Sometimes I finetune models specifically to take on expert roles in a MoE configuration, sometimes I find interesting models others have fine tuned.
Rasmus Rasmussen
theprint
AI & ML interests
Small model experiments and homespun datasets.
Recent Activity
updated a model about 8 hours ago
theprint/Llama3.2-3B-Explained-GGUF published a model about 8 hours ago
theprint/Llama3.2-3B-Explained-GGUF updated a model about 8 hours ago
theprint/Llama3.2-3B-ExplainedOrganizations
models 176
theprint/Llama3.2-3B-Explained-GGUF
3B • Updated
theprint/Llama3.2-3B-Explained
Text Generation • 3B • Updated
theprint/Llama3.2-3B-Math-gsm8k-AutoSFT
3B • Updated • 21
theprint/GeneralChat-Llama3.2-3B-DPO-GGUF
3B • Updated • 2k
theprint/GeneralChat-Llama3.2-3B-DPO
Text Generation • 3B • Updated • 73
theprint/ThinkMix-Qwen2.5-1.5B-GGUF
2B • Updated • 136
theprint/ThinkMix-Gemma3-4B-GRPO-GGUF
4B • Updated • 314
theprint/ThinkMix-Gemma3-4B
Image-Text-to-Text • 4B • Updated • 16 • 1
theprint/ThinkMix-Qwen2.5-1.5B
Text Generation • 2B • Updated • 22
theprint/DevilsAdvocate-8B
Text Generation • 8B • Updated
datasets 112
theprint/TextAnalysis
Viewer • Updated • 77 • 3
theprint/Tom-DPO
Viewer • Updated • 4.14k • 18
theprint/AI-AgentsTools-GPT-Multiround-Conversation
Viewer • Updated • 705 • 17
theprint/ThinkMix-GPT-0126
Viewer • Updated • 22.7k • 12
theprint/TriviaMix
Preview • Updated • 6
theprint/MultiRoundConvos-Code-JS-HTML-CSS-Python
Viewer • Updated • 2.42k • 134
theprint/DS-LLM-Research-Extended-GPT
Viewer • Updated • 8.6k • 11
theprint/DS-LLM-Research
Viewer • Updated • 7.45k • 10
theprint/GeneralChat-GPT
Viewer • Updated • 9.55k • 6
theprint/GeneralChat-alpaca
Preview • Updated • 5