config.json, GSAI-ML/LLaDA-8B-Base

Fields

id

sources/arch-hf-config-llada

URL

https://huggingface.co/GSAI-ML/LLaDA-8B-Base/raw/main/config.json

Publisher

Hugging Face

Kind

repo

Accessed

2026-10-03

notes

d_model 4096, mlp_hidden_size 12288, mlp_ratio 4, embedding_size 126464, block_type 'llama', max_sequence_length 4096, mask_token_id 126336, rms norm, silu. Used for the per-step diffusion FLOP arithmetic.

Notes

d_model 4096, mlp_hidden_size 12288, mlp_ratio 4, embedding_size 126464, block_type 'llama', max_sequence_length 4096, mask_token_id 126336, rms norm, silu. Used for the per-step diffusion FLOP arithmetic.

Cross-references

This record references no other records.