| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 576, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "max_position_embeddings": 2048, | |
| "mha2mla": { | |
| "is_baseline": false, | |
| "is_gqa2mha2mla": false, | |
| "is_mla_from_scratch": false, | |
| "low_rank": 32, | |
| "partial_rope_version": "2-norm", | |
| "qk_tensor_path": "utils/smollm1_135M-2_norm_rank.pth", | |
| "rope_dim_for_mla": 8, | |
| "svd_init_method": "joint", | |
| "uniform_start_point": 0 | |
| }, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 9, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 3, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.0", | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| } | |