NEXUS Training - HuggingFace Spaces

Fine-tunes Qwen3.5-35B for command execution.

Usage

# Set your HF token
export HF_TOKEN=hf_xxxxx

# Run training
python train.py --steps 50

# Or with custom parameters
python train.py --steps 100 --lr 5e-5 --batch 2

Parameters

Parameter Default Description
--steps 50 Training steps
--lr 1e-4 Learning rate
--batch 1 Batch size
--output /tmp/nexus_model Output directory
--local-only false Don't push to Hub

Environment Variables

Variable Required Description
HF_TOKEN Yes HuggingFace token
OUTPUT_REPO No Output repo (default: Gerlai24/nexus-35b-execution)

Model

Base model: unsloth/Qwen3.5-35B-A3B-GGUF

Trained adapter will be pushed to HuggingFace Hub.

ZeroGPU

This space uses ZeroGPU for free GPU access.