WithinUsAI
/

IBM-Grok4-Ultra.Fast.Coder-1B

Text Generation

granitemoehybrid

Model card Files Files and versions

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

IBM-Grok4-UltraFast-Coder-1B

This model is a full fine-tuned derivative of ibm-granite/granite-4.0-1b.

Training notes: - Full model fine-tuning - No adapters - No LoRA - No QLoRA - Dual-GPU DDP training on Kaggle

Downloads last month: 782

Safetensors

Model size

2B params

Tensor type

BF16

·

Model tree for WithinUsAI/IBM-Grok4-Ultra.Fast.Coder-1B

Base model

ibm-granite/granite-4.0-1b-base

Finetuned

ibm-granite/granite-4.0-1b

Finetuned

(9)

this model

Quantizations

Datasets used to train WithinUsAI/IBM-Grok4-Ultra.Fast.Coder-1B

Collection including WithinUsAI/IBM-Grok4-Ultra.Fast.Coder-1B

“IBM Granite 4”

All models are “IBM Granite 4.0” at core fine-tuned, merged & trained by (WithIn Us AI) • 2 items • Updated 10 days ago