Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
AndriejusNak
/
gemma4-26b-moe-finetune
like
1
Text Generation
PEFT
Safetensors
custom
Lithuanian
English
gemma
Mixture of Experts
mixture-of-experts
qlora
nf4
fine-tuning
dpo
ops-agent
infrastructure
tool-calling
single-gpu
rtx-3090
License:
gemma
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
Use this model
Instructions to use AndriejusNak/gemma4-26b-moe-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
Libraries
PEFT
How to use AndriejusNak/gemma4-26b-moe-finetune with PEFT:
Task type is invalid.
Notebooks
Google Colab
Kaggle
main
gemma4-26b-moe-finetune
94.2 MB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
AndriejusNak
Upload v25 training pipeline (~1700 lines)
7d4361c
verified
about 2 months ago
sft_adapter
Upload SFT adapter (loss 1.2146, 0 NaN)
about 2 months ago
.gitattributes
Safe
1.58 kB
Upload SFT adapter (loss 1.2146, 0 NaN)
about 2 months ago
README.md
Safe
6.86 kB
Add comprehensive model card
about 2 months ago
v6_26b_pipeline.py
Safe
66 kB
Upload v25 training pipeline (~1700 lines)
about 2 months ago
