Update README.md
Browse files
README.md
CHANGED
@@ -55,4 +55,247 @@ The following hyperparameters were used during training:
|
|
55 |
- Transformers 4.38.0
|
56 |
- Pytorch 2.2.2+cu121
|
57 |
- Datasets 2.18.0
|
58 |
-
- Tokenizers 0.15.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
- Transformers 4.38.0
|
56 |
- Pytorch 2.2.2+cu121
|
57 |
- Datasets 2.18.0
|
58 |
+
- Tokenizers 0.15.2
|
59 |
+
|
60 |
+
<! --- ############################################################## ----->
|
61 |
+
<!--
|
62 |
+
Esta plantilla de Model Card es una adaptación de la de Hugging Face: https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md
|
63 |
+
|
64 |
+
¿Cómo utilizar esta plantilla? Copia el contenido en el README.md del repo de tu modelo en el Hub de Hugging Face y rellena cada sección.
|
65 |
+
|
66 |
+
Para más información sobre cómo rellenar cada sección ver las docs: https://huggingface.co/docs/hub/model-cards
|
67 |
+
-->
|
68 |
+
|
69 |
+
# Model Card for < Nombre del modelo >
|
70 |
+
|
71 |
+
<!-- Suele haber un nombre corto ("pretty name") para las URLs, tablas y demás y uno largo más descriptivo. Para crear el pretty name podéis utilizar acrónimos. -->
|
72 |
+
|
73 |
+
<!-- Resumen del modelo y motivación del proyecto (inc. los ODS relacionados). Esta sección es como el abstract. También se puede incluir aquí el logo del proyecto. -->
|
74 |
+
|
75 |
+
<!-- Si queréis incluir una versión de la Dataset Card en español, enlazarla aquí al principio (e.g. `README_es.md`).-->
|
76 |
+
|
77 |
+
## Model Details
|
78 |
+
|
79 |
+
### Model Description
|
80 |
+
|
81 |
+
<!-- Resumen del modelo. -->
|
82 |
+
|
83 |
+
- **Developed by:** [More Information Needed] <!-- Nombre de los miembros del equipo -->
|
84 |
+
- **Funded by:** SomosNLP, HuggingFace <!-- Si contasteis con apoyo de otra entidad (e.g. vuestra universidad), añadidla aquí -->
|
85 |
+
- **Model type:** Language model, instruction tuned
|
86 |
+
- **Language(s):** [More Information Needed] <!-- Enumerar las lenguas en las que se ha entrenado el modelo, especificando el país de origen. Utilizar códigos ISO. Por ejemplo: Spanish (`es-CL`, `es-ES`, `es-MX`), Catalan (`ca`), Quechua (`qu`). -->
|
87 |
+
- **License:** apache-2.0 <!-- Elegid una licencia lo más permisiva posible teniendo en cuenta la licencia del model pre-entrenado y los datasets utilizados -->
|
88 |
+
- **Fine-tuned from model:** [More Information Needed] <!-- Enlace al modelo pre-entrenado que habéis utilizado como base -->
|
89 |
+
- **Dataset used:** [More Information Needed] <!-- Enlace al dataset utilizado para el ajuste -->
|
90 |
+
|
91 |
+
### Model Sources
|
92 |
+
|
93 |
+
- **Repository:** [More Information Needed] <!-- Enlace al `main` del repo donde tengáis los scripts, i.e.: o del mismo repo del modelo en HuggingFace o a GitHub. -->
|
94 |
+
- **Paper:** [optional] [More Information Needed] <!-- Si vais a presentarlo a NAACL poned "WIP", "Comming soon!" o similar. Si no tenéis intención de presentarlo a ninguna conferencia ni escribir un preprint, eliminar. -->
|
95 |
+
- **Demo:** [More Information Needed] <!-- Enlace a la demo -->
|
96 |
+
- **Video presentation:** [optional] [More Information Needed] <!-- Enlace a vuestro vídeo de presentación en YouTube (están todos subidos aquí: https://www.youtube.com/playlist?list=PLTA-KAy8nxaASMwEUWkkTfMaDxWBxn-8J) -->
