Update README.md

README.md

@@ -14,13 +14,13 @@ datasets:
 - FreedomIntelligence/alpaca-gpt4-korean
 ---
 
-# unsloth/mistral-7b-v0.3 fine tuning after Continued Pretraining
+# unsloth/Meta-Llama-3.1-8B-bnb-4bit fine tuning after Continued Pretraining
 # (TREX-Lab at Seoul Cyber University)
 
 <!-- Provide a quick summary of what the model is/does. -->
 
 ## Summary
-  - Base Model : unsloth/mistral-7b-v0.3
+  - Base Model : unsloth/Meta-Llama-3.1-8B-bnb-4bit
   - Dataset : wikimedia/wikipedia(Continued Pretraining), FreedomIntelligence/alpaca-gpt4-korean(FineTuning)
   - This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
   - Test whether fine tuning of a large language model is possible on A30 GPU*1 (successful)
@@ -29,7 +29,7 @@ datasets:
 
 - **Developed by:** [TREX-Lab at Seoul Cyber University]
 - **Language(s) (NLP):** [Korean]
-- **Finetuned from model :** [unsloth/mistral-7b-v0.3]
+- **Finetuned from model :** [unsloth/Meta-Llama-3.1-8B-bnb-4bit]
 
 ## Continued Pretraining
 ```