metadata
license: apache-2.0
base_model: ibm-granite/granite-4.0-1b
language:
- en
tags:
- granite
- ibm
- full-finetune
- dual-gpu
- code
- reasoning
- text-generation
pipeline_tag: text-generation
datasets:
- Roman1111111/gpt-5.4-step-by-step-reasoning
- TeichAI/gpt-5.1-codex-max-1000x
- TeichAI/gpt-5.1-high-reasoning-1000x
IBM-GPT-5.4-Coder-1B
This model is a full fine-tuned derivative of ibm-granite/granite-4.0-1b.
Training setup:
- Full model fine-tuning
- No adapters
- No LoRA
- No QLoRA
- Dual-GPU DDP training