hamishivi/1309_rl_rag_sft_mcp_all_adaptive_rubric__1__1758491414_step_400
Updated
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated
a model 34 minutes ago
hamishivi/step500-test2 published
a model 35 minutes ago
hamishivi/step500-test2 updated
a model about 1 hour ago
hamishivi/tmax-qwen3.5-4b-sft-20260313 Organizations
hamishivi/1309_rl_rag_sft_apaptive_rubric_overfit__1__1758663540_step350
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.6__1__1758525156_step_100
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8.5__1__1758525087_step_100
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8__1__1758528845_step_100
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.5__1__1758524910_step_100
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7__1__1758524968_step_100
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.6__1__1758423145_step_250
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.5__1__1758353280_step_300
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_all_apaptive_rubric__1__1758491414_step_150
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_all_adaptive_rubric__1__1758491414_step_150
Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8.5__1__1758525087_step_50
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR8__1__1758528845_step_50
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.6__1__1758525156_step_50
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7.5__1__1758524910_step_50
8B • Updated
• 1
hamishivi/1309_rl_rag_sft_mcp_rubric_lfrs_NAR7__1__1758524968_step_50
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR8.5__1__1758353488_step_250
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.6__1__1758423145_step_200
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.5__1__1758353280_step_250
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_all_apaptive_rubric__1__1758491414_step_100
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_all_apaptive_rubric__1__1758491414_step_50
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR8.5__1__1758353488_step_200
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR8__1__1758353461_step_200
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.5__1__1758353280_step_200
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.6__1__1758423145_step_100
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR8.5__1__1758353488_step_150
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR8__1__1758353461_step_150
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.5__1__1758353280_step_150
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7__1__1758353204_step_150
8B • Updated
hamishivi/1309_rl_rag_sft_mcp_NAR7.6__1__1758423145_step_50
8B • Updated