| { |
| "_name_or_path": "SmallDoge/Doge-160M-checkpoint", |
| "architectures": [ |
| "DogeForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_doge.DogeConfig", |
| "AutoModelForCausalLM": "modeling_doge.DogeForCausalLM" |
| }, |
| "bos_token_id": 0, |
| "dynamic_mask_ratio": 0.0, |
| "eos_token_id": 1, |
| "expert_retrieval_size": 64, |
| "hidden_act": "silu", |
| "hidden_bias": false, |
| "hidden_dropout": 0.0, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 1536, |
| "is_moe": false, |
| "max_position_embeddings": 2048, |
| "model_type": "doge", |
| "num_attention_heads": 6, |
| "num_cdmoe_experts": 16348, |
| "num_cdmoe_experts_per_head": 8, |
| "num_cdmoe_heads": 4, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 3, |
| "pad_token_id": 2, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "factor": 4.0, |
| "original_max_position_embeddings": 2048, |
| "rope_type": "dynamic" |
| }, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.48.3", |
| "use_cache": true, |
| "vocab_size": 32768 |
| } |
|
|
