| { | |
| "architectures": [ | |
| "LoliCoreForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_lolicore.LoliCoreConfig", | |
| "AutoModelForCausalLM": "modeling_lolicore.LoliCoreForCausalLM" | |
| }, | |
| "bos_token_id": 2, | |
| "eos_token_id": 3, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 512, | |
| "max_position_embeddings": 8192, | |
| "model_type": "lolicore", | |
| "moe_top_k": 4, | |
| "num_attention_heads": 32, | |
| "num_experts": 20, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 32, | |
| "num_shared_experts": 2, | |
| "output_router_logits": false, | |
| "pad_token_id": 1, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "router_aux_loss_coef": 0.01, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.2", | |
| "use_cache": true, | |
| "vocab_size": 100534 | |
| } | |