-
llama-3.1-8b-instruct-phactual_fp16_he20
Model finetuned starting with llama 3.1 8b using a full precision LoRA he20, rank 64, alpha 16
tools273 Pulls 1 Tag Updated 1 year ago
-
llama-3.1-8b-instruct-phactual_fp16
First test
tools7 Pulls 1 Tag Updated 1 year ago
-
llama_dpo
a finetuned Llama 3.1 8b model with supplementary DPO training
tools3 Pulls 1 Tag Updated 1 year ago