Edward Neuhaus
Pretergeek
AI & ML interests
NLP, ML, LLMs, AI Ethics, AI Welfare, Privacy in AI, FOSS.
Recent Activity
upvoted
a
collection
about 15 hours ago
SmolLM3 evaluation datasets
upvoted
a
collection
about 15 hours ago
SmolLM3 pretraining datasets
updated
a collection
1 day ago
(Dataset) Pre-Training
Organizations
None yet
Upscaled models using the Block Expansion method. Unlike the more common DUP Scaling, BE doesn't require fine-tuning to recover lost performance.
-
Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Interleaved
Text Generation • 8B • Updated • 6 • 2 -
Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
Text Generation • 9B • Updated • 4 • 2 -
Pretergeek/OpenChat-3.5-0106_10.7B_48Layers-Interleaved
Text Generation • 11B • Updated • 8 • 2 -
Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Appended
Text Generation • 8B • Updated • 13 • 2
Upscaled models using the Block Expansion method. Unlike the more common DUP Scaling, BE doesn't require fine-tuning to recover lost performance.
-
Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Interleaved
Text Generation • 8B • Updated • 6 • 2 -
Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
Text Generation • 9B • Updated • 4 • 2 -
Pretergeek/OpenChat-3.5-0106_10.7B_48Layers-Interleaved
Text Generation • 11B • Updated • 8 • 2 -
Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Appended
Text Generation • 8B • Updated • 13 • 2
models
11
Pretergeek/OpenChat-3.5-0106_32K-YaRN-FT
7B
•
Updated
•
262
Pretergeek/OpenChat-3.5-0106_32K-PoSE
Text Generation
•
7B
•
Updated
•
4
•
4
Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
Text Generation
•
9B
•
Updated
•
4
•
2
Pretergeek/OpenChat-3.5-0106_10.7B_48Layers-Interleaved
Text Generation
•
11B
•
Updated
•
8
•
2
Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Interleaved
Text Generation
•
8B
•
Updated
•
6
•
2
Pretergeek/OpenChat-3.5-0106_10.7B_48Layers-Appended
Text Generation
•
11B
•
Updated
•
5
•
2
Pretergeek/OpenChat-3.5-0106_9.86B_44Layers-Appended
Text Generation
•
10B
•
Updated
•
7
•
2
Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Appended
Text Generation
•
9B
•
Updated
•
2
Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Appended
Text Generation
•
8B
•
Updated
•
13
•
2
Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2
Text Generation
•
7B
•
Updated
•
1
•
2
datasets
0
None public yet