| { | |
| "architectures": ["MonetForCausalLM"], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "modeling_monet.MonetConfig", | |
| "AutoModelForCausalLM": "modeling_monet.MonetForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "relu2", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": null, | |
| "model_type": "monet", | |
| "moe_decompose": "vertical", | |
| "moe_dim": 16, | |
| "moe_experts": 512, | |
| "moe_groups": 4, | |
| "moe_heads": 8, | |
| "moe_topk": 8, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "output_router_probs": false, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-6, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.44.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |