All models are “IBM Granite 4.0” at core fine-tuned, merged & trained by (WithIn Us AI) • 2 items • Updated
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
- 546
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-4.0-1bQuantizations
2 models