| { | |
| "architectures": [ | |
| "Lfm2MoeForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "conv_L_cache": 3, | |
| "conv_bias": false, | |
| "dtype": "float32", | |
| "eos_token_id": 7, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "is_decoder": true, | |
| "layer_types": [ | |
| "full_attention", | |
| "conv" | |
| ], | |
| "max_position_embeddings": 512, | |
| "model_type": "lfm2_moe", | |
| "moe_intermediate_size": 16, | |
| "norm_eps": 1e-05, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 2, | |
| "num_dense_layers": 1, | |
| "num_experts": 8, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 0, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "routed_scaling_factor": 1.0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.16.0.dev0", | |
| "use_cache": true, | |
| "use_expert_bias": true, | |
| "vocab_size": 64400 | |
| } | |