hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_31605_no_cite__1__1762677729_checkpoints_step_1700
8B • Updated
• 1
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated
a model 1 day ago
hamishivi/step500_test published
a model 1 day ago
hamishivi/step500_test updated
a dataset 4 days ago
hamishivi/rlenv-appworld-eval-nothink Organizations
hamishivi/1011_rl_rag_open_judge_no_citation_1037__1__1762832496_checkpoints_step_850
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step600
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step600
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step600
8B • Updated
hamishivi/1810_rl_rag_NAR8_onpolicy_step600
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_31605_no_cite_step1000
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step750
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_no_cite_step900
8B • Updated
• 2
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step900
Updated
hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE
Text Generation • 2B • Updated
• 2 • 2
hamishivi/OpenThinker3-1.5B-RLVE
Text Generation • 2B • Updated
• 2 • 2
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_31605_no_cite_step_750
8B • Updated
• 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step_750
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step700
8B • Updated
• 3
hamishivi/1810_rl_rag_NAR8_onpolicy_step750
Updated
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step400
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step200
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step100
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step400
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step200
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step100
8B • Updated
hamishivi/1810_rl_rag_NAR8_onpolicy_step400
8B • Updated
hamishivi/1810_rl_rag_NAR8_onpolicy_step200
8B • Updated
hamishivi/1810_rl_rag_NAR8_onpolicy_step100
8B • Updated
• 2
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step400
8B • Updated
• 2
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step200
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step100
8B • Updated
hamishivi/1810_rl_rag_NAR8_onpolicy_step650
8B • Updated
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step650
8B • Updated
• 5