Cleaned up model description (removed Lankabizz and hardware specs)

README.md

@@ -31,7 +31,6 @@ Chat2Find-CPT is a specialized version of the Qwen 3.5 4B model, enhanced via **
 ## Technical Specifications
 
 ### Training Hardware
-- **GPU:** NVIDIA GeForce RTX 3060 (12GB VRAM)
 - **Frameworks:** Unsloth, Hugging Face Transformers, PEFT
 
 ### Training Hyperparameters
@@ -45,7 +44,6 @@ Chat2Find-CPT is a specialized version of the Qwen 3.5 4B model, enhanced via **
 ### Dataset
 The model was trained on a curated corpus of ~270,000 sequences focusing on:
 - **Sri Lankan News & Media:** Current events and reporting styles.
-- **Business & Logistics:** Domain-specific data from Lankabizz and local commerce.
 - **Cultural Context:** General web-scraped data reflecting local nuances.
 
 ## Capabilities
@@ -64,7 +62,7 @@ from unsloth import FastLanguageModel
 import torch
 
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "SENTIENT_ID/Chat2Find-CPT",
+    model_name = "Chat2Find/Chat2Find-CPT",
     max_seq_length = 2048,
     load_in_4bit = True,
 )
@@ -84,7 +82,7 @@ print(tokenizer.batch_decode(outputs))
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "SENTIENT_ID/Chat2Find-CPT"
+model_name = "Chat2Find/Chat2Find-CPT"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")