Edd
Erland
AI & ML interests
None yet
Recent Activity
authored
a paper
about 10 hours ago
Softpick: No Attention Sink, No Massive Activations with Rectified
Softmax
updated
a model
about 21 hours ago
Erland/gemma_without_embedding
published
a model
about 21 hours ago
Erland/gemma_without_embedding
Organizations
Collections
2
Papers
2
models
143
Erland/gemma_without_embedding
Text Generation
•
Updated
Erland/gemma_with_embedding
Text Generation
•
Updated
Erland/llama-2-13b-JAX
Text Generation
•
Updated
•
2
Erland/softpick-340M-4096-model
Text Generation
•
Updated
•
82
Erland/vanilla-340M-4096-model-HQQ-3bit
Text Generation
•
Updated
•
13
Erland/softpick-340M-4096-model-HQQ-3bit
Text Generation
•
Updated
•
20
Erland/vanilla-340M-4096-model-HQQ-2bit
Text Generation
•
Updated
•
13
Erland/softpick-340M-4096-model-HQQ-2bit
Text Generation
•
Updated
•
33
Erland/vanilla-340M-4096-model-AO-W4A4
Text Generation
•
Updated
•
8
Erland/softpick-340M-4096-model-AO-W4A4
Text Generation
•
Updated
•
10
datasets
30
Erland/fineweb-edu-cleaned-simplified-subset-with-eval
Viewer
•
Updated
•
11k
•
64
Erland/alpaca-cleaned-1000
Viewer
•
Updated
•
1.02k
•
25
Erland/fineweb-edu-cleaned-simplified-subset
Viewer
•
Updated
•
10k
•
202
Erland/alpaca-cleaned-sample
Viewer
•
Updated
•
100
•
15
Erland/FineTome-100k-sample-fixed
Viewer
•
Updated
•
1k
•
23
Erland/oscar_sampled_1000
Viewer
•
Updated
•
1k
•
34
Erland/rlaif-v-sample-non-processed
Viewer
•
Updated
•
100
•
21
Erland/rlaif-v-sample
Viewer
•
Updated
•
823
•
15
Erland/NLP701_Assignment2_Subtask3_KTO_Dataset_3
Viewer
•
Updated
•
440
•
19
Erland/NLP701_Assignment2_Subtask3
Viewer
•
Updated
•
118
•
25