|
97 |
+
|
98 |
+
### Model Family [optional]
|
99 |
+
|
100 |
+
<!-- Si habéis entrenado varios modelos similares podéis enumerarlos aquí. -->
|
101 |
+
|
102 |
+
## Uses
|
103 |
+
|
104 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
105 |
+
|
106 |
+
### Direct Use
|
107 |
+
|
108 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
109 |
+
|
110 |
+
[More Information Needed]
|
111 |
+
|
112 |
+
### Downstream Use [optional]
|
113 |
+
|
114 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
115 |
+
|
116 |
+
[More Information Needed]
|
117 |
+
|
118 |
+
### Out-of-Scope Use
|
119 |
+
|
120 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
121 |
+
|
122 |
+
[More Information Needed]
|
123 |
+
|
124 |
+
## Bias, Risks, and Limitations
|
125 |
+
|
126 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
### Recommendations
|
131 |
+
|
132 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
133 |
+
|
134 |
+
<!-- Example: Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. -->
|
135 |
+
|
136 |
+
## How to Get Started with the Model
|
137 |
+
|
138 |
+
Use the code below to get started with the model.
|
139 |
+
|
140 |
+
```
|
141 |
+
|
142 |
+
[More Information Needed]
|
143 |
+
|
144 |
+
```
|
145 |
+
|
146 |
+
## Training Details
|
147 |
+
|
148 |
+
### Training Data
|
149 |
+
|
150 |
+
<!-- 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. -->
|
151 |
+
|
152 |
+
[More Information Needed]
|
153 |
+
|
154 |
+
### Training Procedure
|
155 |
+
|
156 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
157 |
+
|
158 |
+
<!-- Detallar la técnica de entrenamiento utilizada y enlazar los scripts/notebooks. -->
|
159 |
+
|
160 |
+
#### Preprocessing [optional]
|
161 |
+
|
162 |
+
[More Information Needed]
|
163 |
+
|
164 |
+
#### Training Hyperparameters
|
165 |
+
|
166 |
+
<!-- Enumerar los valores de los hiperparámetros de entrenamiento. -->
|
167 |
+
|
168 |
+
- **Training regime:** <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
169 |
+
|
170 |
+
#### Speeds, Sizes, Times [optional]
|
171 |
+
|
172 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
173 |
+
|
174 |
+
[More Information Needed]
|
175 |
+
|
176 |
+
## Evaluation
|
177 |
+
|
178 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
179 |
+
|
180 |
+
### Testing Data, Factors & Metrics
|
181 |
+
|
182 |
+
#### Testing Data
|
183 |
+
|
184 |
+
<!-- This should link to a Dataset Card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
#### Factors
|
189 |
+
|
190 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
191 |
+
|
192 |
+
[More Information Needed]
|
193 |
+
|
194 |
+
#### Metrics
|
195 |
+
|
196 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
### Results
|
201 |
+
|
202 |
+
<!-- Enlazar aquí los scripts/notebooks de evaluación y especificar los resultados. -->
|
203 |
+
|
204 |
+
[More Information Needed]
|
205 |
+
|
206 |
+
## Model Examination [optional]
|
207 |
+
|
208 |
+
<!-- Relevant interpretability work for the model goes here. -->
|
209 |
+
|
210 |
+
[More Information Needed]
|
211 |
+
|
212 |
+
## Environmental Impact
|
213 |
+
|
214 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly. -->
|
215 |
+
|
216 |
+
<!-- Rellenar la información de la lista y calcular las emisiones con la página mencionada. -->
|
217 |
+
|
218 |
+
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).
