Downloads · 30 days
6
18% of all-time downloads
AriaV9.3
SurgeFF/AriaV9.3
AriaV9.3 is a machine learning model from SurgeFF. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Full merged model — unsloth/gemma-4-12b-it (gemma4unified, 12B) with the AriaV9.3 fine-tune (adapter-v7, DMT staged QLoRA on Surge's home fleet) merged into the base weights. This repo previously contained only the Lo…
All-time downloads
34
Public
Parameters
12B
28.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors28.5 GB · 100%
At a glance
- Model type
- gemma4_unified
- Access
- Public
- Created
- Aug 7, 2026
- Updated
- Aug 8, 2026
- SHA
- c22e0498
Model card
From the Hugging Face model README
AriaV9.3
Full merged model — unsloth/gemma-4-12b-it (gemma4_unified, 12B) with the
AriaV9.3 fine-tune (adapter-v7, DMT staged QLoRA on Surge's home fleet) merged
into the base weights. This repo previously contained only the LoRA adapter;
that adapter now lives under adapter/ and the root is the complete model.
Contents
- root: merged bf16 safetensors (~24 GB) + tokenizer/chat template — load with
AutoModelForCausalLM.from_pretrained("SurgeFF/AriaV9.3")or Unsloth. gguf/: full llama.cpp quant ladder — F16, Q2_K, Q3_K_S/M/L, Q4_0, Q4_K_S/M, Q5_0, Q5_K_S/M, Q6_K, Q8_0.adapter/: the original LoRA adapter (PEFT), for stacking or re-training.
Eval (Aria capability suite, fingerprint c11acc0589a501c3)
| capability | score |
|---|---|
| math (GSM8K-100) | 0.87 |
| tools | 1.00 |
| identity | 1.00 |
| identity_bare | 0.50 |
| memory | 0.95 |
| mean | 0.864 |
Lineage
Base unsloth/gemma-4-12b-it → continuation QLoRA (r=32, α=32, attention+MLP
target modules, no embedding pass) over the AgentOS self-training corpus
(975 task rows + multimodal floor 25%) → promoted as AriaV9.3 on 2026-08-06.
Private fleet model. Trained and merged on CudaCuda (RTX 3090 / local only).
- Type
- gemma4_unified
- Created
- Aug 7, 2026
- Updated
- Aug 8, 2026