You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
thinhlpg
90b45c62ab
docs: update docs and notebooks for the past few days, (observation, debugging)
...
- observation: model hallucniate the search result, docs about debugigng and adapting to r1 distil base model, notebooks on the detail of making training r1 distil works
3 months ago
..
archived
chores: update worklog and research progress
3 months ago
assets
docs: update docs and notebooks for the past few days, (observation, debugging)
3 months ago
00_worklog.md
chores: update worklog and research progress
3 months ago
agentic-reward-modeling.md
chores: update worklog and research progress
3 months ago
anti-dumb-reward-extact-match-chunk-prompt.md
chores: update worklog and research progress
3 months ago
brain-rotting-multiple-gpu-workflow-for-dummies.md
chores: update worklog and research progress
3 months ago
chat-template-101.md
chores: update worklog and research progress
3 months ago
choosing-llm-and-prompt-101.md
feat: add draft data generation and documentation
3 months ago
dataset.md
chore: update worklog 250324
3 months ago
debug-training-grpo-for-r1-distil.md
docs: update docs and notebooks for the past few days, (observation, debugging)
3 months ago
ds-pipeline-v0.md
chore: update worklog 250324
3 months ago
evaluation.md
docs: update docs and notebooks for the past few days, (observation, debugging)
3 months ago
grpo-idea.md
chores: update worklog and research progress
3 months ago
hallucination.md
docs: update docs and notebooks for the past few days, (observation, debugging)
3 months ago
inspect-chat-state.md
chores: update worklog and research progress
3 months ago
merge-chunk-content-to-data-prompt.md
chores: update worklog and research progress
3 months ago
project-overview-mermaid.md
feat: add initial project structure and core functionality
3 months ago
r1-searcher.md
chores: update worklog and research progress
3 months ago
random-popup-idea-💡.md
chores: update worklog and research progress
3 months ago
reward-functions.md
chores: update worklog and research progress
3 months ago
search-backends.md
feat: add draft data generation and documentation
3 months ago
search-r1.md
chores: update worklog and research progress
3 months ago
stuff-that-didnt-work-❌.md
chores: update worklog and research progress
3 months ago
stuff-that-worked-✅.md
chores: update worklog and research progress
3 months ago
understanding-search-engine-101.md
feat: add draft data generation and documentation
3 months ago