www.questdecoding.com/alignment
Gonçalo Faria
graf
AI & ML interests
NLP
Recent Activity
updated
a model
14 days ago
graf/Llama-3.2-1B-RM-GSM8k
published
a model
14 days ago
graf/Llama-3.2-1B-RM-GSM8k
updated
a model
17 days ago
graf/Llama-3.1-Tulu-3-8B-SFT-MATH-RM
Organizations
Collections
2
models
8
graf/Llama-3.2-1B-RM-GSM8k
Text Generation
•
Updated
•
11
graf/Llama-3.1-Tulu-3-8B-SFT-MATH-RM
Updated
•
77
graf/Llama-3.1-Tulu-3-8B-SFT-onpolicymath-1e-6-b96
Updated
•
220
graf/Llama-3.1-ultra-it1-8B-GenRM
Updated
•
1
graf/Llama-3.1-ultra-cloud-8B-GenRM
Updated
•
3
graf/Llama-3.1-ultra-oracle-8B-GenRM
Updated
•
3
graf/tulusft-8b-onpolicybon-50k
Text Generation
•
Updated
•
3
graf/Llama-3.1-GSM8K-8B-RM
Text Generation
•
Updated
•
4
datasets
13
graf/cloud-sft-100k-1.0-round2-bon8-selfgen
Viewer
•
Updated
•
117k
•
41
graf/ultra-cloud-1.0-bon16
Viewer
•
Updated
•
91.2k
•
39
graf/cloud-sft-100k-1.0-round2-bon8
Viewer
•
Updated
•
91.2k
•
40
graf/ultra-sft-selfgen
Viewer
•
Updated
•
122k
•
37
graf/ultra-cloud-1.0-bon8-selfgen
Viewer
•
Updated
•
117k
•
40
graf/ultra-cloud-1.0-bon8
Viewer
•
Updated
•
91.2k
•
37
graf/tulu-3-sft-personas-math-filtered-onpolicy-pass64
Viewer
•
Updated
•
80k
•
30
graf/tulu-3-sft-personas-math-filtered-onpolicy-pass64-10k
Viewer
•
Updated
•
10k
•
25
graf/tulu-3-sft-personas-math-filtered-onpolicy-pass64-25k
Viewer
•
Updated
•
25k
•
28
graf/tulu-3-sft-personas-math-filtered-onpolicy-pass64-50k
Viewer
•
Updated
•
50k
•
32