{ "architectures": [ "DbrxForCausalLM" ], "attn_config": { "attn_pdrop": 0.0, "clip_qkv": null, "kv_n_heads": 1, "model_type": "", "rope_theta": 10000.0 }, "d_model": 8, "dtype": "float32", "emb_pdrop": 0.0, "ffn_config": { "ffn_act_fn": { "name": "silu" }, "ffn_hidden_size": 3584, "model_type": "", "moe_jitter_eps": null, "moe_loss_weight": 0.01, "moe_normalize_expert_weights": 1.0, "moe_num_experts": 4, "moe_top_k": 1 }, "initializer_range": 0.02, "intermediate_size": 32, "max_seq_len": 2048, "model_type": "dbrx", "n_heads": 4, "n_layers": 2, "num_key_value_heads": 2, "output_router_logits": false, "resid_pdrop": 0.0, "tie_word_embeddings": false, "transformers_version": "4.57.0", "use_cache": true, "vocab_size": 100280 }