Update README.md

README.md

@@ -37,4 +37,73 @@ Herberta combines the strengths of modern pretraining techniques and domain know
   "num_hidden_layers": 24,
   "torch_dtype": "float32",
   "vocab_size": 21128
-}
+}
+### requirements
+"transformers_version": "4.45.1"
+```bash
+pip install herberta
+```
+
+###  Quickstart
+
+#### Use Huggingface
+```python
+from transformers import AutoTokenizer, AutoModel
+
+# Replace "XiaoEnn/herberta" with the Hugging Face model repository name
+model_name = "XiaoEnn/herberta"
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+
+# Input text
+text = "中医理论是我国传统文化的瑰宝。"
+
+# Tokenize and prepare input
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding="max_length", max_length=128)
+
+# Get the model's outputs
+with torch.no_grad():
+    outputs = model(**inputs)
+
+# Get the embedding (sentence-level average pooling)
+sentence_embedding = outputs.last_hidden_state.mean(dim=1)
+
+print("Embedding shape:", sentence_embedding.shape)
+print("Embedding vector:", sentence_embedding)
+```
+
+
+#### LocalModel
+```python
+from transformers import BertTokenizer, BertForMaskedLM
+
+# Load the model and tokenizer
+model_name = "Chengfengke/herberta"
+tokenizer = BertTokenizer.from_pretrained(model_name)
+model = BertForMaskedLM.from_pretrained(model_name)
+inputs = tokenizer("This is an example text for herbal medicine.", return_tensors="pt")
+outputs = model(**inputs)
+```
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```bibtex
+@misc{herberta-embedding,
+  title = {Herberta: A Pretrain_Bert_Model for TCM_herb and downstream Tasks as Text Embedding Generation},
+  url = {https://github.com/15392778677/herberta},
+  author = {Yehan Yang,Xinhan Zheng},
+  month = {December},
+  year = {2024}
+}
+
+@article{herbert-technical-report,
+  title={Herbert: A Pretrain_Bert_Model for TCM_herb and downstream Tasks as Text Embedding Generation},
+  author={Yehan Yang,Xinhan Zheng},
+  institution={Beijing Angopro Technology Co., Ltd.},
+  year={2024},
+  note={Presented at the 2024 Machine Learning Applications Conference (MLAC)}
+}