Adapted models to the low-resource Spanish-Valencian (ES-VLCA) direction using supervised fine-tuning (SFT) and GRPO
Paula Guerrero Castelló
guerreropaula
·
AI & ML interests
NLP, MT & AI
Organizations
models 9
guerreropaula/translategemma4b-sft-es-va
Translation • Updated
guerreropaula/translategemma4b-grpov2-es-va
Translation • 4B • Updated • 11
guerreropaula/translategemma4b-grpov1-es-va
Translation • 4B • Updated • 21
guerreropaula/ht_mt_classifier_best
Text Classification • 0.1B • Updated • 16
guerreropaula/nllb-spa-ast-lorav2
Updated
guerreropaula/nllb-spa-ast-lora2
Updated
guerreropaula/qwen-clinical-merged
Image-Text-to-Text • 0.9B • Updated • 14
guerreropaula/llama_sent_finetuned
Updated
guerreropaula/translategemma4b_grpo_final_merged
Image-Text-to-Text • 4B • Updated • 13