Update README.md

README.md

@@ -8,7 +8,7 @@ base_model: google/flan-t5-small
 base_model_relation: adapter
 
 library_name: peft
-pipeline_tag: text2text-generation
+pipeline_tag: text-generation
 
 datasets:
 - syed7741/aegis-industrial-ai-dataset
@@ -52,9 +52,7 @@ The project is part of **AEGIS AI**, an end-to-end industrial artificial intelli
 
 # Model Status
 
-✅ **This repository now contains a genuinely trained LoRA adapter.**
-
-It is no longer only a documentation repository.
+✅ **This repository contains a genuinely trained LoRA adapter.**
 
 The trained adapter weights are stored in:
 
@@ -154,8 +152,6 @@ Final evaluation examples:
 
 The model was trained using **LoRA — Low-Rank Adaptation** through Hugging Face PEFT.
 
-Configuration:
-
 | Parameter | Value |
 |---|---:|
 | Base model | google/flan-t5-small |
@@ -213,7 +209,7 @@ Training Loss:   1.1880
 Evaluation Loss: 0.7744
 ```
 
-Both the training and evaluation loss decreased during the two training epochs.
+Both training and evaluation loss decreased during the two training epochs.
 
 ---
 
@@ -243,7 +239,7 @@ Install the required libraries:
 pip install transformers peft torch sentencepiece
 ```
 
-Then load the AEGIS adapter:
+Load the AEGIS adapter:
 
 ```python
 from transformers import (
@@ -267,6 +263,7 @@ config = PeftConfig.from_pretrained(
     ADAPTER_ID
 )
 
+
 base_model = (
     AutoModelForSeq2SeqLM
     .from_pretrained(
@@ -274,6 +271,7 @@ base_model = (
     )
 )
 
+
 tokenizer = (
     AutoTokenizer
     .from_pretrained(
@@ -281,16 +279,16 @@ tokenizer = (
     )
 )
 
+
 model = PeftModel.from_pretrained(
     base_model,
     ADAPTER_ID,
 )
 
+
 model.eval()
 ```
 
-PEFT adapters are loaded together with their original base model.
-
 ---
 
 # Example Inference
@@ -387,7 +385,7 @@ The embedding model performs semantic retrieval over the industrial knowledge ba
 
 # Technology Stack
 
-### AI / Machine Learning
+## AI / Machine Learning
 
 - Hugging Face
 - Transformers
@@ -399,20 +397,20 @@ The embedding model performs semantic retrieval over the industrial knowledge ba
 - Semantic Search
 - Vector Embeddings
 
-### Backend
+## Backend
 
 - Python
 - FastAPI
 - REST APIs
 - PostgreSQL
 
-### Frontend
+## Frontend
 
 - React
 - TypeScript
 - Material UI
 
-### AI Platform Components
+## AI Platform Components
 
 - RAG
 - AI Agents
@@ -450,7 +448,7 @@ Implemented:
 
 # Development Roadmap
 
-Planned improvements include:
+Planned improvements:
 
 - Larger industrial training dataset
 - Arabic + English training data
@@ -475,7 +473,7 @@ AEGIS demonstrates concepts applicable to enterprise AI systems including:
 
 - LLM application development
 - Parameter-efficient fine-tuning
-- RAG
+- Retrieval-Augmented Generation
 - Document intelligence
 - Semantic search
 - Conversational AI
@@ -489,7 +487,7 @@ AEGIS demonstrates concepts applicable to enterprise AI systems including:
 
 # Safety Notice
 
-The AEGIS training dataset currently contains **synthetic industrial records** created for:
+The AEGIS training dataset contains **synthetic industrial records** created for:
 
 - AI engineering experimentation
 - learning