.

README.md

@@ -34,34 +34,6 @@ tags:
 
 ## Usage
 
-### Load with `transformers` (recommended)
-
-```python
-from transformers import AutoModel, AutoTokenizer
-import torch
-
-model = AutoModel.from_pretrained("Manhph2211/Q-HEART", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
-model.eval()
-
-# 12-lead ECG: [batch, leads, length], 5000 = 10s × 500 Hz
-ecg = torch.randn(1, 12, 5000)
-question = "What is the heart rhythm shown in this ECG?"
-inputs = tokenizer(question, return_tensors="pt")
-
-with torch.no_grad():
-    output_ids = model.generate(
-        ecg=ecg,
-        input_ids=inputs["input_ids"],
-        attention_mask=inputs["attention_mask"],
-        max_new_tokens=50,
-    )
-answer = tokenizer.decode(output_ids[0], skip_special_tokens=True)
-print(answer)
-```
-
-### Load with the GitHub repo
-
 ```bash
 git clone https://github.com/manhph2211/Q-HEART.git && cd Q-HEART
 conda create -n qheart python=3.9
@@ -70,21 +42,12 @@ pip install torch --index-url https://download.pytorch.org/whl/cu118
 pip install -r requirements.txt
 ```
 
-Download the checkpoint from [here](https://huggingface.co/Manhph2211/Q-HEART) and place it at `ckpts/sample.bin`, then run evaluation:
+Download the checkpoint from [here](https://huggingface.co/Manhph2211/Q-HEART) and place it at `ckpts/pytorch_model.bin`, then run evaluation:
 
 ```bash
 python main.py --eval --model_type meta-llama/Llama-3.2-1B-Instruct --mapping_type Transformer
 ```
 
-## Requirements
-
-In addition to `transformers`, this model requires:
-
-```
-peft
-einops
-```
-
 ## Citation
 
 ```bibtex