Hamish Ivison

hamishivi 's models 218

Sort:  Recently updated

hamishivi/2010_rl_rag_NAR8_testing64_base_model_step100

8B • Updated Nov 6, 2025 • 3

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step400

8B • Updated Nov 6, 2025 • 2

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step200

8B • Updated Nov 6, 2025 • 4

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step100

8B • Updated Nov 6, 2025 • 3

hamishivi/1810_rl_rag_NAR8_onpolicy_step400

8B • Updated Nov 6, 2025 • 3

hamishivi/1810_rl_rag_NAR8_onpolicy_step200

8B • Updated Nov 6, 2025 • 3

hamishivi/1810_rl_rag_NAR8_onpolicy_step100

8B • Updated Nov 6, 2025 • 3

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step400

8B • Updated Nov 6, 2025 • 4

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step200

8B • Updated Nov 6, 2025 • 4

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step100

8B • Updated Nov 6, 2025 • 2

hamishivi/1810_rl_rag_NAR8_onpolicy_step650

8B • Updated Nov 4, 2025 • 3

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step650

8B • Updated Nov 4, 2025 • 79

hamishivi/2010_rl_rag_NAR8_testing64_base_model_step500

8B • Updated Nov 1, 2025 • 3

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step500

8B • Updated Oct 31, 2025 • 3

hamishivi/1810_rl_rag_NAR8_onpolicy_step500

8B • Updated Oct 31, 2025 • 3

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step500

8B • Updated Oct 31, 2025 • 2

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step300

8B • Updated Oct 28, 2025 • 3

hamishivi/2010_rl_rag_NAR8_testing64_base_model_step300

8B • Updated Oct 28, 2025 • 3

hamishivi/1810_rl_rag_NAR8_onpolicy_step300

8B • Updated Oct 27, 2025 • 3

hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step300

8B • Updated Oct 27, 2025 • 2

hamishivi/1710_rl_rag_dpo_8b_lf_twoit_5epochs_29206__42__1760725767

Updated Oct 17, 2025 • 11

hamishivi/1710_rl_rag_dpo_8b_lf_twoit_3epochs_19511__42__1760723027

Updated Oct 17, 2025 • 7

hamishivi/1710_rl_rag_dpo_8b_twoit_5epochs_30705__42__1760722599

Updated Oct 17, 2025 • 7

hamishivi/1710_rl_rag_dpo_8b_twoit_3epochs_5622__42__1760722421

Updated Oct 17, 2025 • 7

hamishivi/1003_rl_rag_dpo_8b_extra_dpo_mask_lr_3e-7_8000__42__1760587452

Updated Oct 16, 2025 • 10

hamishivi/1003_rl_rag_dpo_8b_extra_dpo_mask_lr_3e-7_26162__42__1760588922

Updated Oct 16, 2025 • 5

hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_3e-7_6585__42__1760588384

Updated Oct 16, 2025 • 9

hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_3e-7_4523__42__1760587072

Updated Oct 16, 2025 • 8

hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_3e-7_18261__42__1760502719

Updated Oct 15, 2025 • 11

hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_1e-7_28652__42__1760501895

Updated Oct 15, 2025 • 9