| { |
| "architectures": [ |
| "MicroDistilleryBigramForCausalLM" |
| ], |
| "model_type": "custom", |
| "custom_model_type": "micro-distillery-bigram", |
| "vocab_size": 256, |
| "max_position_embeddings": 1024, |
| "hidden_size": 512, |
| "num_hidden_layers": 0, |
| "num_attention_heads": 0, |
| "intermediate_size": 0, |
| "activation_function": "gelu_new", |
| "layer_norm_epsilon": 0.00001, |
| "use_cache": true, |
| "bos_token_id": 0, |
| "eos_token_id": 1, |
| "transformers_version": "4.44.0", |
| "library_name": "micro-distillery", |
| "micro_distillery": { |
| "format": "bigram-distilled", |
| "dialect": "character-level", |
| "reference_arch": "tiny-bigram", |
| "distill_from": [ |
| "smollm2-135m", |
| "qwen2.5-0.5b", |
| "olmo2-1b", |
| "tinyllama-1.1b" |
| ], |
| "harmonic_seed": 1251963776, |
| "harmonic_frequencies": [ |
| 1, |
| 1.618033988749895, |
| 2, |
| 3.141592653589793 |
| ], |
| "grpo_config": { |
| "group_size": 8, |
| "kl_penalty": 0.1 |
| }, |
| "vae_config": { |
| "latent_dim": 32, |
| "filter_threshold": 0.7 |
| } |
| } |
| } |
