RLVF pipeline using parser oracles to align LMs for Icelandic and Danish. GPT-SW3 and Viking-13B trained with Delta-DPO.
Fakhar
Hodfa71
AI & ML interests
None yet
Recent Activity
updated a Space 3 days ago
TrustLLMeu/saga-annotation published a Space 9 days ago
TrustLLMeu/saga-annotation updated a dataset 14 days ago
omniagentbench/OmniAgentBenchOrganizations
