| { |
| "architectures": [ |
| "NemotronHForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "chunk_size": 128, |
| "conv_kernel": 4, |
| "dtype": "bfloat16", |
| "eos_token_id": 2, |
| "expand": 2, |
| "head_dim": 128, |
| "hidden_dropout": 0.0, |
| "hidden_size": 288, |
| "layers_block_type": [ |
| "mamba", "moe", "mamba", "attention", "moe", "mamba", "moe" |
| ], |
| "initializer_range": 0.02, |
| "intermediate_size": 384, |
| "layer_norm_epsilon": 1e-05, |
| "mamba_head_dim": 64, |
| "mamba_hidden_act": "silu", |
| "mamba_num_heads": 128, |
| "mamba_proj_bias": false, |
| "mamba_ssm_cache_dtype": "float32", |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "mlp_hidden_act": "relu2", |
| "model_type": "nemotron_h", |
| "moe_intermediate_size": 384, |
| "moe_latent_size": 576, |
| "moe_shared_expert_intermediate_size": 5376, |
| "moe_shared_expert_overlap": false, |
| "mtp_layers_block_type": [ |
| "attention", "moe" |
| ], |
| "n_group": 1, |
| "n_groups": 8, |
| "n_routed_experts": 128, |
| "n_shared_experts": 1, |
| "norm_eps": 1e-05, |
| "norm_topk_prob": true, |
| "num_attention_heads": 40, |
| "num_experts_per_tok": 6, |
| "num_hidden_layers": 7, |
| "num_key_value_heads": 2, |
| "num_logits_to_keep": 1, |
| "num_nextn_predict_layers": 2, |
| "pad_token_id": 0, |
| "partial_rotary_factor": 1.0, |
| "rescale_prenorm_residual": true, |
| "residual_in_fp32": false, |
| "rope_theta": 10000, |
| "routed_scaling_factor": 5.0, |
| "sliding_window": null, |
| "ssm_state_size": 128, |
| "tie_word_embeddings": false, |
| "time_step_floor": 0.0001, |
| "time_step_max": 0.1, |
| "time_step_min": 0.001, |
| "topk_group": 1, |
| "transformers_version": "4.57.6", |
| "use_bias": false, |
| "use_cache": true, |
| "use_conv_bias": true, |
| "use_mamba_kernels": true, |
| "vocab_size": 131072 |
| } |
|
|
