jinli.yl d145a67843 feat(config): update default LLM model configuration ... - Changed default model from qwen3-30b-a3b-instruct-2507 to qwen-flash - Updated evaluation tools to use EVALUATION_PROMPT_FOR_QUESTION instead of QUESTION2 - Added new PROMPT_MEMZERO_JSON2 configuration with context priority rules - Modified llm_request_for_json to use qwen-flash as default model - Updated halumem evaluation to specify qwen3-max model explicitly for certain requests		2026-01-19 16:52:35 +08:00
..
analyze_dataset_stats.py	feat(core): add ReMe V3 implementation with optional MCP client and enhanced filtering	2026-01-17 01:15:49 +08:00
analyze_results.py	feat(benchmark): add HaluMem baseline evaluation and analysis tools	2026-01-13 23:59:55 +08:00
compute_qa_stats_v4.py	refactor(mem_agent): optimize agent execution and enhance evaluation pipeline	2026-01-19 00:46:52 +08:00
compute_stats_from_tmp.py	feat(mem-agent): introduce version 4 memory agents and tools	2026-01-18 15:50:46 +08:00
eval_baseline_simple.py	feat(bench): add HaluMem dataset statistics analyzer and update LLM concurrency control	2026-01-14 10:14:35 +08:00
eval_reme.py	feat(mem_agent): introduce version 2 memory agents and tools	2026-01-13 01:54:20 +08:00
eval_reme_simple.py	feat(benchmark): add HaluMem baseline evaluation and analysis tools	2026-01-13 23:59:55 +08:00
eval_reme_simple_v3.py	feat(mem-agent): introduce version 4 memory agents and tools	2026-01-18 15:50:46 +08:00
eval_reme_simple_v4.py	refactor(mem_agent): optimize agent execution and enhance evaluation pipeline	2026-01-19 00:46:52 +08:00
eval_tools.py	feat(config): update default LLM model configuration	2026-01-19 16:52:35 +08:00
halumem.yaml	feat(config): update default LLM model configuration	2026-01-19 16:52:35 +08:00
llms.py	feat(config): update default LLM model configuration	2026-01-19 16:52:35 +08:00