RLHF 101: A Technical Dive into RLHF
•
5
Zhaolin Gao
GitBag
AI & ML interests
Reinforcement Learning from Human Feedback
Recent Activity
updated
a model
2 days ago
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rfst_eta_1e4_lr_3e-7_1738016708
published
a model
2 days ago
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rfst_eta_1e4_lr_3e-7_1738016708
updated
a model
2 days ago
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rfst_eta_1e2_lr_3e-7_1737991767
Articles
Organizations
Collections
1
models
299
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rfst_eta_1e4_lr_3e-7_1738016708
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rfst_eta_1e2_lr_3e-7_1737991767
Text Generation
•
Updated
•
4
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rfst_eta_1e3_lr_3e-7_1738004267
Text Generation
•
Updated
•
6
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_st_eta_1e4_lr_3e-7_1737941473
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_st_eta_1e3_lr_3e-7_1737929737
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_st_eta_1e2_lr_3e-7_1737917960
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rf_eta_1e4_lr_3e-7_1737906394
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rf_eta_1e3_lr_3e-7_1737894763
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_uf_dp_1k3k_from1735956551_rf_eta_1e2_lr_3e-7_1737883170
Text Generation
•
Updated
•
3
GitBag/reasoning_rebel_nianli_lr_3e-7_eta_1e6_1737077907
Text Generation
•
Updated
•
3
datasets
308
GitBag/llama3-uf-dp-from1735956551-token-rfst-1k3k_harvard
Viewer
•
Updated
•
91.9k
•
26
GitBag/llama3-uf-dp-from1735956551-token-rfst-1k3k
Viewer
•
Updated
•
91.9k
•
52
GitBag/llama3-uf-dp-from1735956551-token-st-1k3k_harvard
Viewer
•
Updated
•
50.5k
•
28
GitBag/llama3-uf-dp-from1735956551-token-rf-1k3k_harvard
Viewer
•
Updated
•
41.4k
•
55
GitBag/llama3-uf-dp-from1735956551-token-oa-1k3k
Viewer
•
Updated
•
45.2k
•
17
GitBag/llama3-uf-dp-from1735956551-token-st-1k3k
Viewer
•
Updated
•
50.5k
•
21
GitBag/llama3-uf-dp-from1735956551-token-rf-1k3k
Viewer
•
Updated
•
41.4k
•
18
GitBag/regenerated_responses_from_base_harvard
Viewer
•
Updated
•
55.1k
•
18
GitBag/llama3-uf-dp-from1735956551-same-turn
Viewer
•
Updated
•
56.6k
•
31
GitBag/llama3-uf-dp-from1735956551-reinforce
Viewer
•
Updated
•
57.9k
•
37