Auxiliary datasets for tmax.
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a model about 9 hours ago
hamishivi/vip-dolci-if-grpo-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b published a model about 9 hours ago
hamishivi/vip-dolci-if-grpo-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b updated a model 1 day ago
hamishivi/vip-dolci-if-sae-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4bOrganizations
Models for "RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments" - https://arxiv.org/abs/2511.07317
-
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
Paper • 2511.07317 • Published • 18 -
hamishivi/OpenThinker3-1.5B-RLVE
Text Generation • 2B • Updated • 20 • 2 -
hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE
Text Generation • 2B • Updated • 11 • 3
Auxiliary datasets for tmax.
Models for "RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments" - https://arxiv.org/abs/2511.07317
-
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
Paper • 2511.07317 • Published • 18 -
hamishivi/OpenThinker3-1.5B-RLVE
Text Generation • 2B • Updated • 20 • 2 -
hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE
Text Generation • 2B • Updated • 11 • 3
models 346
hamishivi/vip-dolci-if-grpo-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b
Updated • 1
hamishivi/vip-dolci-if-sae-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b
Updated • 107
hamishivi/vip-dolci-if-sae-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b
Updated • 32
hamishivi/vip-dolci-if-grpo-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b
Updated • 236
hamishivi/vip-grpo-centered-g8-p32-as-zvf-tis2-restart-qwen3-4b-math
Updated • 10
hamishivi/vip-grpo-centered-g8-p32-as-zvf-tis2-qwen3-4b-math
Updated • 1
hamishivi/vip-g8-p32-mse-ap-as-zvf-tis2-vlr2-qwen3-4b-math
Updated • 20
hamishivi/vip-g8-p32-mse-ap-as-zvf-tis2-qwen3-4b-math
Updated • 9
hamishivi/vip-g8-p32-mse-ap-as-zvf-qwen3-4b-math
Reinforcement Learning • Updated • 11
hamishivi/vip-g8-p32-cls-ap-as-zvf-qwen3-4b-math
Text Generation • Updated • 2
datasets 228
hamishivi/qwen35-4b-drpo-vs0f49th-trainer-logprobs
Viewer • Updated • 56.3k • 404
hamishivi/tmax-sft-big
Viewer • Updated • 327k • 41
hamishivi/agent-task-endless-terminals
Viewer • Updated • 2.49k • 26
hamishivi/sft_ablations_scientific_minimax_v1_sanitized
Viewer • Updated • 2.23k • 18
hamishivi/sft_ablations_bc_only_v1_sanitized
Viewer • Updated • 5.59k • 33
hamishivi/agent-task-cli-gym
Viewer • Updated • 1.55k • 48
hamishivi/agent-task-swe-smith
Viewer • Updated • 59.1k • 32
hamishivi/agent-task-r2e-gym
Viewer • Updated • 4.58k • 9
hamishivi/agent-task-combined
Viewer • Updated • 27k • 349
hamishivi/sft_ablations_redsearcher_sft_sanitized
Viewer • Updated • 9.81k • 34