| { | |
| "activation_function": "silu", | |
| "architectures": [ | |
| "JetMoeForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "aux_loss_coef": 0.01, | |
| "bos_token_id": 1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 37, | |
| "kv_channels": 8, | |
| "max_position_embeddings": 512, | |
| "model_type": "jetmoe", | |
| "num_attention_heads": 4, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "num_local_experts": 4, | |
| "output_router_logits": false, | |
| "pad_token_id": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.16.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |