| { | |
| "architectures": [ | |
| "SwitchLlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "dropout_rate": 0.01, | |
| "eos_token_id": 2, | |
| "expert_capacity": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 3200, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8640, | |
| "max_position_embeddings": 2048, | |
| "model_type": "switchllama", | |
| "num_attention_heads": 32, | |
| "num_experts": 4, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "router_bias": false, | |
| "router_ignore_padding_tokens": false, | |
| "router_jitter_noise": 0.01, | |
| "router_z_loss_coef": 0.001, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.32.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |