kalomaze

gemma-4-26B-A4B-intellect3-sft-step-768

Gemma 4 26B-A4B INTELLECT-3 SFT — step 768

Intermediate BF16 checkpoint from a one-epoch SFT run over a roughly 1 GB stratified sample of INTELLECT-3 SFT. This is training step 768 of 1024.

Sequence length: 32,768
Global batch size: 8 packed sequences
Optimizer: AdamW, learning rate 1e-5, max gradient norm 0.2
Schedule: linear decay over the final 250 steps
Attention: FlashAttention 4 with packed-example boundary masking
Chat format: GLM-4.5 Air renderer over a Gemma 4 tokenizer whose unused filler tokens were reassigned to the GLM role/tool/thinking tokens

The complete Gemma 4 multimodal tensors and processor metadata are retained, but the SFT data itself was text-only. Use the GLM-4.5 renderer/template for text turns; this checkpoint does not use Google's Gemma chat template.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

kalomaze

Model Tree

Base

google/gemma-4-26B-A4B

Fine-tuned

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer