arxiv:2502.18293
Taneesh Gupta
gupta-tanish
·
AI & ML interests
Post-Training @MicrosoftResearch
Recent Activity
updated
a dataset
about 2 hours ago
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked-new
updated
a dataset
about 2 hours ago
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked-old
published
a dataset
about 2 hours ago
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked-old
Organizations
models
25
gupta-tanish/llama-3-8b-instruct-refa-budget_length-256-lamda-1.0-iteration2
Text Generation
•
Updated
•
16
gupta-tanish/llama-3-8b-instruct-refa-budget_length-256-lamda-20.0-iteration1
Text Generation
•
Updated
•
54
gupta-tanish/llama-3-8b-instruct-refa-lr-1e-6-beta10-gamma4-lambda-1.0-eos-increase-iteration2-lamda-0.1
Text Generation
•
Updated
•
59
gupta-tanish/llama-3-8b-instruct-refa-lr-1e-6-beta10-gamma4-lambda-0.1-eos-increase-iteration2
Text Generation
•
Updated
•
43
gupta-tanish/llama3-8b-instruct-refa-eos-increase-lamda-0.001-lr-1e-6-iteration1
Text Generation
•
Updated
•
89
gupta-tanish/llama3-8b-instruct-refa-eos-increase-lamda-0.01-lr-1e-6-iteration1
Text Generation
•
Updated
•
46
gupta-tanish/llama3-8b-instruct-refa-eos-increase-lamda-0.1-lr-1e-6-iteration1
Text Generation
•
Updated
•
44
gupta-tanish/llama3-8b-instruct-refa-eos-increase-lamda-1.0-lr-1e-6-iteration1
Text Generation
•
Updated
•
60
gupta-tanish/mistral-7b-instruct-refa-iteration2
Text Generation
•
Updated
•
147
gupta-tanish/mistral-7b-instruct-refa-iteration1
Text Generation
•
Updated
•
30
datasets
119
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked-new
Viewer
•
Updated
•
12.9k
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked-old
Viewer
•
Updated
•
31.1k
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-masked
Viewer
•
Updated
•
33.5k
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation
Viewer
•
Updated
•
41.5k
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-training-data-iteration2
Viewer
•
Updated
•
200
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-training-data-Step-MPO
Viewer
•
Updated
•
8.8k
•
9
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-training-data
Viewer
•
Updated
•
9.05k
•
51
gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-logps
Viewer
•
Updated
•
4.32k
•
39
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-pertubation-generation-logps
Viewer
•
Updated
•
41.5k
•
41
gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-on-policy-alignment-pertubation-generation-logps
Viewer
•
Updated
•
38
•
46