Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,251 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- ACE05
|
5 |
+
- bc5cdr
|
6 |
+
- conll2003
|
7 |
+
- ncbi_disease
|
8 |
+
- conll2012_ontonotesv5
|
9 |
+
- rams
|
10 |
+
- tacred
|
11 |
+
- wnut_17
|
12 |
+
- broad_twitter_corpus
|
13 |
+
- casie
|
14 |
+
- CrossNER
|
15 |
+
- e3c
|
16 |
+
- fabner
|
17 |
+
- harvey_ner
|
18 |
+
- mit_movies
|
19 |
+
- mit_restaurant
|
20 |
+
- multinerd
|
21 |
+
- WikiEvent
|
22 |
+
language:
|
23 |
+
- en
|
24 |
+
metrics:
|
25 |
+
- f1
|
26 |
+
pipeline_tag: text-generation
|
27 |
---
|
28 |
+
# Model Card for Model ID
|
29 |
+
|
30 |
+
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.
|
31 |
+
|
32 |
+
## Model Details
|
33 |
+
|
34 |
+
```Python
|
35 |
+
|
36 |
+
# The following lines describe the task definition
|
37 |
+
@dataclass
|
38 |
+
class PersonTemplate(Template):
|
39 |
+
"""Person templates encodes the information about the given query
|
40 |
+
Person entity."""
|
41 |
+
query: str # The Person entity query
|
42 |
+
alternate_names: Optional[List[Name]] = None
|
43 |
+
"""Names used to refer to the query person that are distinct from the
|
44 |
+
'official' name. Including: aliases, stage names, abbreviations ..."""
|
45 |
+
date_of_birth: Optional[Value] = None
|
46 |
+
"""The date on which the query person was born."""
|
47 |
+
age: Optional[Value] = None
|
48 |
+
"""A reported age of the query person."""
|
49 |
+
city_of_birth: Optional[Name] = None
|
50 |
+
"""The geopolitical entity at the municipality level (city, town, or
|
51 |
+
village) in which the query person was born"""
|
52 |
+
date_of_death: Optional[Value] = None
|
53 |
+
"""The date of the query person's death."""
|
54 |
+
|
55 |
+
# This is the text to analyze
|
56 |
+
text = "Mongolian Prime Minister M. Enkhbold arrived on Monday. "
|
57 |
+
# The annotation instances that take place in the text above are listed here
|
58 |
+
result = [
|
59 |
+
PersonTemplate(
|
60 |
+
query="M. Enkhbold",
|
61 |
+
countries_of_residence=[Name("Mongolian")],
|
62 |
+
title=[String("Prime Minister")],
|
63 |
+
),
|
64 |
+
]
|
65 |
+
|
66 |
+
```
|
67 |
+
|
68 |
+
|
69 |
+
### Model Description
|
70 |
+
|
71 |
+
<!-- Provide a longer summary of what this model is. -->
|
72 |
+
|
73 |
+
|
74 |
+
|
75 |
+
- **Developed by:** Oscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier Lopez de Lacalle, German Rigau, Eneko Agirre
|
76 |
+
- **Institution:** HiTZ Basque Center for Language Technology - Ixa, University of the Basque Country UPV/EHU
|
77 |
+
- **Model type:** CODE-LLaMA2
|
78 |
+
- **Language(s) (NLP):** English
|
79 |
+
- **License:** LLaMA2 License for the base and merged model. Apache 2.0 for pre-trained LoRA Adapters
|
80 |
+
- **Finetuned from model [optional]:** CODE-LLaMA2
|
81 |
+
|
82 |
+
### Model Sources [optional]
|
83 |
+
|
84 |
+
- **Repository:** https://github.com/osainz59/CoLLIE
|
85 |
+
- **Paper [optional]:** **Coming soon**
|
86 |
+
- **Demo [optional]:** **Coming soon**
|
87 |
+
|
88 |
+
## Uses
|
89 |
+
|
90 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
91 |
+
|
92 |
+
### Direct Use
|
93 |
+
|
94 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
95 |
+
|
96 |
+
[More Information Needed]
|
97 |
+
|
98 |
+
### Downstream Use [optional]
|
99 |
+
|
100 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
101 |
+
|
102 |
+
[More Information Needed]
|
103 |
+
|
104 |
+
### Out-of-Scope Use
|
105 |
+
|
106 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
107 |
+
|
108 |
+
[More Information Needed]
|
109 |
+
|
110 |
+
## Bias, Risks, and Limitations
|
111 |
+
|
112 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
113 |
+
|
114 |
+
[More Information Needed]
|
115 |
+
|
116 |
+
### Recommendations
|
117 |
+
|
118 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
119 |
+
|
120 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
121 |
+
|
122 |
+
## How to Get Started with the Model
|
123 |
+
|
124 |
+
Use the code below to get started with the model.
