Eklav checkpoints for math reasoning, plus the CotGen baseline for comparison. Same base model and data, different training method.
Adarsh Singh
AdarshSingh7647
AI & ML interests
Information Retrieval over structured data and retrieval-augmented question answering. Focuses on retrieval, reranking, and representation learning methods that enable robust and scalable reasoning over structured data.
Recent Activity
updated a model 3 days ago
AdarshSingh7647/TabRankMultiTableCoTCond published a model 3 days ago
AdarshSingh7647/TabRankMultiTableCoTCond updated a model 3 days ago
AdarshSingh7647/TabRankMultiTableCoTGenOrganizations
None yet
Eklav: hint conditioned CoT distillation. See the Passage Reranking and Math Reasoning collections below for task specific checkpoints.
Qwen3-8B listwise table rerankers (arXiv:2607.25182). 3 variants: Naive (fast), Standard SFT (reasoning), TabRank (best). Start with TabRank.
Eklav checkpoints for passage reranking (BRIGHT, NevIR), plus the CotGen baseline for comparison. Same base model and data, different training method.
-
AdarshSingh7647/Eklav-0.6B-Reranker
Text Generation • 0.6B • Updated • 341 -
AdarshSingh7647/Eklav-0.6B-Reranker-CotGen
Text Generation • 0.6B • Updated • 357 -
AdarshSingh7647/Eklav-4B-Reranker
Text Generation • 4B • Updated • 341 -
AdarshSingh7647/Eklav-4B-Reranker-CotGen
Text Generation • 4B • Updated • 336
Data generated as augmentations to NQ-Tables and OTT-QA for Table Retrieval
Eklav checkpoints for math reasoning, plus the CotGen baseline for comparison. Same base model and data, different training method.
Eklav checkpoints for passage reranking (BRIGHT, NevIR), plus the CotGen baseline for comparison. Same base model and data, different training method.
-
AdarshSingh7647/Eklav-0.6B-Reranker
Text Generation • 0.6B • Updated • 341 -
AdarshSingh7647/Eklav-0.6B-Reranker-CotGen
Text Generation • 0.6B • Updated • 357 -
AdarshSingh7647/Eklav-4B-Reranker
Text Generation • 4B • Updated • 341 -
AdarshSingh7647/Eklav-4B-Reranker-CotGen
Text Generation • 4B • Updated • 336
Eklav: hint conditioned CoT distillation. See the Passage Reranking and Math Reasoning collections below for task specific checkpoints.
Data generated as augmentations to NQ-Tables and OTT-QA for Table Retrieval
Qwen3-8B listwise table rerankers (arXiv:2607.25182). 3 variants: Naive (fast), Standard SFT (reasoning), TabRank (best). Start with TabRank.