Improve model card with paper information and usage details

README.md

@@ -1,165 +1,125 @@
 ---
 library_name: transformers
-tags: []
+license: cc-by-4.0
+pipeline_tag: feature-extraction
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
+This model is a BERT-based model fine-tuned for generating text embeddings. It was trained to improve the robustness of information retrieval systems by identifying and relabeling false negatives in training data. This process uses cascading LLM prompts, as described in [Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval](https://huggingface.co/papers/2505.16967).
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+*   **Developed by:** \[More Information Needed]
+*   **Shared by:** \[More Information Needed]
+*   **Model type:** BERT
+*   **Language(s) (NLP):** en
+*   **License:** cc-by-4.0
+*   **Finetuned from model:** e5-base-unsupervised-bge-retrieval-7-datasets-680K
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+### Model Sources
 
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+*   **Repository:** This repository.
+*   **Paper:** [Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval](https://huggingface.co/papers/2505.16967)
+*   **Github:** https://github.com/luojunyu/rlhn
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+This model is primarily used to generate text embeddings. These embeddings can then be used for various downstream tasks, especially information retrieval.
 
-[More Information Needed]
+### Downstream Use
 
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
+The model can be used as a drop-in replacement for the original e5-base model and for generating embeddings for improving retrieval performance.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+This model is not intended for use cases outside of information retrieval, such as content generation.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+The model's performance is tied to the quality of the relabeling process. The prompts used during relabeling can introduce biases.
 
 ## How to Get Started with the Model
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+```python
+from transformers import AutoModel, AutoTokenizer
+import torch
+
+model_name = "ThisHuggingFaceRepoID"  # Replace with the actual model name
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name).to('cuda')
+
+text = "This is an example sentence."
+inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512).to('cuda')
+with torch.no_grad():
+    embeddings = model(**inputs).last_hidden_state[:, 0, :]  # Extract embeddings
+print(embeddings.shape)
+```
 
 ## Training Details
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
+The model was fine-tuned using a semi-supervised approach, leveraging both labeled and unlabeled data. The unlabeled data was relabeled using a cascading LLM prompting strategy to correct false negatives.
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+The model utilizes supervised fine-tuning (SFT) and a bi-level knowledge propagation and selection mechanism (SemiEvol) to enhance its performance.
 
-#### Preprocessing [optional]
+#### Preprocessing
 
 [More Information Needed]
 
-
 #### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
+*   **Training regime:** bf16 mixed precision
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
 ### Testing Data, Factors & Metrics
 
 #### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
+The model was evaluated on several datasets, including BEIR and AIR-Bench.
 
 #### Factors
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
+The model's performance was analyzed across different benchmark datasets to assess its generalization capability.
 
 #### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+The primary evaluation metric is nDCG@10, which measures the ranking quality of retrieved passages.
 
 ### Results
 
-[More Information Needed]
+Relabeling false negatives with true positives improves both E5 (base) and Qwen2.5-7B retrieval models by 0.7-1.4 nDCG@10 on BEIR and by 1.7-1.8 nDCG@10 on zero-shot AIR-Bench evaluation. Similar gains are observed for rerankers fine-tuned on the relabeled data, such as Qwen2.5-3B on BEIR.
 
 #### Summary
 
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+The model achieves significant improvements on BEIR and AIR-Bench benchmarks, indicating that the relabeling strategy improves retrieval performance.
 
 ## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
 Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+*   **Hardware Type:** \[More Information Needed]
+*   **Hours used:** \[More Information Needed]
+*   **Cloud Provider:** \[More Information Needed]
+*   **Compute Region:** \[More Information Needed]
+*   **Carbon Emitted:** \[More Information Needed]
 
-## Technical Specifications [optional]
+## Technical Specifications
 
 ### Model Architecture and Objective
 
-[More Information Needed]
+The model uses a BERT-based architecture fine-tuned for generating text embeddings. The objective is to improve retrieval and reranking performance by relabeling hard negatives in the training data.
 
 ### Compute Infrastructure
 
-[More Information Needed]
-
 #### Hardware
 
 [More Information Needed]
@@ -168,32 +128,24 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 [More Information Needed]
 
-## Citation [optional]
+## Citation
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+```
+@misc{luo2024semievol,
+    title={SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation},
+    author={Junyu Luo and Xiao Luo and Xiusi Chen and Zhiping Xiao and Wei Ju and Ming Zhang},
+    year={2024},
+    eprint={2410.14745},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL},
+    url={https://arxiv.org/abs/2410.14745},
+}
+```
 
-**BibTeX:**
+## Model Card Authors
 
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
+\[More Information Needed]
 
 ## Model Card Contact
 
-[More Information Needed]
+\[More Information Needed]