HiTZ
/

GoLLIE-7B

@@ -14,228 +14,156 @@ language:
 metrics:
 - f1
 pipeline_tag: text-generation
 ---
-# Model Card for Model ID
-GoLLIE **G**uideline-f**o**llowing **L**arge **L**anguage Model for **IE**, is a model able to improve zero-shot results on unseen IE tasks by virtue of being fine-tuned to comply with  annotation guidelines.
-## Model Details
-```Python
-# The following lines describe the task definition
-@dataclass
-class PersonTemplate(Template):
-  """Person templates encodes the information about the given query
-  Person entity."""
-  query: str # The Person entity query
-  alternate_names: Optional[List[Name]] = None
-  """Names used to refer to the query person that are distinct from the
-  'official' name. Including: aliases, stage names, abbreviations ..."""
-  date_of_birth: Optional[Value] = None
-  """The date on which the query person was born."""
-  age: Optional[Value] = None
-  """A reported age of the query person."""
-  city_of_birth: Optional[Name] = None
-  """The geopolitical entity at the municipality level (city, town, or
-  village) in which the query person was born"""
-  date_of_death: Optional[Value] = None
-  """The date of the query person's death."""
-# This is the text to analyze
-text = "Mongolian Prime Minister M. Enkhbold arrived on Monday. "
-# The annotation instances that take place in the text above are listed here
-result = [
-  PersonTemplate(
-    query="M. Enkhbold",
-    countries_of_residence=[Name("Mongolian")],
-    title=[String("Prime Minister")],
-  ),
-]
-```
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-- **Developed by:** Oscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier Lopez de Lacalle, German Rigau, Eneko Agirre
-- **Institution:** HiTZ Basque Center for Language Technology - Ixa, University of the Basque Country UPV/EHU
-- **Model type:** CODE-LLaMA2
 - **Language(s) (NLP):** English
 - **License:** LLaMA2 License for the base and merged model. Apache 2.0 for pre-trained LoRA Adapters
-- **Finetuned from model [optional]:** CODE-LLaMA2
-### Model Sources [optional]
-- **Repository:** https://github.com/osainz59/CoLLIE
-- **Paper [optional]:** **Coming soon**
-- **Demo [optional]:** **Coming soon**
-## 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. -->
-[More Information Needed]
-### 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]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## 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.
 ## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Data 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]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[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]
 ## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Data Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- 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
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- 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]
-**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]
-## Model Card Contact
-[More Information Needed]

