chore: push model card

README.md

@@ -5,195 +5,147 @@ datasets:
 ---
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+This model is a fine-tune of [GLiNER](https://huggingface.co/urchade/gliner_small-v2.1) aimed at improving accuracy across a broad range of topics, especially with respect to long-context news entity extraction. As hown in the table below, these fine-tunes improved upon the base GLiNER model zero-shot accuracy by up to 7.5% across 18 benchmark datasets.
 
-This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
+![results table](assets/zero-shot_20_table.png)
 
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **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 [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
+The underlying dataset, [AskNews-NER-v0](https://huggingface.co/datasets/EmergentMethods/AskNews-NER-v0) was engineered with the objective of diversifying global perspectives by enforcing country/language/topic/temporal diversity. All data used to fine-tune this model was synthetically generated. WizardLM 13B v2.0 was used for translation/summarization of open-web news articles, while Llama3 70b instruct was used for entity extraction. Both the diversification and fine-tuning methods are presented in a [pre-print submitted to NeurIps2024](https://linktoarxiv.org).
 
-<!-- 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. -->
-
-[More Information Needed]
+# Usage
 
-### Downstream Use [optional]
+```python
+from gliner import GLiNER
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+model = GLiNER.from_pretrained("EmergentMethods/gliner_small_news-v2.1")
 
-[More Information Needed]
+text = """
+The Chihuahua State Public Security Secretariat (SSPE) arrested 35-year-old Salomón C. T. in Ciudad Juárez, found in possession of a stolen vehicle, a white GMC Yukon, which was reported stolen in the city's streets. The arrest was made by intelligence and police analysis personnel during an investigation in the border city. The arrest is related to a previous detention on February 6, which involved armed men in a private vehicle. The detainee and the vehicle were turned over to the Chihuahua State Attorney General's Office for further investigation into the case. 
+"""
 
-### Out-of-Scope Use
+labels = ["person", "location", "date", "event", "facility", "vehicle", "number", "organization"]
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+entities = model.predict_entities(text, labels)
 
-[More Information Needed]
+for entity in entities:
+    print(entity["text"], "=>", entity["label"])
+```
 
-## Bias, Risks, and Limitations
+Output:
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+```
+Chihuahua State Public Security Secretariat => organization
+SSPE => organization
+35-year-old => number
+Salomón C. T. => person
+Ciudad Juárez => location
+GMC Yukon => vehicle
+February 6 => date
+Chihuahua State Attorney General's Office => organization
+```
 
-[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.
-
-## How to Get Started with the Model
+## Model Details
 
-Use the code below to get started with the model.
+### Model Description
 
-[More Information Needed]
+<!-- Provide a longer summary of what this model is. -->
 
-## Training Details
+The synthetic data underlying this news fine-tune was pulled from the [AskNews API](https://docs.asknews.app). We enforced diveristy across country/language/topic/time.
 
-### Training Data
+Countries:
 
-<!-- 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. -->
+![country distribution](assets/countries_distribution.png)
 
-[More Information Needed]
+Entity types:
 
-### Training Procedure
+![entities](assets/entity-types_limited.png)
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+Topics:
 
-#### Preprocessing [optional]
+![topics](assets/topics_fig_connected.png)
 
-[More Information Needed]
 
+- **Developed by:** [Emergent Methods](https://www.emergentmethods.ai/)
+- **Funded by:** [Emergent Methods](https://www.emergentmethods.ai/)
+- **Shared by:** [Emergent Methods](https://www.emergentmethods.ai/)
+- **Model type:** microsoft/deberta
+- **Language(s) (NLP):** English (en), and translated French, Spanish, German, Swedish, Italian, Arabic, Chinese, Norwegian, Danish, Dutch, Russian, Ukranian
+- **License:** Apache 2.0
+- **Finetuned from model:** [GLiNER](https://huggingface.co/urchade/gliner_small-v2.1)
 
-#### Training Hyperparameters
+### Model Sources [optional]
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+<!-- Provide the basic links for the model. -->
 
-#### Speeds, Sizes, Times [optional]
+- **Repository:** To be added
+- **Paper:** To be added
+- **Demo:** To be added
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+## Uses
 
-[More Information Needed]
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-## Evaluation
+### Direct Use
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-### Testing Data, Factors & Metrics
+As the name suggests, this model is aimed at generalist entity extraction. Although we used news to fine-tune this model, it improved accuracy across 18 benchmark datasets by up to 7.5%. This means that the broad and diversified underlying dataset has helped it to recognize and extract more entity types.
 
-#### Testing Data
+This model is shockingly compact, and can be used for high-throughput production usecases. This is another reason we have licensed this as Apache 2.0. Currently, [AskNews](https://asknews.app) is using this fine-tune for entity extraction in their system.
 
-<!-- This should link to a Dataset Card if possible. -->
 
-[More Information Needed]
+## Bias, Risks, and Limitations
 
-#### Factors
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+Although the goal of the dataset is to reduce bias, and improve diversity, it is still biased to western languages and countries. This limitation originates from the abilities of Llama2 for the translation and summary generations. Further, any bias originating in Llama2 training data will also be present in this dataset, since Llama2 was used to summarize the open-web articles. Further, any biases present in Llama3 will be present in the present dataaset since Llama3 was used to extract entities from the summaries.
 
-[More Information Needed]
+![countries distribution](figures/topics_fig_connected.png)
 
-#### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+## How to Get Started with the Model
 
-[More Information Needed]
+Use the code below to get started with the model.
 
-### Results
 
-[More Information Needed]
 
-#### Summary
+## Training Details
 
+<!-- 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. -->
 
+The training dataset is [AskNews-NER-v0](https://huggingface.co/datasets/EmergentMethods/AskNews-NER-v0).
 
-## Model Examination [optional]
+Other training details can be found in the [companion paper](https://linktoarxiv.org).
 
-<!-- Relevant interpretability work for the model goes here -->
 
-[More Information Needed]
 
 ## 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]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
+- **Hardware Type:** 1xA4500
+- **Hours used:** 10
+- **Carbon Emitted:** 0.6 kg (According to [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute))
 
-#### Hardware
 
-[More Information Needed]
-
-#### Software
-
-[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. -->
 
 **BibTeX:**
 
-[More Information Needed]
+To be added
 
 **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]
+To be added
 
-[More Information Needed]
+## Model Authors
 
-## Model Card Authors [optional]
+Elin Törnquist, Emergent Methods elin at emergentmethods.ai
+Robert Caulk, Emergent Methods rob at emergentmethods.ai
 
-[More Information Needed]
 
-## Model Card Contact
+## Model Contact
 
-[More Information Needed]
+Elin Törnquist, Emergent Methods elin at emergentmethods.ai
+Robert Caulk, Emergent Methods rob at emergentmethods.ai