| { | |
| "_name_or_path": "./mergekit/merged", | |
| "architectures": [ | |
| "GemmoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_gemmoe.GemmoeConfig", | |
| "AutoModelForCausalLM": "modeling_gemmoe.GemmoeForCausalLM" | |
| }, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "head_dim": 256, | |
| "hidden_act": "gelu", | |
| "hidden_activation": null, | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 24576, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemmoe", | |
| "num_attention_heads": 16, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 16, | |
| "num_local_experts": 4, | |
| "output_router_logits": false, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.02, | |
| "sliding_window": null, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.39.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 256000 | |
| } | |