Downloads · 30 days
2
3% of all-time downloads
gemma-4-26b-a4b-it-au-v5-adapter
dennisonb/gemma-4-26b-a4b-it-au-v5-adapter
gemma-4-26b-a4b-it-au-v5-adapter is a machine learning model from dennisonb. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Trained purely on skills: real error→diagnosis→fix traces, implementation tasks, and tool-grounded answers — exact facts are delegated to retrieval by design.
All-time downloads
58
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2 GB · 98%
At a glance
- License
- apache-2.0
- Model type
- gemma4
- Access
- Public
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026
- SHA
- bb2e0857
Base models
Model card
From the Hugging Face model README
Agent University Gemma-4 specialist v5 — skill-focused (debug + tools, no memorization)
Trained purely on skills: real error→diagnosis→fix traces, implementation tasks, and tool-grounded answers — exact facts are delegated to retrieval by design.
Benchmark (40 app-building tasks and 210 knowledge questions the models never saw during training, scored against real, tested reference implementations): 53.2% knowledge retention via tool use; 47.1% on build tasks; tool calibration retained (95–98% / 7.5%). For comparison, Claude Sonnet 5 scored 31.5% on the same build tasks.
- Base:
google/gemma-4-26B-A4B-it(Apache-2.0, subject to Gemma Terms) - Training: LoRA supervised fine-tuning on the Agent University corpus — ~90 live-tested curricula for AI/agent libraries and dev tools (Supabase, MCP, Next.js, Cloudflare, Slack, and more)
- Format: Fireworks
fused_peft_3d_v1layout — MoE expert LoRAs are fused 3D tensors. Standard PEFT loads the attention/MLP portion; for a full-fidelity merge usemerge_adapter.pyfrom the agent-university harness. A merged, ready-to-run Q8_0 GGUF is in the companion-ggufrepo.
- Type
- gemma4
- License
- apache-2.0
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026