| { | |
| "pretrained_model_name_or_path": "meta-llama/Llama-3.2-1B", | |
| "llama_config": { | |
| "hidden_size": 256, | |
| "intermediate_size": 1024, | |
| "num_hidden_layers": 8, | |
| "num_attention_heads": 16, | |
| "hidden_act": "silu", | |
| "max_position_embeddings": 131072, | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-06, | |
| "use_cache": true, | |
| "pretraining_tp": 1, | |
| "tie_word_embeddings": true, | |
| "rope_theta": 500000.0, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "mlp_bias": false, | |
| "head_dim": 16 | |
| }, | |
| "embed_dim": 1024 | |
| } |