Update README.md

README.md

@@ -41,7 +41,7 @@ The model was fine-tuned on a synthetic dataset derived from GPT-4 (for user que
 
 ### Performance Metrics
 - **Training Loss:** Final loss of 1.3721 after 3 epochs
-- **Initial MMLU Score:** 25% (equivalent to random guessing)
+- **Real-world Use** Seems to struggle with maintaining conversational context.
 
 ### Limitations and Current Shortcomings
 - The model's knowledge is limited to its training data and cut-off date.
@@ -101,7 +101,7 @@ Detailed evaluation results are not available, but the model showed consistent i
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-model_path = "path/to/your/finetuned/model"
+model_path = "QuietImpostor/OpenELM-270M-Instruct-SonnOpus"
 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained(model_path)