20 Commits (58dcf9a99df43c09889a334935976c970536fa91)
 

Author SHA1 Message Date
thinhlpg 58dcf9a99d refactor: simplify inference script by removing logger, load 16 bit model intead of raw lora finetuned
1 month ago
thinhlpg da79e986b6 feat: add new script and functionality in train script to save model in 16 bit format
1 month ago
thinhlpg f6b6cca2ce feat: add multiple reference notebooks for model training and inference
1 month ago
thinhlpg 04593fa8fd style: change line length to 119, organize imports
1 month ago
thinhlpg abb18b10d8 feat: add CLI inference script with search functionality
1 month ago
thinhlpg fe70896023 chore: add Makefile for installation, code quality checks, style formatting, cleanup, and other tasks
1 month ago
thinhlpg 60233f2113 chore: update .gitignore
1 month ago
thinhlpg fd32bcacfd chores: update worklog and research progress
1 month ago
thinhlpg 37730095a9 feat: add eval scripts that compare base model performance with the grpo trained model
1 month ago
thinhlpg 7f2f43aa46 chore: clean up notebooks
1 month ago
thinhlpg 3c2deaced9 refactor: restructure code base, better centralize logging logic
1 month ago
thinhlpg 04d56325bb feat: add new reward functions, add less dumb data generation logic, implement better logging
2 months ago
thinhlpg b22b02ea1d feat: changed `<reasoning>` tags to `<think>
2 months ago
thinhlpg 7d4de89186 chore: update worklog 250324
2 months ago
thinhlpg 1bdee261b6 feat: add draft data generation and documentation
2 months ago
thinhlpg f19354a8c9 chore: clean up notebook output
2 months ago
thinhlpg f60ab499eb chore: update worklog
2 months ago
thinhlpg a58722e16f feat: add initial project structure and core functionality
2 months ago
Thinh Le 91c2476c28 chore: initial commit - the ugliest code i've ever written 💀
2 months ago
Thinh Le bf32fdd897 Initial commit
2 months ago