|
219 |
+
|
220 |
+
- **Hardware Type:** [More Information Needed]
|
221 |
+
- **Hours used:** [More Information Needed]
|
222 |
+
- **Cloud Provider:** [More Information Needed]
|
223 |
+
- **Compute Region:** [More Information Needed]
|
224 |
+
- **Carbon Emitted:** [More Information Needed]
|
225 |
+
|
226 |
+
## Technical Specifications [optional]
|
227 |
+
|
228 |
+
<!-- Esta sección es opcional porque seguramente ya habéis mencionado estos detalles más arriba, igualmente está bien incluirlos aquí de nuevo como bullet points a modo de resumen. -->
|
229 |
+
|
230 |
+
### Model Architecture and Objective
|
231 |
+
|
232 |
+
[More Information Needed]
|
233 |
+
|
234 |
+
### Compute Infrastructure
|
235 |
+
|
236 |
+
[More Information Needed]
|
237 |
+
|
238 |
+
#### Hardware
|
239 |
+
|
240 |
+
<!-- Indicar el hardware utilizado, podéis agradecer aquí a quien lo patrocinó. -->
|
241 |
+
|
242 |
+
[More Information Needed]
|
243 |
+
|
244 |
+
#### Software
|
245 |
+
|
246 |
+
<!-- Enumerar las librerías utilizadas (e.g. transformers, distilabel). -->
|
247 |
+
|
248 |
+
[More Information Needed]
|
249 |
+
|
250 |
+
## License
|
251 |
+
|
252 |
+
<!-- Indicar bajo qué licencia se libera el modelo explicando, si no es apache 2.0, a qué se debe la licencia más restrictiva (i.e. herencia de las licencias del modelo pre-entrenado o de los datos utilizados). -->
|
253 |
+
|
254 |
+
## Citation
|
255 |
+
|
256 |
+
**BibTeX:**
|
257 |
+
|
258 |
+
[More Information Needed]
|
259 |
+
|
260 |
+
<!--
|
261 |
+
|
262 |
+
Aquí tenéis un ejemplo de cita de un dataset que podéis adaptar:
|
263 |
+
|
264 |
+
```
|
265 |
+
@software{benallal2024cosmopedia,
|
266 |
+
author = {Ben Allal, Loubna and Lozhkov, Anton and Penedo, Guilherme and Wolf, Thomas and von Werra, Leandro},
|
267 |
+
title = {Cosmopedia},
|
268 |
+
month = February,
|
269 |
+
year = 2024,
|
270 |
+
url = {https://huggingface.co/datasets/HuggingFaceTB/cosmopedia}
|
271 |
+
}
|
272 |
+
```
|
273 |
+
|
274 |
+
- benallal2024cosmopedia -> nombre + año + nombre del modelo
|
275 |
+
- author: lista de miembros del equipo
|
276 |
+
- title: nombre del modelo
|
277 |
+
- year: año
|
278 |
+
- url: enlace al modelo
|
279 |
+
|
280 |
+
-->
|
281 |
+
|
282 |
+
## Glossary [optional]
|
283 |
+
|
284 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
285 |
+
|
286 |
+
## More Information
|
287 |
+
|
288 |
+
<!-- Indicar aquí que el marco en el que se desarrolló el proyecto, en esta sección podéis incluir agradecimientos y más información sobre los miembros del equipo. Podéis adaptar el ejemplo a vuestro gusto. -->
|
289 |
+
|
290 |
+
This project was developed during the [Hackathon #Somos600M](https://somosnlp.org/hackathon) organized by SomosNLP. The model was trained using GPUs sponsored by HuggingFace.
|
291 |
+
|
292 |
+
**Team:** [More Information Needed]
|
293 |
+
|
294 |
+
<!--
|
295 |
+
- [Name 1](Link to Hugging Face profile)
|
296 |
+
- [Name 2](Link to Hugging Face profile)
|
297 |
+
-->
|
298 |
+
|
299 |
+
## Contact [optional]
|
300 |
+
|
301 |
+
<!-- Email de contacto para´posibles preguntas sobre el modelo. -->
|