Skip to content

Actions: kurisu/SQuAD_Agent_Experiment

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
56 workflow runs
56 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

chore: Cleaning up code and documentation Run Python script #56: Commit b6bf8bb pushed by kurisu
October 26, 2024 06:53 35s main
main
October 26, 2024 06:53 35s
chore: ignore deep eval's telemetry file Run Python script #55: Commit b669dc7 pushed by kurisu
October 26, 2024 06:47 40s main
main
October 26, 2024 06:47 40s
chore: add missing dependency to requirements.txt Run Python script #54: Commit 7a63ac5 pushed by kurisu
October 26, 2024 06:46 36s main
main
October 26, 2024 06:46 36s
feat: Finalized benchmarking and evaluation Run Python script #53: Commit 1f01e54 pushed by kurisu
October 25, 2024 03:17 41s main
main
October 25, 2024 03:17 41s
bug: Fix image qa tool Run Python script #52: Commit bef822f pushed by kurisu
October 24, 2024 16:13 43s main
main
October 24, 2024 16:13 43s
chore: added missing dependency to requirements.txt - accelerate Run Python script #51: Commit b3e718c pushed by kurisu
October 24, 2024 06:32 42s main
main
October 24, 2024 06:32 42s
chore: added missing dependency to requirements.txt - termcolor Run Python script #50: Commit ee05627 pushed by kurisu
October 24, 2024 06:07 44s main
main
October 24, 2024 06:07 44s
bug: HF-specific bugs continue. hopefully this is the last. Run Python script #49: Commit 140a9f9 pushed by kurisu
October 24, 2024 06:00 37s main
main
October 24, 2024 06:00 37s
bug: more strange bugs on HF. something to do with quotes? Run Python script #48: Commit b566979 pushed by kurisu
October 24, 2024 05:51 36s main
main
October 24, 2024 05:51 36s
bug: Fixing a strange bug on HF (works locally) Run Python script #47: Commit 68d9214 pushed by kurisu
October 24, 2024 05:44 44s main
main
October 24, 2024 05:44 44s
feat: Expanded benchmarking to 100 samples and added further analysis… Run Python script #46: Commit b561eb0 pushed by kurisu
October 24, 2024 05:36 37s main
main
October 24, 2024 05:36 37s
feat: Compared 3 different prompting approaches Run Python script #45: Commit af5828d pushed by kurisu
October 23, 2024 04:01 44s main
main
October 23, 2024 04:01 44s
feat: switched to using the cheaper, faster, gpt-4o-mini as the defau… Run Python script #44: Commit 074043b pushed by kurisu
October 22, 2024 06:48 35s main
main
October 22, 2024 06:48 35s
feat: Added synthesis of contextual questions that could be used to b… Run Python script #43: Commit f6183fe pushed by kurisu
October 22, 2024 06:47 40s main
main
October 22, 2024 06:47 40s
chore: Cleaned up the Observation output, corrected a tool usage docu… Run Python script #42: Commit 8c89f91 pushed by kurisu
October 17, 2024 07:16 36s main
main
October 17, 2024 07:16 36s
feat: greatly expanded the available tools, while also simplifying th… Run Python script #41: Commit 5532a05 pushed by kurisu
October 17, 2024 06:48 39s main
main
October 17, 2024 06:48 39s
feat: simplified squad tools to hopefully prevent errors Run Python script #40: Commit 9640c92 pushed by kurisu
October 17, 2024 06:47 39s main
main
October 17, 2024 06:47 39s
feat: simplified guidance to focus on squad Run Python script #39: Commit afd3c81 pushed by kurisu
October 17, 2024 06:46 38s main
main
October 17, 2024 06:46 38s
feat: added support for using openai as the llm engine Run Python script #38: Commit f2afcac pushed by kurisu
October 17, 2024 06:46 42s main
main
October 17, 2024 06:46 42s
chore: refactor to make it easier to customize agents with different … Run Python script #37: Commit 985ea85 pushed by kurisu
October 14, 2024 02:53 36s main
main
October 14, 2024 02:53 36s
chore: set model based on being in HF Space or not (presumed local) Run Python script #36: Commit 6b088d7 pushed by kurisu
October 14, 2024 00:04 38s main
main
October 14, 2024 00:04 38s
chore: Prevent committing compressed vector data Run Python script #35: Commit 33bb2de pushed by kurisu
October 14, 2024 00:04 41s main
main
October 14, 2024 00:04 41s
chore: Deploy updated data to HF Space Run Python script #34: Commit 286b251 pushed by kurisu
October 14, 2024 00:03 38s main
main
October 14, 2024 00:03 38s
chore: refactored agents to allow configuration of the agent created Run Python script #33: Commit c21450b pushed by kurisu
October 13, 2024 19:51 38s main
main
October 13, 2024 19:51 38s
feat: Benchmarking now supports multiple benchmarks against different… Run Python script #32: Commit a6b3632 pushed by kurisu
October 13, 2024 19:37 36s main
main
October 13, 2024 19:37 36s