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 1 day ago
omniagentbench/OmniAgentBench updated a model 1 day ago
Hodfa71/gemma4-e4b-da-saga-delta-dpo published a model 1 day ago
Hodfa71/gemma4-e4b-da-saga-delta-dpoOrganizations
models 17
Hodfa71/gemma4-e4b-da-saga-delta-dpo
Text Generation • Updated • 4
Hodfa71/llama-3.1-8b-da-saga-delta-dpo
Text Generation • Updated • 4
Hodfa71/gemma4-e4b-is-saga-kl-sft-delta-dpo
Text Generation • Updated • 8
Hodfa71/llama-3.2-1b-is-saga-kl-sft-delta-dpo
Text Generation • Updated • 13
Hodfa71/llama-3.1-8b-is-saga-kl-sft-delta-dpo
Text Generation • Updated • 13
Hodfa71/gpt-sw3-356m-is-saga-delta-dpo
Text Generation • 0.4B • Updated
Hodfa71/viking-13b-is-saga-delta-dpo
Text Generation • Updated • 15
Hodfa71/gpt-sw3-1b3-is-saga-delta-dpo
Text Generation • Updated • 13
Hodfa71/viking-13b-da-saga-delta-dpo
Text Generation • Updated • 15
Hodfa71/gpt-sw3-1b3-da-saga-delta-dpo
Text Generation • Updated • 13
datasets 7
Hodfa71/OmniAgentBench
Viewer • Updated • 30 • 9
Hodfa71/OmniAgentBench-Audio
Viewer • Updated • 30 • 50
Hodfa71/saga-da-delta-dpo-r1
Viewer • Updated • 7.41k • 22
Hodfa71/saga-da-delta-dpo-r2
Viewer • Updated • 7.31k • 26
Hodfa71/pstu-synthetic-secrets
Viewer • Updated • 175 • 30
Hodfa71/NER-German
Preview • Updated • 20
Hodfa71/distill-and-forget-data
Viewer • Updated • 1.18M • 6