Flan_large_full_FT Fully finetune on Q, V (enc, dec, cross) matrices Speeeed/Flan_large_finance_full_ft 0.8B • Updated Jan 19, 2025 • 3
LLAMA-3.2-3B-Instruct-LoRA-GLUE-QA Finetuning using LoRA with rank 16, on GLUE and SuperGlue datasets. Speeeed/Llama-3.2-3B-instruct-sst2-lora Updated Dec 7, 2024 Speeeed/Llama-3.2-3B-instruct-mrpc-lora Updated Dec 7, 2024 Speeeed/Llama-3.2-3B-instruct-wic-lora Updated Dec 7, 2024 Speeeed/Llama-3.2-3B-instruct-cola-lora Updated Dec 7, 2024
LLAMA-3.2-3B-Instruct-LoRA-Generation Finetuning Llama on summarization/translation tasks using LoRA with rank set to 16. Speeeed/Llama-3.2-3B-instruct-samsum-lora Updated Dec 7, 2024
Flan_large_full_FT Fully finetune on Q, V (enc, dec, cross) matrices Speeeed/Flan_large_finance_full_ft 0.8B • Updated Jan 19, 2025 • 3
LLAMA-3.2-3B-Instruct-LoRA-Generation Finetuning Llama on summarization/translation tasks using LoRA with rank set to 16. Speeeed/Llama-3.2-3B-instruct-samsum-lora Updated Dec 7, 2024
LLAMA-3.2-3B-Instruct-LoRA-GLUE-QA Finetuning using LoRA with rank 16, on GLUE and SuperGlue datasets. Speeeed/Llama-3.2-3B-instruct-sst2-lora Updated Dec 7, 2024 Speeeed/Llama-3.2-3B-instruct-mrpc-lora Updated Dec 7, 2024 Speeeed/Llama-3.2-3B-instruct-wic-lora Updated Dec 7, 2024 Speeeed/Llama-3.2-3B-instruct-cola-lora Updated Dec 7, 2024
