hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step100
8B • Updated • 1
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a model about 11 hours ago
hamishivi/sft_qwen3_8b_our_tmax_sft published a model about 12 hours ago
hamishivi/sft_qwen3_8b_our_tmax_sft updated a model 2 days ago
hamishivi/sft_qwen35_9b_rl_rag_2_bc_only_v1Organizations
hamishivi/1810_rl_rag_NAR8_onpolicy_step400
8B • Updated • 2
hamishivi/1810_rl_rag_NAR8_onpolicy_step200
8B • Updated • 1
hamishivi/1810_rl_rag_NAR8_onpolicy_step100
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step400
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step200
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step100
8B • Updated • 1
hamishivi/1810_rl_rag_NAR8_onpolicy_step650
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step650
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step500
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step500
8B • Updated • 1
hamishivi/1810_rl_rag_NAR8_onpolicy_step500
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step500
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step300
8B • Updated • 1
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step300
8B • Updated • 1
hamishivi/1810_rl_rag_NAR8_onpolicy_step300
8B • Updated • 4
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_sft_step300
8B • Updated • 2
hamishivi/1710_rl_rag_dpo_8b_lf_twoit_5epochs_29206__42__1760725767
Updated • 4
hamishivi/1710_rl_rag_dpo_8b_lf_twoit_3epochs_19511__42__1760723027
Updated • 4
hamishivi/1710_rl_rag_dpo_8b_twoit_5epochs_30705__42__1760722599
Updated • 1
hamishivi/1710_rl_rag_dpo_8b_twoit_3epochs_5622__42__1760722421
Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_mask_lr_3e-7_8000__42__1760587452
Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_mask_lr_3e-7_26162__42__1760588922
Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_3e-7_6585__42__1760588384
Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_3e-7_4523__42__1760587072
Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_3e-7_18261__42__1760502719
Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_1e-7_28652__42__1760501895
Updated • 1
hamishivi/0810_rl_rag_sft_mcp_op_NAR2__1__1760040658_step_500
8B • Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_1e-6_16165__42__1760378171
Updated • 1
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_5e-7_13946__42__1760378070
Updated • 1