gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-single-position-regex-perturbation
Viewer • Updated • 204k • 3
Taneesh Gupta
gupta-tanish
·
AI & ML interests
Post-Training @MicrosoftResearch
Organizations
None yet
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Qwen2.5-7B-model-pertubation-generation-margin-20
Viewer • Updated • 56.3k • 3
gupta-tanish/QwQ-Long-CoT-10k-subset-Qwen2.5-7B-Instruct-model-pertubation-generation
Viewer • Updated • 62.7k • 3
gupta-tanish/QwQ-Long-CoT-10k-subset-Qwen2.5-7B-Instruct-on-policy-alignment-pertubation-generation
Viewer • Updated • 79.8k • 2
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-regex-perturbation-generation
Viewer • Updated • 929 • 3
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-model-dynamic-perturbation-generation
Viewer • Updated • 20 • 3
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-model-pertubation-generation-masked-logp30
Viewer • Updated • 40.1k • 1
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-model-pertubation-generation-masked-new
Viewer • Updated • 37.3k • 3
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-model-pertubation-generation-masked
Viewer • Updated • 10.1k • 3
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked-new
Viewer • Updated • 12.9k • 2
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked-old
Viewer • Updated • 31.1k • 2
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked
Viewer • Updated • 33.5k • 2
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation
Viewer • Updated • 41.5k • 2
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-training-data-iteration2
Viewer • Updated • 200 • 2
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-training-data-Step-MPO
Viewer • Updated • 8.8k • 2
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-training-data
Viewer • Updated • 9.05k • 2
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-logps
Viewer • Updated • 4.32k • 2
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-logps
Viewer • Updated • 41.5k • 2
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-on-policy-alignment-pertubation-generation-logps
Viewer • Updated • 38 • 2
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-on-policy-alignment-pertubation-generation
Viewer • Updated • 41.4k • 2
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-on-policy-alignment-pertubation-generation-full
Viewer • Updated • 43.6k • 2
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-on-policy-alignment-pertubation-generation
Viewer • Updated • 412 • 2
gupta-tanish/llama-3-8b-instruct-refa-budget_length-256-lamda-1.0-iteration3
Viewer • Updated • 21k • 3
gupta-tanish/llama-3-8b-instruct-refa-budget_length-256-lamda-20.0-iteration2
Viewer • Updated • 21k • 3
gupta-tanish/llama-3-8b-instruct-refa-budget_length-300-lamda-20.0-iteration1
Viewer • Updated • 200 • 3
gupta-tanish/llama3-8b-instruct-on-policy-refa-eos-increase-lambda-1.0-lr-1e-6-iteration3-train-data
Viewer • Updated • 21k • 3
gupta-tanish/llama3-8b-instruct-on-policy-refa-eos-increase-lambda-0.1-lr-1e-6-iteration3-train-data
Viewer • Updated • 21k • 3
gupta-tanish/llama3-8b-instruct-on-policy-refa-eos-increase-lambda-0.01-lr-1e-6-iteration2-train-data
Viewer • Updated • 21k • 3
gupta-tanish/llama3-8b-instruct-on-policy-refa-eos-increase-lambda-0.1-lr-1e-6-iteration2-train-data
Viewer • Updated • 21k • 3
gupta-tanish/llama3-8b-instruct-on-policy-refa-eos-increase-lambda-1.0-lr-1e-6-iteration2-train-data
Viewer • Updated • 21k • 3