{ "source_revision": "e3a47d5b986e7141b6efd62597d598ebb392060d", "model": { "vocab_size": 157184, "hidden_size": 1536, "layer_count": 24, "attention_heads": 16, "head_dim": 128, "kv_lora_rank": 512, "q_lora_rank": 256, "qk_nope_dim": 128, "qk_rope_dim": 64, "value_head_dim": 128, "dense_ffn_dim": 4608, "expert_ffn_dim": 512, "shared_ffn_dim": 512, "expert_count": 128, "experts_per_token": 8, "expert_group_count": 8, "selected_group_count": 4, "layer_group_size": 4, "leading_dense_layers": 1, "convolution_kernel": 4, "max_context": 4096, "eos_token": 156895, "pad_token": 156892, "bos_token": 156891, "mla_layer_count": 6, "kda_layer_count": 18, "default_weight_bits": 4, "default_activation_bits": 8, "rms_epsilon": 0.000001, "rope_theta": 6000000.0, "routed_scale": 2.5, "kda_lower_bound": -5.0 }, "tensors": [] }