{ "model_args": { "block_size": 131072, "vocab_size": 128256, "rope_freq_base": 10000, "rope_freq_scale": 1.0, "n_layer": 28, "num_kv_heads": 8, "head_size": 128, "n_head": 24, "n_embd": 3072, "intermediate_size": 8192, "dropout": 0.0, "bias": false, "multiple_of": 256, "norm_eps": 1e-05, "sliding_window": null, "gradient_checkpointing": false } }