| { |
| "architectures": [ |
| "OmegaForCausalLM" |
| ], |
| "model_type": "omega_3060", |
| "auto_map": { |
| "AutoConfig": "configuration_omega.OmegaConfig", |
| "AutoModelForCausalLM": "modeling_omega.OmegaForCausalLM" |
| }, |
| "vocab_size": 163840, |
| "hidden_size": 7168, |
| "intermediate_size": 2048, |
| "expert_intermediate": 2048, |
| "num_hidden_layers": 61, |
| "num_attention_heads": 64, |
| "num_key_value_heads": 64, |
| "num_experts_per_layer": 10, |
| "kv_lora_rank": 512, |
| "q_lora_rank": 1536, |
| "qk_rope_head_dim": 64, |
| "v_head_dim": 128, |
| "qk_nope_head_dim": 128, |
| "hidden_act": "silu", |
| "max_position_embeddings": 262144, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 50000.0, |
| "tau": 0.1, |
| "expert_floor": 0.05, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.48.0", |
| "use_cache": false |
| } |
