| { |
| "vocab_size": 8192, |
| "hidden_size": 256, |
| "num_hidden_layers": 8, |
| "num_attention_heads": 8, |
| "num_key_value_heads": 2, |
| "head_dim": 32, |
| "num_experts": 64, |
| "num_experts_per_sequence": 13, |
| "expert_intermediate_size": 56, |
| "router_prefix_length": 32, |
| "router_jitter_noise": 0.01, |
| "router_aux_loss_coeff": 0.01, |
| "router_z_loss_coeff": 0.001, |
| "expert_output_scale": 3.605551275463989, |
| "max_position_embeddings": 4096, |
| "rope_theta": 100000.0, |
| "rms_norm_eps": 1e-06, |
| "initializer_range": 0.02, |
| "use_cache": true, |
| "transformers_version": "5.15.0", |
| "architectures": [ |
| "SLMoEForCausalLM" |
| ], |
| "output_hidden_states": false, |
| "return_dict": true, |
| "dtype": null, |
| "chunk_size_feed_forward": 0, |
| "is_encoder_decoder": false, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "problem_type": null, |
| "_name_or_path": "Banaxi-Tech/slmoe-test", |
| "tie_word_embeddings": true, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "pad_token_id": 0, |
| "unk_token_id": 3, |
| "model_type": "slmoe", |
| "output_attentions": false, |
| "auto_map": { |
| "AutoConfig": "configuration_slmoe.SLMoEConfig", |
| "AutoModelForCausalLM": "modeling_slmoe.SLMoEForCausalLM" |
| }, |
| "torch_dtype": "float32" |
| } |
|
|
