| { |
| "ablate": [ |
| "none" |
| ], |
| "architectures": [ |
| "MiCRoLlama" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "backbone_num_layers": 30, |
| "bos_token_id": 0, |
| "config_path": "../mixture-of-reasoners/configs/config_micro_smollm2_135m.yml", |
| "eos_token_id": 0, |
| "gradient_checkpointing": false, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 576, |
| "initializer_range": 0.041666666666666664, |
| "intermediate_size": 1536, |
| "is_llama_config": true, |
| "jitter_noise": 0, |
| "loss_method": "all", |
| "loss_type": "ForCausalLMLoss", |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 9, |
| "num_experts": 4, |
| "num_experts_per_tok": 1, |
| "num_hidden_layers": 120, |
| "num_key_value_heads": 3, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_interleaved": false, |
| "rope_scaling": null, |
| "rope_theta": 100000, |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.2", |
| "use_bfloat16": true, |
| "use_cache": true, |
| "use_router": true, |
| "vocab_size": 49152 |
| } |
|
|
