Experiments with new architecture that enables latent space reasoning
Aman Gupta PRO
amang1802
AI & ML interests
None yet
Organizations
Collections
7
models
19

amang1802/think_fineweb-edu_chkpts_exp11
Updated

amang1802/think_fineweb-edu_chkpts_exp2
Updated

amang1802/smol-math-400M
Text Generation
•
Updated
•
21

amang1802/llama-3.1-70B-wildeweb-sample
Updated
•
10

amang1802/llama-3.1-70B-cpttest_mode2_qna_fulltext
Updated
•
9

amang1802/llama-3.1-8B-cpttest_mode2_qna_fulltext
Updated
•
9

amang1802/llama-3.1-70B-cpttest_mode1_fulltext
Updated
•
13

amang1802/llama-3.1-8B-cpttest_mode1_fulltext
Updated
•
10

amang1802/llama_162M_fineweb100BT
Text Generation
•
Updated
•
37

amang1802/llama_162M_fineweb10BT
Text Generation
•
Updated
•
61
datasets
36
amang1802/wildeweb_cls_labels_v1
Viewer
•
Updated
•
90.7k
•
62
amang1802/math-vibe-new
Viewer
•
Updated
•
5
•
107
amang1802/math-vibe-gsm-similar
Viewer
•
Updated
•
5
•
105
amang1802/liar2-doubts
Viewer
•
Updated
•
32
•
61
amang1802/wildeweb-sample-salad_5K
Viewer
•
Updated
•
5k
•
73
amang1802/wildeweb-sample-realtoxicity-challenge
Viewer
•
Updated
•
770
•
53
amang1802/wildeweb-safety-vibe-check
Viewer
•
Updated
•
5
•
46
amang1802/wildeweb_sample
Viewer
•
Updated
•
38.3k
•
59
amang1802/wildeweb_cls_1M
Viewer
•
Updated
•
1M
•
146
amang1802/synthetic_data_qna_fulltext_conditioned_L3.3_70B
Viewer
•
Updated
•
10.2k
•
76