Update README.md

README.md

@@ -1,7 +1,5 @@
 ---
 library_name: peft
-tags:
-- generated_from_trainer
 metrics:
 - precision
 - recall
@@ -11,6 +9,12 @@ base_model: NousResearch/Llama-2-7b-hf
 model-index:
 - name: billm-llama-7b-conll03-ner
   results: []
+license: mit
+datasets:
+- conll2003
+language:
+- en
+pipeline_tag: token-classification
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,7 +22,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 # billm-llama-7b-conll03-ner
 
-This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) using [BiLLM](https://github.com/WhereIsAI/BiLLM).
+
 It achieves the following results on the evaluation set:
 - Loss: 0.1664
 - Precision: 0.9243
@@ -26,19 +31,38 @@ It achieves the following results on the evaluation set:
 - F1: 0.9319
 - Accuracy: 0.9860
 
-## Model description
+## Inference
 
-More information needed
+```bash
+python -m pip install -U billm
+```
 
-## Intended uses & limitations
+```python
+from transformers import AutoTokenizer, pipeline
+from peft import PeftModel, PeftConfig
+from billm import MistralForTokenClassification
 
-More information needed
 
-## Training and evaluation data
+label2id = {'O': 0, 'B-PER': 1, 'I-PER': 2, 'B-ORG': 3, 'I-ORG': 4, 'B-LOC': 5, 'I-LOC': 6, 'B-MISC': 7, 'I-MISC': 8}
+id2label = {v: k for k, v in label2id.items()}
+model_id = 'WhereIsAI/billm-llama-7b-conll03-ner'
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+peft_config = PeftConfig.from_pretrained(model_id)
+model = MistralForTokenClassification.from_pretrained(
+    peft_config.base_model_name_or_path,
+    num_labels=len(label2id), id2label=id2label, label2id=label2id
+)
+model = PeftModel.from_pretrained(model, model_id)
+# merge_and_unload is necessary for inference
+model = model.merge_and_unload()
 
-More information needed
+token_classifier = pipeline("token-classification", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
+sentence = "I live in Hong Kong. I am a student at Hong Kong PolyU."
+tokens = token_classifier(sentence)
+print(tokens)
+```
 
-## Training procedure
+## Training Details
 
 ### Training hyperparameters
 
@@ -73,4 +97,23 @@ The following hyperparameters were used during training:
 - Transformers 4.38.2
 - Pytorch 2.0.1
 - Datasets 2.16.0
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0
+
+## Citation
+
+```bibtex
+@inproceedings{li2024bellm,
+    title = "BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings",
+    author = "Li, Xianming and Li, Jing",
+    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics",
+    year = "2024",
+    publisher = "Association for Computational Linguistics"
+}
+
+@article{li2023label,
+  title={Label supervised llama finetuning},
+  author={Li, Zongxi and Li, Xianming and Liu, Yuzhang and Xie, Haoran and Li, Jing and Wang, Fu-lee and Li, Qing and Zhong, Xiaoqin},
+  journal={arXiv preprint arXiv:2310.01208},
+  year={2023}
+}
+```