TYTTYTTYT/llama-pixar-477m-p32-stage2
Text Generation • 0.5B • Updated • 158
MIXAR
Multilingual pixel-based language models from the MIXAR paper, plus the MGPT-2 baseline. Code: github.com/april-tools/mixar
Note Recommended. 477M, 32x32 patches, stage 2 (GRPO). The strongest generator.
TYTTYTTYT/llama-pixar-116m-p32-stage2
Text Generation • 0.1B • Updated • 151Note 116M, 32x32 patches, stage 2 (GRPO).
TYTTYTTYT/llama-pixar-116m-p8-stage2
Text Generation • 0.1B • Updated • 149Note 113M, 8x8 patches, stage 2 (GRPO).
TYTTYTTYT/llama-pixar-477m-p32
Text Generation • 0.5B • Updated • 154Note 477M, 32x32 patches, stage-1 backbone.
TYTTYTTYT/llama-pixar-116m-p32
Text Generation • 0.1B • Updated • 146Note 116M, 32x32 patches, stage-1 backbone.
TYTTYTTYT/llama-pixar-116m-p8
Text Generation • 0.1B • Updated • 147Note 113M, 8x8 patches, stage-1 backbone.
TYTTYTTYT/llama-pixar-116m-p8-stage2-gan
Text Generation • 0.1B • Updated • 151Note Ablation: adversarial (GAN) stage 2 of the 113M 8x8 model.
TYTTYTTYT/mgpt2-124m-mc4
Text Generation • 0.1B • Updated • 176Note Baseline: GPT-2 124M pretrained on the same mC4 corpus.