AI & ML interests
ML & NLP
Organizations
None yet
martimfasantos/sft-xcomet_xl_xxl-chosen-10lp-shuff-full-tiny2
Text Generation
• 1B • Updated • 3
martimfasantos/sft-sum-chosen-10lp-shuff-full-tiny
Summarization
• 1B • Updated martimfasantos/dpo-xcomet_xl_xxl-10p-shuff-5e-7-full-from-sft-tiny
Text Generation
• 1B • Updated martimfasantos/sft-xcomet_xl_xxl-chosen-10lp-shuff-full-tiny
Text Generation
• 1B • Updated • 1
martimfasantos/tinyllama-1.1b-mt-sft-full_sardine2
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-dpo-full_LR1e-7_BS32_rmsprop_3epochs_sft_sardine_dpo_sardine
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-sft-full_sardine
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR1e-7_BS32_rmsprop_3epochs_compare
Text Generation
• 1B • Updated • 1
martimfasantos/tinyllama-1.1b-mt-dpo-full_LR1e-7_BS32_rmsprop_3epochs_compare
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_rmsprop_2epochs_new
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-sft-full_new
Text Generation
• 1B • Updated • 2
martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-7_BS32_rmsprop_3epochs_test
Text Generation
• 1B • Updated • 3
martimfasantos/tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR5e-8_BS16_rmsprop_2epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR5e-8_BS16_adamw_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR5e-8_BS16_rmsprop_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-simpo_beta2.0_gamma1.0_LR5e-8_BS16_rmsprop_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-simpo_beta2.0_gamma1.0_LR5e-8_BS16_adamw_3epochs
Text Generation
• 1B • Updated • 1
• 1
martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_rmsprop_2epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_rmsprop_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_2epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_2epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-sum-dpo-full_LR5e-8_2epochs_BS4_old
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-sum-dpo-full_LR5e-8_2epochs_maxtarget64_old
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-sum-simpo_beta2.0_gamma1.6_LR5e-8_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-sum-simpo_beta1.0_gamma0.8_LR5e-8_3epochs
Text Generation
• 1B • Updated • 1
martimfasantos/tinyllama-1.1b-sum-sft-full_3epochs
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-sum-sft-full_LR4e-5
Text Generation
• 1B • Updated martimfasantos/tinyllama-1.1b-sum-sft-full_v1.1
Text Generation
• 1B • Updated