Update README.md

README.md

@@ -10,7 +10,7 @@ language:
 
 ### Overview
 
-The FINGU-AI/FinguAI-Chat-v1, model offers a specialized curriculum tailored to English, Korean, and Japanese speakers interested in finance, investment, and legal frameworks. It aims to enhance language proficiency while providing insights into global finance markets and regulatory landscapes.
+The FINGU-AI/FinguAI-Chat-v1 model offers a specialized curriculum tailored to English, Korean, and Japanese speakers interested in finance, investment, and legal frameworks. It aims to enhance language proficiency while providing insights into global finance markets and regulatory landscapes.
 
 ### Key Features
 
@@ -26,6 +26,12 @@ The FINGU-AI/FinguAI-Chat-v1, model offers a specialized curriculum tailored to
 - **Author**: Grinda AI Inc.
 - **License**: Apache-2.0
 
+### Training Details
+
+- **Fine-Tuning**: The model was fine-tuned on the base model Qwen/Qwen1.5-0.5B-Chat through supervised fine-tuning using the TrL Library and Transformer.
+- **Dataset**: The fine-tuning dataset consisted of 9042 training samples, with 3000 samples each in Korean, English, and Japanese languages.
+
+
 ### How to Use
 
 To use the FINGU-AI/FinguAI-Chat-v1 model, you can utilize the Hugging Face Transformers library. Here's a Python code snippet demonstrating how to load the model and generate predictions:
@@ -58,19 +64,22 @@ tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_gene
 generation_params = {
     'max_new_tokens': 1000,
     'use_cache': True,
-    #'prompt_lookup_num_tokens':10,
     'do_sample': True,
     'temperature': 0.7,
     'top_p': 0.9,
     'top_k': 50,
-    #'bos_token_id': tokenizer.bos_token_id,
     'eos_token_id': tokenizer.eos_token_id,
 }
 
 outputs = model.generate(tokenized_chat, **generation_params, streamer=streamer)
 decoded_outputs = tokenizer.batch_decode(outputs)
-
-'''
-To avoid losses, it's essential to maintain discipline, set realistic goals, and adhere to predetermined rules for trading. Diversification is key as it spreads investments across different sectors and asset classes to reduce overall risk. Regularly reviewing and rebalancing positions can also ensure alignment with investment objectives. Additionally, staying informed about market trends and economic indicators can provide opportunities for long-term capital preservation. It's also important to stay patient and avoid emotional decision-making, as emotions often cloud judgment. If you encounter significant losses, consider using stop-loss orders to limit your losses. Staying disciplined and focusing on long-term objectives can help protect your investment portfolio from permanent damage.
-'''
+```
+To avoid losses, it's essential to maintain discipline, set realistic goals, and adhere to predetermined rules for trading.
+Diversification is key as it spreads investments across different sectors and asset classes to reduce overall risk.
+Regularly reviewing and rebalancing positions can also ensure alignment with investment objectives. Additionally,
+staying informed about market trends and economic indicators can provide opportunities for long-term capital preservation.
+It's also important to stay patient and avoid emotional decision-making, as emotions often cloud judgment.
+If you encounter significant losses, consider using stop-loss orders to limit your losses.
+Staying disciplined and focusing on long-term objectives can help protect your investment portfolio from permanent damage.
+```
 ```