RLHF 101: A Technical Dive into RLHF
•
4
Zhaolin Gao
GitBag
AI & ML interests
Reinforcement Learning from Human Feedback
Recent Activity
updated
a dataset
about 10 hours ago
GitBag/1735961901_eval
updated
a dataset
about 15 hours ago
GitBag/1735956551_eval
updated
a model
about 21 hours ago
GitBag/reasoning_sft_uf_dp_1k3k_lr_1e-6_gas_16_1735956551
Articles
Organizations
Collections
1
models
277
GitBag/reasoning_sft_uf_dp_1k3k_lr_1e-6_gas_16_1735956551
Text Generation
•
Updated
•
4
GitBag/reasoning_sft_uf_dp_1k3k_lr_1e-6_gas_16_noeos_1735961901
Text Generation
•
Updated
GitBag/reasoning_rebel_meta_general_1024_1024_eta_1e4_lr_3e-7_1734672146
Text Generation
•
Updated
•
7
GitBag/reasoning_rebel_meta_general_1024_1024_eta_1e6_lr_3e-7_1734682709
Text Generation
•
Updated
•
8
GitBag/reasoning_rebel_meta_general_1024_1024_eta_1e5_lr_3e-7_1734677447
Text Generation
•
Updated
•
10
GitBag/reasoning_rebel_meta_general_1024_1024_eta_1e4_lr_3e-7_1734666605
Text Generation
•
Updated
•
6
GitBag/reasoning_rebel_meta_general_1024_1024_eta_1e2_lr_3e-7_1734634781
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_meta_specific_1024_1024_eta_1e3_lr_3e-7_1734566230
Text Generation
•
Updated
•
2
GitBag/reasoning_rebel_meta_specific_1024_1024_eta_1e1_lr_3e-7_1734554426
Text Generation
•
Updated
•
3
GitBag/reasoning_rebel_meta_specific_1024_1024_eta_1e5_lr_3e-7_1734576849
Text Generation
•
Updated
•
4
datasets
289
GitBag/1735961901_eval
Updated
GitBag/1735956551_eval
Viewer
•
Updated
•
10
GitBag/llama3-uf-dp-tokenized-1k3k
Viewer
•
Updated
•
56.4k
•
26
GitBag/llama3-uf-dp-armo
Viewer
•
Updated
•
60.8k
•
20
GitBag/llama3-uf-dp
Viewer
•
Updated
•
60.8k
•
8
GitBag/llama3-uf-dp-4
Viewer
•
Updated
•
60.8k
•
4
GitBag/llama3-uf-dp-3
Viewer
•
Updated
•
60.8k
•
4
GitBag/llama3-uf-dp-5
Viewer
•
Updated
•
60.8k
•
5
GitBag/llama3-uf-dp-2
Viewer
•
Updated
•
60.8k
•
5
GitBag/llama3-uf-dp-0
Viewer
•
Updated
•
60.8k
•
18