WELCOME TO CARVALHOCHAT 4
The CarvalhoChat 4 is the fourth of the CarvalhoChat models, obtained via FFT on the base model Nos-PT/Llama-Carvalho-PT-GL with the objective of creating a Galician chatbot.
This particular version has a context window of 8192 tokens and was trained on the following datasets:
- OASST2
- DOLLY
- PERSOAS GALICIAN
- DATABRICKS DOLLY
- NANOORCA
- MULTITURN GALEGU
- WIKISUM
More versions with longer context lengths and more training data are on their way, so stay tuned!
Funding and acknowledgements
This work is funded by the Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the project Desarrollo de Modelos ALIA.
- Downloads last month
- 273