AICrossSim/bitflip-fc-clm-400m

Model Card for AICrossSim/bitflip-clm-400m

A 200M parameter bitflip-aware language model trained on 22 * 400M tokens from FineWeb-Edu dataset.

Model Details

bitflip-aixsim-400M is a transformer-based language model with approximately 400 million parameters (embedding layer params excluded). It uses RMSNorm for normalization and is trained on the FineWeb-Edu dataset.

• Developed by: AICrossSim
• Funded by: ARIA
• Model type: Transformer Language Model
• Language(s) (NLP): English
• Tokenizer: HuggingFaceTB/cosmo2-tokenizer
• Repository: AICrossSim/NewComputeBench

Training Details

Experiment setup and training logs can be found at wandb run.