-
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper • 2203.05482 • Published • 6 -
Diverse Weight Averaging for Out-of-Distribution Generalization
Paper • 2205.09739 • Published • 1 -
Fusing finetuned models for better pretraining
Paper • 2204.03044 • Published • 5 -
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Paper • 2309.07311 • Published • 4
Niels Horn PRO
nilq
AI & ML interests
Natural language understanding, synthetic emotional speech, mechanistic interpretability.
Recent Activity
liked
a model
about 9 hours ago
zzzrw/DeepMesh
liked
a Space
1 day ago
nanotron/ultrascale-playbook
liked
a Space
4 days ago
tencent/Hunyuan3D-2mini-Turbo
Organizations
Collections
4
Papers
1
models
16
nilq/baby-python-mistral-1L-tiny-TinyStories-ft
Text Generation
•
Updated
•
42
•
1
nilq/baby-python-mistral-1L-tiny-lua-ft
Text Generation
•
Updated
•
30
nilq/baby-python-1L-mistral-lua-stories-slerp
Text Generation
•
Updated
•
78
nilq/baby-python-mistral-1L-tiny-base
Text Generation
•
Updated
•
76
nilq/lua-stories-slerp-mistral-1L-tiny
Text Generation
•
Updated
•
25
nilq/lua-stories-slerp-mistral-2L-tiny
Text Generation
•
Updated
•
23
nilq/mistral-2L-tiny
Text Generation
•
Updated
•
73
nilq/lua-stories-linear-mistral-1L-tiny
Text Generation
•
Updated
•
40
nilq/python-mistral-1L-mini
Text Generation
•
Updated
•
33
nilq/mistral-1L-tiny
Text Generation
•
Updated
•
691
•
5
datasets
9
nilq/baby-python-and-tiny-stories-and-lua
Viewer
•
Updated
•
12.3M
•
130
nilq/baby-python-and-lua
Viewer
•
Updated
•
12.3M
•
101
•
1
nilq/baby-python-and-tiny-stories
Viewer
•
Updated
•
13.9M
•
80
nilq/python-and-tiny-stories
Updated
•
4
nilq/baby-python
Viewer
•
Updated
•
11.7M
•
75
•
1
nilq/small-lua-stack
Viewer
•
Updated
•
559k
•
61
•
2
nilq/small-python-stack
Viewer
•
Updated
•
2.59M
•
196
nilq/babylm-100M
Viewer
•
Updated
•
12.7M
•
102
nilq/babylm-10M
Viewer
•
Updated
•
3.14M
•
102