| { |
| "architectures": [ |
| "GravityMoEForCausalLM" |
| ], |
| "model_type": "gravity_moe", |
| "auto_map": { |
| "AutoConfig": "configuration_gravity_moe.GravityMoEConfig", |
| "AutoModelForCausalLM": "modeling_gravity_moe.GravityMoEForCausalLM" |
| }, |
| "vocab_size": 151552, |
| "hidden_size": 2048, |
| "intermediate_size": 8192, |
| "moe_intermediate_size": 1408, |
| "num_hidden_layers": 28, |
| "num_attention_heads": 16, |
| "num_key_value_heads": 16, |
| "q_lora_rank": null, |
| "kv_lora_rank": 512, |
| "qk_rope_head_dim": 64, |
| "qk_nope_head_dim": 128, |
| "v_head_dim": 128, |
| "n_routed_experts": 64, |
| "n_shared_experts": 1, |
| "num_experts_per_tok": 8, |
| "first_k_dense_replace": 1, |
| "moe_layer_freq": 1, |
| "routed_scaling_factor": 2.446, |
| "norm_topk_prob": true, |
| "scoring_func": "sigmoid", |
| "topk_method": "noaux_tc", |
| "n_group": 1, |
| "topk_group": 1, |
| "hidden_act": "silu", |
| "max_position_embeddings": 32768, |
| "initializer_range": 0.02, |
| "rms_norm_eps": 1e-06, |
| "use_cache": true, |
| "rope_theta": 1000000.0, |
| "rope_scaling": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "tie_word_embeddings": false, |
| "bos_token_id": null, |
| "eos_token_id": 151329, |
| "torch_dtype": "bfloat16", |
| "pad_token_id": 151329 |
| } |