| { | |
| "attention_qkv_bias": false, | |
| "codebook_size": 2051, | |
| "dim": 2048, | |
| "dropout": 0.0, | |
| "fast_attention_qkv_bias": false, | |
| "fast_dim": 1024, | |
| "fast_intermediate_size": 8192, | |
| "fast_head_dim": 128, | |
| "fast_n_head": 8, | |
| "fast_n_local_heads": 2, | |
| "n_fast_layer": 4, | |
| "head_dim": 64, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "is_reward_model": false, | |
| "max_seq_len": 2048, | |
| "model_type": "csm", | |
| "n_head": 32, | |
| "norm_eps": 1e-05, | |
| "n_layer": 16, | |
| "n_local_heads": 8, | |
| "num_codebooks": 32, | |
| "rope_base": 500000, | |
| "scale_codebook_embeddings": false, | |
| "share_codebook_embeddings": true, | |
| "use_gradient_checkpointing": false, | |
| "vocab_size": 128256, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| } | |
| } |