Update README.md

README.md

@@ -22,7 +22,6 @@ This repo contains the instruction-tuned 7B OmniChem model, which has the follow
 * **Context Length**: Supports up to 128K tokens
 * **License**: CC BY-NC-SA 4.0 (for academic, non-commercial use)
 
-For more details, please refer to our **[Paper](Link to your paper)** and **[Project GitHub](Link to your GitHub)**.
 
 ### Requirements
 
@@ -37,8 +36,7 @@ Here is a code snippet showing how to load the OmniChem model and tokenizer to g
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Make sure to replace "YourUsername/OmniChem-7B-v1" with your actual model path on the Hub
-model_name = "YourUsername/OmniChem-7B-Instruct"
+model_name = "YourUsername/OmniChem-7B-v1"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -50,7 +48,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 # Example prompt for a chemistry task
 prompt = "Plan a synthetic route for the small molecule drug lidocaine."
 messages = [
-    {"role": "system", "content": "You are OmniChem, a highly reliable AI assistant for chemistry research. Provide accurate, fact-based, and logical responses."},
+    {"role": "system", "content": "You are a chemistry expert. Your task is to answer the user's problem using the most academic and rigorous professor-level language in a structured format. Think step by step."},
     {"role": "user", "content": prompt}
 ]
 
@@ -87,4 +85,6 @@ To handle extensive inputs exceeding 32,768 tokens, we utilize YaRN, a technique
     "type": "yarn"
   }
 }
-```
+```
+### License
+This model is licensed under CC BY-NC-SA 4.0 for non-commercial use. Commercial use requires explicit permission. Contact [[email protected]] for inquiries.