| { | |
| "architectures": [ | |
| "Dots1ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "eos_token_id": 151643, | |
| "first_k_dense_replace": 1, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10944, | |
| "max_position_embeddings": 32768, | |
| "model_type": "dots1", | |
| "moe_intermediate_size": 1408, | |
| "moe_layer_freq": 1, | |
| "n_routed_experts": 128, | |
| "n_shared_experts": 2, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 6, | |
| "num_hidden_layers": 62, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000000, | |
| "routed_scaling_factor": 2.5, | |
| "sliding_window": null, | |
| "scoring_func": "noaux_tc", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |