GODELEV/Rose-Mini
Text Generation • 49.4M • Updated • 344 • 8
🔄 In a Training Loop
Mr Munk
GODELEV
AI & ML interests
High schooler by day, LLM builder by night. Driven by a deep love for both Physics and AI. Currently spending my runtime building on Hugging Face, experimenting with transformer architectures, and training custom LLMs.
Recent Activity
repliedto Banaxi-Tech's post about 6 hours ago
We're announcing BananaMind 2 Micro, our smallest model in the BananaMind 2 model family.
This model is not released yet, training has not started yet.
It uses only 2.9M parameters, while being overtrained on 75B tokens to get the maximum intelligence per parameter.
The key changes are:
No more AdamW, the model will use the Muon optimizer offering up to 2x faster convergence and higher lr.
LR goes to 2.2e-2.
We're adding the XSA refresh gate from the TX4 architecture into our own.
Training will start on August 3, release date is estimated to be August 4-6.
On August 3 we will also release our Public Preview of BananaMind 2 Pro.
Follow us to know when our models release
https://huggingface.co/BananaMind
@Banaxi-Tech
new activity about 7 hours ago
CyanMonkey/Testing-v2:Delete benchmark_booster_train.txt new activity about 7 hours ago
CyanMonkey/Testing-v2:Delete benchmark_booster.jsonlOrganizations
GODELEV/Archaea-74M-V1.1
Text Generation • 74M • Updated • 179 • 3
GODELEV/Exp-1
9.85M • Updated • 129 • 1
GODELEV/TOK-16K
Updated
GODELEV/TOK-8K
Updated
GODELEV/TOK-32K
Updated
GODELEV/Ant-10M
Text Generation • 9.9M • Updated • 86 • 4
GODELEV/Archaea-74M
Text Generation • 74M • Updated • 282 • 4
GODELEV/TOK-4K
Updated
GODELEV/Ant-5M
Text Generation • 4.71M • Updated • 132 • 2
GODELEV/Test-1-4000
Text Generation • 0.2B • Updated • 40
GODELEV/Test-1-3000
Text Generation • 0.2B • Updated • 10
GODELEV/Test-1-2000
Text Generation • 0.2B • Updated • 10