|
125 |
+
|
126 |
+
[More Information Needed]
|
127 |
+
|
128 |
+
## Training Details
|
129 |
+
|
130 |
+
### Training Data
|
131 |
+
|
132 |
+
<!-- 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. -->
|
133 |
+
|
134 |
+
[More Information Needed]
|
135 |
+
|
136 |
+
### Training Procedure
|
137 |
+
|
138 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
139 |
+
|
140 |
+
#### Preprocessing [optional]
|
141 |
+
|
142 |
+
[More Information Needed]
|
143 |
+
|
144 |
+
|
145 |
+
#### Training Hyperparameters
|
146 |
+
|
147 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
148 |
+
|
149 |
+
#### Speeds, Sizes, Times [optional]
|
150 |
+
|
151 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
152 |
+
|
153 |
+
[More Information Needed]
|
154 |
+
|
155 |
+
## Evaluation
|
156 |
+
|
157 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
158 |
+
|
159 |
+
### Testing Data, Factors & Metrics
|
160 |
+
|
161 |
+
#### Testing Data
|
162 |
+
|
163 |
+
<!-- This should link to a Data Card if possible. -->
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Factors
|
168 |
+
|
169 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
170 |
+
|
171 |
+
[More Information Needed]
|
172 |
+
|
173 |
+
#### Metrics
|
174 |
+
|
175 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
### Results
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
#### Summary
|
184 |
+
|
185 |
+
|
186 |
+
|
187 |
+
## Model Examination [optional]
|
188 |
+
|
189 |
+
<!-- Relevant interpretability work for the model goes here -->
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Environmental Impact
|
194 |
+
|
195 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
196 |
+
|
197 |
+
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).
|
198 |
+
|
199 |
+
- **Hardware Type:** [More Information Needed]
|
200 |
+
- **Hours used:** [More Information Needed]
|
201 |
+
- **Cloud Provider:** [More Information Needed]
|
202 |
+
- **Compute Region:** [More Information Needed]
|
203 |
+
- **Carbon Emitted:** [More Information Needed]
|
204 |
+
|
205 |
+
## Technical Specifications [optional]
|
206 |
+
|
207 |
+
### Model Architecture and Objective
|
208 |
+
|
209 |
+
[More Information Needed]
|
210 |
+
|
211 |
+
### Compute Infrastructure
|
212 |
+
|
213 |
+
[More Information Needed]
|
214 |
+
|
215 |
+
#### Hardware
|
216 |
+
|
217 |
+
[More Information Needed]
|
218 |
+
|
219 |
+
#### Software
|
220 |
+
|
221 |
+
[More Information Needed]
|
222 |
+
|
223 |
+
## Citation [optional]
|
224 |
+
|
225 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
226 |
+
|
227 |
+
**BibTeX:**
|
228 |
+
|
229 |
+
[More Information Needed]
|
230 |
+
|
231 |
+
**APA:**
|
232 |
+
|
233 |
+
[More Information Needed]
|
234 |
+
|
235 |
+
## Glossary [optional]
|
236 |
+
|
237 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
238 |
+
|
239 |
+
[More Information Needed]
|
240 |
+
|
241 |
+
## More Information [optional]
|
242 |
+
|
243 |
+
[More Information Needed]
|
244 |
+
|
245 |
+
## Model Card Authors [optional]
|
246 |
+
|
247 |
+
[More Information Needed]
|
248 |
+
|
249 |
+
## Model Card Contact
|
250 |
+
|
251 |
+
[More Information Needed]
|