Complete set of Llama-3.1-8B LoRA adapters (40 SFT + 36 DPO) trained on OpenAssistant to imitate other models.
-
dementor-research/oasst-gpt-oss-20b-as-gpt-oss-20b-sft-seed42
Text Generation • Updated • 13 -
dementor-research/oasst-gpt-oss-20b-as-llama-3.1-8b-sft-seed42
Text Generation • Updated • 22 -
dementor-research/oasst-gpt-oss-20b-as-llama-3.1-8b-sft-seed43
Text Generation • Updated • 21 -
dementor-research/oasst-gpt-oss-20b-as-llama-3.1-8b-sft-seed44
Text Generation • Updated • 22