Ori/gpqa_experiment_gold_sft_explanations_0
Updated
Yoran PRO
Ori
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Self-Execution Simulation Improves Coding Models upvoted a paper 4 months ago
CWM: An Open-Weights LLM for Research on Code Generation with World
Models upvoted a paper 7 months ago
Set Block Decoding is a Language Model Inference AcceleratorOrganizations
Ori/test_model
Updated
Ori/lama-2-13b-peft-ret-mix-seed-1
Updated • 3
Ori/lama-2-13b-peft-no-ret-seed-1
Updated • 3
Ori/lama-2-13b-peft-mh-at-1-v2-seed-1
Updated • 3
Ori/lama-2-13b-peft-mh-at-1-v2-seed-2
Updated • 5
Ori/lama-2-13b-peft-mh-at-1-v2-seed-3
Updated • 3
Ori/lama-2-13b-peft-mh-ret-mix-v2-seed-3
Updated • 3
Ori/lama-2-13b-peft-mh-ret-mix-v2-seed-2
Updated • 3
Ori/lama-2-13b-peft-mh-no-ret-v2-seed-2
Updated • 3
Ori/lama-2-13b-peft-mh-no-ret-v2-seed-3
Updated • 1
Ori/lama-2-13b-peft-nq-with-ret-at-1
Updated • 4
Ori/lama-2-13b-peft-nq-with-ret-at-1-v2-seed-3
Updated • 5
Ori/lama-2-13b-peft-nq-with-ret-mix-v2-seed-3
Updated • 3
Ori/llama-2-13b-peft-nq-retrobust
Updated • 5 • 1
Ori/lama-2-13b-peft-nq-no-ret-v2-seed-3
Updated • 3
Ori/lama-2-13b-peft-nq-no-ret-v2-seed-2
Updated • 3
Ori/lama-2-13b-peft-2wikihop-with-ret-at-1-v2-seed-3
Updated • 3
Ori/llama-2-13b-peft-2wikihop-with-ret-at-1
Updated • 4
Ori/lama-2-13b-peft-2wikihop-with-ret-mix-v2-seed-3
Updated • 2
Ori/llama-2-13b-peft-2wikihop-retrobust
Updated • 4
Ori/lama-2-13b-peft-2wikihop-no-ret-v2-seed-3
Updated • 2
Ori/llama-2-13b-peft-2wikihop-no-ret
Updated • 3
Ori/lama-2-13b-peft-strategyqa-with-retrieval-at-1-v2-seed-3
Updated • 3
Ori/llama-2-13b-peft-strategyqa-with-ret-at-1
Updated • 3 • 1
Ori/lama-2-13b-peft-strategyqa-with-retrieval-mix-v2-seed-3
Updated • 3
Ori/llama-2-13b-peft-strategyqa-retrobust
Updated • 4
Ori/lama-2-13b-peft-strategyqa-no-retrieval-1-v2-seed-3
Updated • 3
Ori/llama-2-13b-peft-strategyqa-no-ret
Updated • 3
Ori/lama-2-13b-peft-mh-retrieval-mix-v2-seed-0
Updated • 3