{ "_name_or_path": "databricks/dbrx-instruct", "architectures": [ "DbrxForCausalLM" ], "attn_config": { "clip_qkv": 8, "kv_n_heads": 4, "model_type": "", "rope_theta": 500000 }, "d_model": 256, "emb_pdrop": 0.0, "ffn_config": { "ffn_hidden_size": 512, "model_type": "", "moe_jitter_eps": 0, "moe_loss_weight": 0.05, "moe_num_experts": 16, "moe_top_k": 4 }, "initializer_range": 0.02, "max_seq_len": 32768, "model_type": "dbrx", "n_heads": 8, "n_layers": 2, "output_router_logits": false, "resid_pdrop": 0.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.40.0", "use_cache": true, "vocab_size": 100352 }