hamishivi/2909_rl_rag_sft_mcp_rubric_long3__1__1759782085_step_350
8B
•
Updated
•
4
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated
a model
2 days ago
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step600
published
a model
2 days ago
hamishivi/2010_rl_rag_NAR8_testing64_base_model_step600
updated
a model
2 days ago
hamishivi/2010_rl_rag_NAR8_testing64_gpt5_under_trained_step600
Organizations
hamishivi/2909_rl_rag_sft_mcp_rubric_long2__1__1759791238_step_350
8B
•
Updated
•
4
hamishivi/2909_rl_rag_sft_mcp_rubric_long1__1__1759506668_step_450
8B
•
Updated
•
4
hamishivi/2909_rl_rag_sft_mcp_rubric_long0__1__1759850722_step_300
8B
•
Updated
•
4
hamishivi/1003_rl_rag_dpo_8b_extra_dpo_lr_1e-6__42__1759823252
Updated
•
3
hamishivi/1002_rl_rag_dpo_8b_lr_5e-6__42__1759750525
Updated
•
3
hamishivi/1002_rl_rag_dpo_8b_lr_1e-6__42__1759757449
Updated
•
2
hamishivi/2909_rl_rag_sft_mcp_rubric_long3__1__1759166200_step_200
8B
•
Updated
•
3
hamishivi/2909_rl_rag_sft_mcp_rubric_long2__1__1759166076_step_250
8B
•
Updated
•
4
hamishivi/2909_rl_rag_sft_mcp_rubric_long1__1__1759166188_step_200
8B
•
Updated
•
4
hamishivi/2909_rl_rag_sft_mcp_rubric_long0__1__1759437270_step_250
8B
•
Updated
•
4
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8.5__1__1758928287_step_350
8B
•
Updated
•
4
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.6__1__1758525156_step_400
8B
•
Updated
•
5
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8__1__1758528845_step_650
8B
•
Updated
•
274
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8.5__1__1758525087_step_200
8B
•
Updated
•
5
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7__1__1758524968_step_650
8B
•
Updated
•
5
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.5__1__1758524910_step_400
8B
•
Updated
•
5
hamishivi/rl-rag-qwen3-32b-sft-mix-0921_no_simple_short_form__123__1759088284
Updated
•
5
hamishivi/1309_rl_rag_sft_mcp_all_apaptive_rubric__1__1758491414_step_700
8B
•
Updated
•
5
hamishivi/qwen3-32b-sft-mix-v20250921
Updated
•
4
hamishivi/1309_rl_rag_sft_mcp_all_apaptive_rubric__1__1758491414_step_400
8B
•
Updated
•
5
hamishivi/1309_rl_rag_sft_mcp_all_adaptive_rubric__1__1758491414_step_400
Updated
hamishivi/1309_rl_rag_sft_apaptive_rubric_overfit__1__1758663540_step350
8B
•
Updated
•
2
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.6__1__1758525156_step_100
8B
•
Updated
•
4
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8.5__1__1758525087_step_100
8B
•
Updated
•
3
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8__1__1758528845_step_100
8B
•
Updated
•
4
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.5__1__1758524910_step_100
8B
•
Updated
•
4
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7__1__1758524968_step_100
8B
•
Updated
•
4
hamishivi/1309_rl_rag_sft_mcp_NAR7.6__1__1758423145_step_250
8B
•
Updated
•
3
hamishivi/1309_rl_rag_sft_mcp_NAR7.5__1__1758353280_step_300
8B
•
Updated
•
2