Update README.md

README.md

@@ -5,17 +5,16 @@ tags: []
 
 # Model Card for Meta-Llama-3-8B-for-bank
 
-This model, **Meta-Llama-3-8B-for-bank**, is a fine-tuned version of the `meta-llama/Meta-Llama-3-8B-Instruct` model. It is optimized for financial service-related tasks, enabling users to interact with the model using natural language for common financial operations such as balance inquiries, retrieving stock lists, buying stocks, and performing deposit/withdrawal transactions.
-
+This model, **Meta-Llama-3-8B-for-bank**, is a fine-tuned version of the `meta-llama/Meta-Llama-3-8B-Instruct` model. 
 ## Model Details
 
 ### Model Description
 
 - **Model Name**: Meta-Llama-3-8B-for-bank
 - **Base Model**: `meta-llama/Meta-Llama-3-8B-Instruct`
-- **Fine-tuning Data**: Custom financial chat examples
+- **Fine-tuning Data**: Custom bank chat examples
 - **Version**: 1.0
-- **License**: [Model License (if any)]
+- **License**: Free
 - **Language**: English
 
 ### Model Type
@@ -49,19 +48,12 @@ This model is designed for financial service tasks such as:
 
 This model has been fine-tuned with a dataset specifically created to simulate financial service interactions, covering a variety of questions related to account management and stock trading.
 
-## Intended Use
-
-This model is intended for integration into financial chatbots, virtual assistants, or other systems requiring automated handling of financial queries.
 
 ## Limitations
 
-- **Domain Specificity**: The model may not perform well outside financial-related tasks.
-- **Misinterpretation Risks**: There is a potential risk of misunderstanding complex or ambiguous queries.
+- **Misinterpretation Risks**: Right now this is the first version, so when the query is too complex, inconsistent results will be returned.
 
-## Ethical Considerations
 
-- **Bias**: Trained on synthetic data, the model may not represent all user demographics.
-- **Privacy**: The model should be used in compliance with financial privacy regulations.
 
 ## How to Use
 
@@ -70,6 +62,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("jeromecondere/Meta-Llama-3-8B-for-bank")
+#merge it first with llama3-8b-instrucions
 model = AutoModelForCausalLM.from_pretrained("jeromecondere/Meta-Llama-3-8B-for-bank").to("cuda")
 
 # Example of usage