 metrics:
 - f1
 pipeline_tag: text-generation
+tags:
+- code
+- text-generation-inference
+- Information Extraction
+- IE
+- Named Entity Recogniton
+- Event Extraction
+- Relation Extraction
+- LLaMA
 ---
+<p align="center">
+    <br>
+    <img src="assets/GoLLIE.png" style="height: 250px;">
+    <br>
+    <h2 align="center"><b>G</b>uideline f<b>o</b>llowing <b>L</b>arge <b>L</b>anguage Model for <b>I</b>nformation <b>E</b>xtraction</h2>
+# Model Card for GoLLIE 7B
+<p align="justify">
+We present  <img src="assets/GoLLIE.png" width="20"> GoLLIE, a Large Language Model trained to follow annotation guidelines. GoLLIE outperforms previous approaches on zero-shot Information Extraction and allows the user to perform inferences with annotation schemas defined on the fly. Different from previous approaches, GoLLIE is able to follow detailed definitions and does not only rely on the knowledge already encoded in the LLM. Code and models are publicly available.
+- 💻 Code: [https://github.com/osainz59/CoLLIE/](https://github.com/osainz59/CoLLIE/)
+- 📒 Blog Post: [GoLLIE: Guideline-following Large Language Model for Information Extraction](docs/index.md)
+- 📖 Paper: [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction]()
+- <img src="assets/GoLLIE.png" width="20">GoLLIE in the 🤗HuggingFace Hub: [HiTZ/gollie](https://huggingface.co/collections/HiTZ/gollie-651bf19ee315e8a224aacc4f)
+- 🚀 Example Jupyter Notebooks: [GoLLIE Notebooks](notebooks/)
+</p>
+<p align="center">
+<img src="assets/zero_shot_results.png">
+</p>
+### Model Description
+- **Developed by:** [Oscar Sainz](https://osainz59.github.io/), [Iker García-Ferrero](https://ikergarcia1996.github.io/Iker-Garcia-Ferrero/), [Rodrigo Agerri](https://ragerri.github.io/), [Oier Lopez de Lacalle](https://oierldl.github.io/), [German Rigau](https://adimen.si.ehu.es/~rigau/) and [Eneko Agirre](https://eagirre.github.io/)
+- **Institution:** [HiTZ Basque Center for Language Technology](http://www.hitz.eus/) - [Ixa](https://www.ixa.eus/node/2?language=en), [University of the Basque Country UPV/EHU](https://www.ehu.eus/en/en-home)
+- **Model type:** Text Generation
 - **Language(s) (NLP):** English
 - **License:** LLaMA2 License for the base and merged model. Apache 2.0 for pre-trained LoRA Adapters
+- **Finetuned from model:** CODE-LLaMA2
+## Schema definition and inference example
+The labels are represented as Python classes, and the guidelines or instructions are introduced as docstrings. The model start generating after the `result = [` line.
+```Python
+# Entity definitions
+@dataclass
+class Launcher(Template):
+    """Refers to a vehicle designed primarily to transport payloads from the Earth's
+    surface to space. Launchers can carry various payloads, including satellites,
+    crewed spacecraft, and cargo, into various orbits or even beyond Earth's orbit.
+    They are usually multi-stage vehicles that use rocket engines for propulsion."""
+    mention: str
+    """
+    The name of the launcher vehicle.
+    Such as: "Sturn V", "Atlas V", "Soyuz", "Ariane 5"
+    """
+    space_company: str # The company that operates the launcher. Such as: "Blue origin", "ESA", "Boeing", "ISRO", "Northrop Grumman", "Arianespace"
+    crew: List[str] # Names of the crew members boarding the Launcher. Such as: "Neil Armstrong", "Michael Collins", "Buzz Aldrin"
+@dataclass
+class Mission(Template):
+    """Any planned or accomplished journey beyond Earth's atmosphere with specific objectives,
+    either crewed or uncrewed. It includes missions to satellites, the International
+    Space Station (ISS), other celestial bodies, and deep space."""
+    mention: str
+    """
+    The name of the mission.
+    Such as: "Apollo 11", "Artemis", "Mercury"
+    """
+    date: str # The start date of the mission
+    departure: str # The place from which the vehicle will be launched. Such as: "Florida", "Houston", "French Guiana"
+    destination: str # The place or planet to which the launcher will be sent. Such as "Moon", "low-orbit", "Saturn"
+# This is the text to analyze
+text = (
+    "The Ares 3 mission to Mars is scheduled for 2032. The Starship rocket build by SpaceX will take off from Boca Chica,"
+    "carrying the astronauts Max Rutherford, Elena Soto, and Jake Martinez."
+)
+# The annotation instances that take place in the text above are listed here
+result = [
+    Mission(mention='Ares 3', date='2032', departure='Boca Chica', destination='Mars'),
+    Launcher(mention='Starship', space_company='SpaceX', crew=['Max Rutherford', 'Elena Soto', 'Jake Martinez'])
+]
+```
 ## How to Get Started with the Model
+Please read our [🚀 Example Jupyter Notebooks](notebooks/) to get started with GoLLIE.
+The best way to load the model is using our custom `load_model` fuction. However, you can also load them using the AutoModelForCausalLM class.
+**Important**: Our flash attention implementation has small numerical differences compared to the attention implementation in Huggingface.
+You must use the flag `trust_remote_code=True` or you will get inferior results. Flash attention requires an available CUDA GPU. Running GOLLIE
+pre-trained models on a CPU is not supported. We plan to address this in future releases. First, install flash attention 2:
+```bash
+pip install flash-attn --no-build-isolation
+pip install git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary
+```
+Then you can load the model using
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("HiTZ/GoLLIE-7B")
+model = AutoModelForCausalLM.from_pretrained("HiTZ/GoLLIE-7B", trust_remote_code=True)
+```
+Read our [🚀 Example Jupyter Notebooks](notebooks/) to learn how to easily define guidelines, generate model inputs and parse the output!
+### Training Data
+This is the list of task used for training and evaluating GoLLIE. However, as demonstrated in the  🚀 [Create Custom Task notebook](notebooks/Create%20Custom%20Task.ipynb) GoLLIE can perform a wide range of unseen tasks.
+For more info, read our [📖Paper]().
+<p align="center">
+<img src="assets/datasets.png">
+</p>
 ## Evaluation
+| Model | Supervised average F1 | Zero-shot average F1 |                     🤗HuggingFace Hub                     |
+|---|:---------------------:|:--------------------:|:---------------------------------------------------------:|
+| GoLLIE-7B |         73.0          |         55.3         |  [HiTZ/GoLLIE-7B](https://huggingface.co/HiTZ/GoLLIE-7B)  |
+| GoLLIE-13B |         73.9          |         56.0         | [HiTZ/GoLLIE-13B](https://huggingface.co/HiTZ/GoLLIE-13B) |
+| GoLLIE-34B |       **75.0**        |       **57.2**       | [HiTZ/GoLLIE-34B](https://huggingface.co/HiTZ/GoLLIE-34B) |
 ## Environmental Impact
+| Model | Hardware | FLOPs            | Time (h) | CO<sup>2</sup>eq (kg) |
+|----------------|-------------------|---------------------------|-------------------|-------------------------------------|
+| <img src="assets/GoLLIE.png" width="20">GoLLIE 7B       | 1xA100            | 11.9e<sup>18</sup> | 44.5              | 1.57                                |
+| <img src="assets/GoLLIE.png" width="20">GoLLIE 13B    | 1xA100            | 22.7e<sup>18</sup> | 79.5              | 2.80                                |
+| <img src="assets/GoLLIE.png" width="20">GoLLIE 34B    | 2xA100            | 55.8e<sup>18</sup> | 94.6              | 6.67                                |
+## Citation