| { |
| "architectures": [ |
| "SkyworkForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_skywork_moe.SkyworkMoeConfig", |
| "AutoModelForCausalLM": "modeling_skywork_moe.SkyworkForCausalLM" |
| }, |
| "model_type": "skywork_moe", |
| "vocab_size": 65532, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "pad_token_id": 0, |
| "hidden_act": "silu", |
| "hidden_size": 4608, |
| "initializer_range": 0.01, |
| "intermediate_size": 12288, |
| "max_position_embeddings": 8192, |
| "num_attention_heads": 36, |
| "num_key_value_heads": 36, |
| "num_hidden_layers": 52, |
| "num_experts": [ |
| 16 |
| ], |
| "moe_use_skywork_gating": false, |
| "moe_2layer_gate": false, |
| "moe_use_logits_norm": true, |
| "moe_gate_norm_std": 1.0, |
| "moe_feature_no_mul_topk": true, |
| "sliding_window": null, |
| "moe_expert_interval": 1, |
| "rms_norm_eps": 1e-06, |
| "rotary_percent": 1.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "use_cache": true, |
| "transformers_version": "4.40.1", |
| "rope_theta": 10000 |
| } |