arvindcr4/trl_qwen3_8b-grpo-gsm8k
Updated
Arvind Rajasekaran
arvindcr4
AI & ML interests
None yet
Recent Activity
new activity 6 days ago
AfterQuery/App-Bench:AppBench reproducibility: licence, official harness, and grading protocol new activity 6 days ago
ai-safety-institute/AgentHarm:Held-out (test_private) split access request updated a model 25 days ago
arvindcr4/pavlov-portfolio-qwen36-seed809-stepfinal-tinker-cf0ad8c1-1f1b-5ff-9f777c4018b6Organizations
arvindcr4/trl_llama32_3b-grpo-gsm8k
Updated
arvindcr4/trl_llama32_1b-grpo-gsm8k
Updated
arvindcr4/tinker-rl-bench-arch_gsm8k_kimi-k2
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-arch_gsm8k_gpt-oss-20b
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-scale_gsm8k_llama-8b-inst
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-cross_tool_qwen3-32b
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-scale_gsm8k_qwen3.5-4b
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-frontier_gsm8k_nemotron-120b
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-ppo_gsm8k_Qwen3-8B_s42
Text Generation • Updated • 3
arvindcr4/tinker-rl-bench-ppo_gsm8k_Llama-3.1-8B-Instruct_s42
Text Generation • Updated • 2
arvindcr4/tinker-rl-bench-kl_track_Qwen3-8B_s42
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-scale_gsm8k_qwen3-8b
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-frontier_gsm8k_deepseek-v3.1
Reinforcement Learning • Updated
arvindcr4/tinker-rl-bench-cross_tool_llama-8b-inst
Reinforcement Learning • Updated
arvindcr4/skyrl-tinker-qwen3-8b-tool_use
Updated • 1
arvindcr4/llama-3.2-1b-arithmetic-rl-lora
Reinforcement Learning • Updated • 2
arvindcr4/llama-3.2-1b-distillation-offpolicy-lora
Updated • 6
arvindcr4/tool-call-lora-qwen2.5-7b
Updated • 4
arvindcr4/tool-call-lora-qwen2.5-3b
Updated • 1
arvindcr4/tool-call-lora-qwen1.5b
Updated
arvindcr4/tool-call-lora-qwen0.5b
Updated