| { | |
| "architecture": "Eve-2-MoE", | |
| "vocab_size": 50304, | |
| "n_layer": 12, | |
| "n_embd": 512, | |
| "n_head": 8, | |
| "head_dim": 64, | |
| "block_size": 2048, | |
| "num_experts": 8, | |
| "top_k": 2, | |
| "expert_intermediate_size": 1408, | |
| "shared_expert_intermediate_size": 1408, | |
| "rope_theta": 10000.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_eve.EveConfig", | |
| "AutoModelForCausalLM": "modeling_eve.DeepSeekMoE" | |
| }, | |
| "architectures": [ | |
| "DeepSeekMoE" | |
| ] | |
| } |