This Deepseek "Minny" was a somewhat naive attempt at pushing the capabilities of a 1.5B model, without retraining.
For Sure
ForSureTesterSim
AI & ML interests
Working on starting something up, message me if you would be interested.
Recent Activity
updated a model 2 days ago
ForSureTesterSim/Llama-3.1-8B-SLERP-0.5 published a model 2 days ago
ForSureTesterSim/Llama-3.1-8B-SLERP-0.5 updated a model 30 days ago
ForSureTesterSim/Holy-Trinity-7B-PCBOrganizations
models 20
ForSureTesterSim/Llama-3.1-8B-SLERP-0.5
Text Generation • 8B • Updated • 704 • 1
ForSureTesterSim/Holy-Trinity-7B-PCB
Text Generation • 7B • Updated • 25
ForSureTesterSim/Qwen3-4B-SpeechAct-Router-Adapter
Text Generation • Updated • 6
ForSureTesterSim/Qwen3-4B-Thinking-KnowRL-Adapter
Text Generation • Updated • 11
ForSureTesterSim/Llama-3.1-8B-R1-v1-ModelStock
Text Generation • 8B • Updated • 10
ForSureTesterSim/Llama-3.1-8B-R1-v2-Breadcrumbs
Text Generation • 8B • Updated • 4
ForSureTesterSim/Qwen3-14B-NSFW-FDA
Text Generation • 15B • Updated • 31 • 2
ForSureTesterSim/Llama-3.1-8B-TransMLA-PreRecovery
Text Generation • 8B • Updated • 13
ForSureTesterSim/Qwen2.5-R1-Minny-1.5B-v1
Text Generation • 2B • Updated • 12
ForSureTesterSim/Qwen2.5-R1-Minny-1.5B-v2
Text Generation • 2B • Updated • 15