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 dataset about 12 hours ago
omniagentbench/OmniAgentBench published a dataset about 12 hours ago
omniagentbench/OmniAgentBench updated a collection about 12 hours ago
SAGA: Syntax-Aligned Grammar AdaptationOrganizations
models 12
Hodfa71/gpt-sw3-356m-is-saga-delta-dpo
Text Generation • 0.4B • Updated
Hodfa71/viking-13b-is-saga-delta-dpo
Text Generation • Updated • 3
Hodfa71/gpt-sw3-1b3-is-saga-delta-dpo
Text Generation • Updated • 1
Hodfa71/viking-13b-da-saga-delta-dpo
Text Generation • Updated • 3
Hodfa71/gpt-sw3-1b3-da-saga-delta-dpo
Text Generation • Updated • 2
Hodfa71/gpt-sw3-356m-da-saga-delta-dpo
Text Generation • Updated • 3
Hodfa71/gpt-sw3-356m-icelandic-delta-dpo
Text Generation • 0.4B • Updated
Hodfa71/gpt-sw3-1b3-icelandic-delta-dpo
Text Generation • Updated • 12
Hodfa71/deepface-weights
Updated
Hodfa71/olmo-7b-lume-pstu-trim
7B • Updated • 12
datasets 7
Hodfa71/OmniAgentBench
Viewer • Updated • 30
Hodfa71/OmniAgentBench-Audio
Viewer • Updated • 30 • 9
Hodfa71/saga-da-delta-dpo-r1
Viewer • Updated • 7.41k • 18
Hodfa71/saga-da-delta-dpo-r2
Viewer • Updated • 7.31k • 22
Hodfa71/pstu-synthetic-secrets
Viewer • Updated • 175 • 30
Hodfa71/NER-German
Preview • Updated • 17
Hodfa71/distill-and-forget-data
Viewer • Updated • 1.18M • 10