Skip to content

Actions: natolambert/rlhf-book

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
216 workflow runs
216 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix: Include code redirect in build (#225) Deploy static content to Pages #254: Commit adc78b2 pushed by natolambert
7m 38s main
main
7m 38s
Add rlhfbook.com/code redirect (#224) Deploy static content to Pages #253: Commit 4896870 pushed by natolambert
6m 2s main
main
6m 2s
Fix diagrams Makefile and remove unused diagrams (#223) Deploy static content to Pages #252: Commit c81b2df pushed by natolambert
6m 30s main
main
6m 30s
Fix directory structure in README to match actual layout Deploy static content to Pages #251: Commit c37db8a pushed by natolambert
10m 58s main
main
10m 58s
Clean up root files: gitignore, favicon, pyproject (#222) Deploy static content to Pages #250: Commit 6643bf9 pushed by natolambert
5m 18s main
main
5m 18s
Reorganize repo: move book sources into book/ subdirectory (#221) Deploy static content to Pages #249: Commit 1f5a679 pushed by natolambert
7m 6s main
main
7m 6s
[WIP] Add Code Library (#219) Deploy static content to Pages #248: Commit d54f445 pushed by natolambert
6m 30s main
main
6m 30s
Add equation labels to chapters 4 and 10 (#218) Deploy static content to Pages #247: Commit 1944b65 pushed by natolambert
13m 10s main
main
13m 10s
Add equation labels to chapter 11 for consistent numbering (#217) Deploy static content to Pages #246: Commit 0075120 pushed by natolambert
9m 53s main
main
9m 53s
Fix PPO implementation bugs: returns and KL masking (#216) Deploy static content to Pages #245: Commit 5a1f43b pushed by natolambert
11m 58s main
main
11m 58s
Clarify DPO paper quote in chapter 12 (#215) Deploy static content to Pages #244: Commit 9137ab2 pushed by natolambert
11m 40s main
main
11m 40s
Add CartPole diagram to chapter 4 (#213) Deploy static content to Pages #243: Commit aa515bf pushed by natolambert
8m 23s main
main
8m 23s
Delete images/timeline-v2.png Deploy static content to Pages #242: Commit 6c341f0 pushed by natolambert
13m 11s main
main
13m 11s
Fix bibliography citation errors and hallucinations (#211) Deploy static content to Pages #241: Commit 32726e4 pushed by natolambert
8m 11s main
main
8m 11s
Add tool use interleaving diagram to chapter 14.5 (#210) Deploy static content to Pages #240: Commit f35069b pushed by natolambert
6m 5s main
main
6m 5s
Add distillation diagrams to synthetic data chapter (#209) Deploy static content to Pages #239: Commit 9cbdebf pushed by natolambert
6m 36s main
main
6m 36s
Add TikZ diagram comparing PPO, GRPO, and RLOO (#208) Deploy static content to Pages #238: Commit a7d8736 pushed by natolambert
14m 0s main
main
14m 0s
Add PPO vs GRPO architecture comparison diagram (#207) Deploy static content to Pages #237: Commit 33e6b6f pushed by natolambert
8m 38s main
main
8m 38s
Add diagram infrastructure for reward model visualizations (#206) Deploy static content to Pages #236: Commit a2608a2 pushed by natolambert
8m 59s main
main
8m 59s
Update copyright to include 2026 (#205) Deploy static content to Pages #235: Commit 92e656c pushed by natolambert
8m 15s main
main
8m 15s
Update character training chapter with persona vectors and soul docum… Deploy static content to Pages #234: Commit fe9d4b6 pushed by natolambert
12m 3s main
main
12m 3s
explicitly state the dpo loss from bt model (#202) Deploy static content to Pages #233: Commit 993e7da pushed by natolambert
9m 53s main
main
9m 53s
Explain the role of the partition function Z(x) in DPO (#203) Deploy static content to Pages #232: Commit 92fd1b8 pushed by natolambert
6m 56s main
main
6m 56s
Uppercase the ratio term R_t in PPO objective (#201) Deploy static content to Pages #231: Commit b4a47aa pushed by natolambert
8m 19s main
main
8m 19s
Wrap up RL chapter & tooling stability improvements (#200) Deploy static content to Pages #230: Commit f2adb7c pushed by natolambert
6m 28s main
main
6m 28s