Structured Documents](https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE12352544)
 
 ### Model Sources
 - **Repository:** https://github.com/mudasir13cs/hybrid-search
 - **Paper:** https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE12352544
-- **Base Model:** https://huggingface.co/unsloth/gemma-3-4b-it
+- **Base Model:** https://huggingface.co/unsloth/gemma-3-4b-it-unsloth-bnb-4bit
 
 ## Uses
 
@@ -93,8 +94,8 @@ print(generated_text)
 - **Domain:** Presentation templates with field-adaptive metadata
 
 ### Training Procedure
-- **Architecture:** Google Gemma-3-4B-IT with LoRA adapters
-- **Base Model:** unsloth/gemma-3-4b-it
+- **Architecture:** Google Gemma-3-4B with LoRA adapters
+- **Base Model:** unsloth/gemma-3-4b-it-unsloth-bnb-4bit
 - **Loss Function:** Cross-entropy loss
 - **Optimizer:** AdamW
 - **Learning Rate:** 2e-4
@@ -137,7 +138,7 @@ print(generated_text)
 ## Technical Specifications
 
 ### Model Architecture and Objective
-- **Base Architecture:** Google Gemma-3-4B-IT transformer decoder
+- **Base Architecture:** Google Gemma-3-4B transformer decoder
 - **Adaptation:** LoRA adapters for parameter-efficient fine-tuning
 - **Objective:** Generate relevant search queries from template metadata for field-adaptive dense retrieval
 - **Input:** Template metadata (title, description, industries, categories, tags)