Puria Radmard

geodesic-puria's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 1 month ago

geodesic-research/nemotron_120b_warm_start_sft_200k_instruct

Text Generation • 124B • Updated Apr 28 • 184 • 1

liked 2 models about 2 months ago

geodesic-research/nemotron_120b_sft_warm_start_200k

124B • Updated Apr 14 • 287 • 1

geodesic-research/nemotron_super_sft_warm_start_66k

124B • Updated Apr 13 • 1 • 1

updated a model about 2 months ago

geodesic-puria/nemotron-nano-30b-sorh-100k-no-instruct-no-cot-reward-lora

Updated Apr 12

published 3 models about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-16k-no-cot-reward-lora

Updated Apr 12

geodesic-puria/nemotron-nano-30b-sorh-100k-no-instruct-no-cot-reward-lora

Updated Apr 12

geodesic-puria/nemotron-nano-30b-sorh-100k-no-instruct-lora

Updated Apr 12

updated a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-short-cot-16k-warmstart-lora

Updated Apr 12 • 1

published a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-short-cot-16k-warmstart-lora

Updated Apr 12 • 1

updated a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-band-cot-16k-warmstart-lora

Updated Apr 11

published a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-band-cot-16k-warmstart-lora

Updated Apr 11

updated a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-cot-penalty-lora

Updated Apr 11

published a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-cot-penalty-lora

Updated Apr 11

updated a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-reward-hack-lora

Updated Apr 11

published a model about 2 months ago

geodesic-puria/nemotron-nano-30b-mbpp-reward-hack-lora

Updated Apr 11

liked 4 models about 2 months ago

geodesic-research/nemotron_nano_sft_warm_start_1150

Text Generation • 32B • Updated Apr 9 • 3 • 1

geodesic-research/nemotron_nano_sft_warm_start_16k

Text Generation • 32B • Updated Apr 9 • 2 • 1

geodesic-research/nemotron_nano_sft_warm_start_100k

Text Generation • 32B • Updated Apr 9 • 2 • 1

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16

Text Generation • 124B • Updated Mar 14 • 21.1k • 30

upvoted a collection 2 months ago

(Some) Emergent Misalignment from Reward Hacking in RL

Collection

Model checkpoints from the project "(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL" • 228 items • Updated 17 days ago • 5