Update README.md with new details

README.md

@@ -19,11 +19,11 @@ pipeline_tag: text-generation
 
 # 🧪 Qwen2.5-0.5B-Instruct + LoRA Fine-Tuned on PubMedQA (pqa_labeled)
 
-This model is a LoRA-adapted version of [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct), fine-tuned using [Unsloth](https://github.com/unslothai/unsloth) on the `pqa_labeled` subset of the [PubMedQA](https://huggingface.co/datasets/pubmed_qa) dataset.
+This model is a LoRA-adapted version of [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct), fine-tuned using [Unsloth](https://github.com/unslothai/unsloth) on the `pqa_labeled` subset of the [PubMedQA](https://huggingface.co/datasets/qiaojin/PubMedQA) dataset.
 
 ## ✅ Summary
 
-This work demonstrates that even a compact instruction-tuned model like Qwen2.5 0.5B can achieve near state-of-the-art performance on biomedical QA tasks. With LoRA fine-tuning on just 1,000 examples, this model achieves **98.99% accuracy** on the PubMedQA test set.
+This work demonstrates that even a compact instruction-tuned model like Qwen2.5 0.5B Instruct can achieve near state-of-the-art performance on biomedical QA tasks. With LoRA fine-tuning using just 1,000  examples, this model achieves **98.99% accuracy** on the PubMedQA test set.
 
 It reframes the classification task as a text generation problem — prompting the model to generate "yes", "no", or "maybe" responses. This results in highly interpretable and efficient predictions with excellent generalization.
 
@@ -59,10 +59,9 @@ It reframes the classification task as a text generation problem — prompting t
   - `r`: 16
   - `alpha`: 16
   - `target_modules`: ["q_proj", "v_proj"]
-- **Epochs:** [Insert if known]
-- **Batch Size:** [Insert if known]
-- **Learning Rate:** [Insert if known]
-- **NEFTune:** [Insert if used]
+- **Epochs:** 100
+- **Batch Size:** 16
+- **Learning Rate:** 2e-4
 
 ---
 
@@ -73,8 +72,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel
 
 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
-model = PeftModel.from_pretrained(model, "ShahzebKhoso/qwen2.5-pubmedqa-lora")
-tokenizer = AutoTokenizer.from_pretrained("ShahzebKhoso/qwen2.5-pubmedqa-lora")
+model = PeftModel.from_pretrained(model, "ShahzebKhoso/qwen2.5-instruct-0.5B-pubmedqa-lora")
+tokenizer = AutoTokenizer.from_pretrained("ShahzebKhoso/qwen2.5-instruct-0.5B-pubmedqa-lora")
 ```
 
 ---
@@ -94,7 +93,7 @@ tokenizer = AutoTokenizer.from_pretrained("ShahzebKhoso/qwen2.5-pubmedqa-lora")
   title={Fine-tuning Qwen2.5-0.5B on PubMedQA with LoRA},
   author={Shahzeb Khoso},
   year={2025},
-  howpublished={\\url{https://huggingface.co/ShahzebKhoso/qwen2.5-pubmedqa-lora}},
+  howpublished={\\url{https://huggingface.co/ShahzebKhoso/qwen2.5-instruct-0.5B-pubmedqa-lora}},
 }
 ```
 
@@ -103,6 +102,6 @@ tokenizer = AutoTokenizer.from_pretrained("ShahzebKhoso/qwen2.5-pubmedqa-lora")
 ## ✨ Acknowledgements
 
 - [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
-- [PubMedQA Dataset](https://huggingface.co/datasets/pubmed_qa)
+- [PubMedQA Dataset](https://huggingface.co/datasets/qiaojin/PubMedQA)
 - [Unsloth](https://github.com/unslothai/unsloth)
 - [Hugging Face PEFT](https://github.com/huggingface/peft)