Analysing the RLHF pipeline
Russel
rshwndsz
·
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 7 hours ago
rshwndsz/tulu-3-sft-mixture-en-2048
published
a dataset
about 8 hours ago
rshwndsz/tulu-3-sft-mixture-en-2048
updated
a dataset
16 days ago
rshwndsz/ambrosia
Organizations
None yet
Collections
1
models
15
rshwndsz/Qwen-2.5-0.5B-SFT
Updated
•
4
rshwndsz/Llama-3.2-1B-SFT
Updated
•
7
rshwndsz/Llama-3.2-3B-SFT
Updated
•
35
•
1
rshwndsz/Mistral-7B-v0.3-SFT
Updated
•
3
rshwndsz/Llama-3.1-8B-SFT
Updated
•
9
rshwndsz/ft_paraphrased-mistral-7b-v0.3-instruct
Updated
•
1
rshwndsz/ft_paraphrased-phi-3.5-mini-instruct
Updated
•
1
rshwndsz/ft_paraphrased-phi-4
Updated
rshwndsz/ft_paraphrased-hermes-3-llama-3.2-3b
Updated
•
1
rshwndsz/ft_paraphrased-longformer-base-4096
Updated
•
2
datasets
6
rshwndsz/tulu-3-sft-mixture-en-2048
Viewer
•
Updated
•
761k
rshwndsz/ambrosia
Viewer
•
Updated
•
26.1k
•
91
rshwndsz/Reviewer2_filtered_with_features_and_cluster
Viewer
•
Updated
•
76.3k
•
11
rshwndsz/Reviewer2_filtered_with_cluster
Viewer
•
Updated
•
76.3k
•
17
rshwndsz/processed-hh-rlhf
Viewer
•
Updated
•
91k
•
41
rshwndsz/Reviewer2
Viewer
•
Updated
•
96.5k
•
29