Update README.md

README.md

@@ -7,7 +7,7 @@ tags:
 - ruslanmv
 - llama
 - trl
-base_model: meata/llama-3-8b
+base_model: meta-llama/Meta-Llama-3-8B
 datasets:
 - ruslanmv/ai-medical-chatbot
 ---
@@ -20,7 +20,7 @@ This repository provides a fine-tuned version of the powerful Llama3 8B model, s
 
 - **Developed by:** ruslanmv
 - **License:** Apache-2.0
-- **Finetuned from model:** unsloth/llama-3-8b-bnb-4bit
+- **Finetuned from model:** meta-llama/Meta-Llama-3-8B
 
 **Key Features**
 
@@ -44,8 +44,8 @@ Here's a Python code snippet demonstrating how to interact with the `Medical-Lla
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("ruslanmv/Medical-Llama3-8B-16bit")
-model = AutoModelForCausalLM.from_pretrained("ruslanmv/Medical-Llama3-8B-16bit").to("cuda")  # If using GPU
+tokenizer = AutoTokenizer.from_pretrained("ruslanmv/Medical-Llama3-8B")
+model = AutoModelForCausalLM.from_pretrained("ruslanmv/Medical-Llama3-8B").to("cuda")  # If using GPU
 
 # Function to format and generate response with prompt engineering
 def askme(question):