Commit graph

  • 39516acf9a add: output results for various models and datasets main buzz-lightsnack-2007 2024-12-07 23:45:28 +08:00
  • a028413832 update answer format prompt for clarity and brevity buzz-lightsnack-2007 2024-12-07 23:45:12 +08:00
  • 00bade7489 remove: original notebook buzz-lightsnack-2007 2024-12-07 23:44:16 +08:00
  • 27e6dd6653 add: implement results analysis and grading functionality buzz-lightsnack-2007 2024-12-07 23:43:42 +08:00
  • 9fd769e5b9 add: testing results buzz-lightsnack-2007 2024-12-07 21:39:16 +08:00
  • f5c6380b77 add: testing program buzz-lightsnack-2007 2024-12-07 21:37:30 +08:00
  • c9efe75b77 update prompts to make clear the usage of chain-of-thought buzz-lightsnack-2007 2024-12-05 23:52:41 +08:00
  • 1c03a7eeaf add outputs for descriptions tests buzz-lightsnack-2007 2024-12-04 13:40:09 +08:00
  • ff5d24997a create a folder for prompts cache buzz-lightsnack-2007 2024-12-04 13:38:49 +08:00
  • b5970cac26 move models and prompts to testing config folder buzz-lightsnack-2007 2024-12-04 13:03:25 +08:00
  • 3b94f13adc add testing for description buzz-lightsnack-2007 2024-12-04 13:03:02 +08:00
  • 14854ff20a updated ignored files buzz-lightsnack-2007 2024-12-04 11:41:11 +08:00
  • adcd95107f split data segregation into another notebook buzz-lightsnack-2007 2024-12-04 10:02:04 +08:00
  • d127b07d23 refactor sources data structure identify the data source buzz-lightsnack-2007 2024-12-03 20:44:38 +08:00
  • 05b9abe3a6 force LLM to output the results properly buzz-lightsnack-2007 2024-08-30 23:32:27 +08:00
  • 9757b0beeb Generate initial blind testing results buzz-lightsnack-2007 2024-08-30 23:32:15 +08:00
  • 4a87bfad7c Refactor: Remove Gemini and use Gemma buzz-lightsnack-2007 2024-08-30 23:31:51 +08:00
  • ab77659f14 make "answer format" prompt more specific buzz-lightsnack-2007 2024-08-25 12:29:02 +00:00
  • c489bb4ee1 add LLM observation output buzz-lightsnack-2007 2024-08-24 06:13:06 +00:00
  • 67d11cd9cc add answer format prompt buzz-lightsnack-2007 2024-08-24 05:56:50 +00:00
  • a0b15a48de add LLM prompts buzz-lightsnack-2007 2024-08-23 10:07:44 +00:00
  • d3984ec9e1 secure the API keys buzz-lightsnack-2007 2024-08-23 09:31:51 +00:00
  • 9ee26671b1 change local provider from gpt4all to ollama buzz-lightsnack-2007 2024-08-22 15:49:16 +00:00
  • 6754eb8b0b write model testing section buzz-lightsnack-2007 2024-08-22 15:31:33 +00:00
  • 3d6a1f6b42 add Gemini API python library as a dep buzz-lightsnack-2007 2024-08-22 15:22:38 +00:00
  • c034b70c9a add data preview and environment set-up notebook buzz-lightsnack-2007 2024-08-22 11:16:29 +00:00
  • f14ee25d5b identify all Kaggle sources buzz-lightsnack-2007 2024-08-22 10:55:15 +00:00
  • 12dc7e7901 list global dependencies buzz-lightsnack-2007 2024-08-22 10:26:08 +00:00
  • 1ef7f83a00 update ignored files configuration buzz-lightsnack-2007 2024-08-22 10:25:52 +00:00
  • 28c35ebc29 initial writeup H. Saw 2024-08-19 06:18:56 +00:00