Self-Improving LLMs Through Iterative Refinement
ethicalabs.ai
non-profit
AI & ML interests
Building practical, ethical and sustainable AI/ML projects.
Recent Activity
View all activity
Collections
6
The empathetic mental-health assistant
-
ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO-GGUF
Text Generation • Updated • 30 -
ethicalabs/Kurtis-SmolLM2-360M-Instruct-DPO-GGUF
Text Generation • Updated • 106 -
ethicalabs/Kurtis-Qwen2.5-0.5B-Instruct-DPO-GGUF
Text Generation • Updated • 37 -
ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO
Text Generation • Updated • 210 •
models
18
ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO-ONNX
Text Generation
•
Updated
•
9
ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO
Text Generation
•
Updated
•
210
•
ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO-GGUF
Text Generation
•
Updated
•
30
ethicalabs/Kurtis-Qwen2.5-0.5B-Instruct-DPO-GGUF
Text Generation
•
Updated
•
37
ethicalabs/Kurtis-Qwen2.5-0.5B-Instruct-DPO
Text Generation
•
Updated
•
118
•
ethicalabs/FlowerTune-SmolLM2-360M-Instruct-Finance-PEFT
Text Classification
•
Updated
•
23
ethicalabs/Kurtis-Qwen2.5-0.5B-Instruct-DPO-PEFT
Text Generation
•
Updated
•
8
ethicalabs/Kurtis-Qwen2.5-0.5B-Instruct-PEFT
Text Generation
•
Updated
•
14
ethicalabs/Kurtis-Qwen2.5-0.5B-Instruct
Text Generation
•
Updated
•
34
ethicalabs/Kurtis-SmolLM2-360M-Instruct-DPO-GGUF
Text Generation
•
Updated
•
106