| license: apache-2.0 | |
| datasets: | |
| - karpathy/tinystories-gpt4-clean | |
| language: | |
| - en | |
| A small Gemma4-based model with fused MoE layers trained on the TinyStories dataset. |
| license: apache-2.0 | |
| datasets: | |
| - karpathy/tinystories-gpt4-clean | |
| language: | |
| - en | |
| A small Gemma4-based model with fused MoE layers trained on the TinyStories dataset. |