| { | |
| "architectures": [ | |
| "MLAForCausalLM" | |
| ], | |
| "bos_token_id": 0, | |
| "dtype": "float32", | |
| "elementwise_affine": true, | |
| "eos_token_id": 1, | |
| "fuse_cross_entropy": true, | |
| "fuse_linear_cross_entropy": false, | |
| "fuse_norm": true, | |
| "fuse_swiglu": true, | |
| "hidden_act": "swish", | |
| "hidden_ratio": 4, | |
| "hidden_size": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 896, | |
| "kv_lora_rank": 64, | |
| "max_position_embeddings": 2048, | |
| "model_type": "mla", | |
| "norm_eps": 1e-05, | |
| "num_heads": 4, | |
| "num_hidden_layers": 35, | |
| "q_lora_rank": 32, | |
| "qk_head_dim": 96, | |
| "qk_nope_head_dim": 64, | |
| "qk_rope_head_dim": 32, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.1", | |
| "use_cache": true, | |
| "use_l2warp": false, | |
| "v_head_dim": 32, | |
| "vocab_size": 256, | |
| "window_size": null | |
| } | |