trillionlabs/NemoSlides
693
1{2 "architectures": [3 "NemotronHForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "auto_map": {8 "AutoConfig": "configuration_nemotron_h.NemotronHConfig",9 "AutoModel": "modeling_nemotron_h.NemotronHForCausalLM",10 "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"11 },12 "bos_token_id": 1,13 "chunk_size": 128,14 "conv_kernel": 4,15 "dtype": "bfloat16",16 "eos_token_id": 2,17 "expand": 2,18 "head_dim": 128,19 "hidden_dropout": 0.0,20 "hidden_size": 2688,21 "hybrid_override_pattern": "MEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEMEM*EMEMEMEME",22 "initializer_range": 0.02,23 "intermediate_size": 1856,24 "layer_norm_epsilon": 1e-05,25 "mamba_head_dim": 64,26 "mamba_hidden_act": "silu",27 "mamba_num_heads": 64,28 "mamba_proj_bias": false,29 "mamba_ssm_cache_dtype": "float32",30 "max_position_embeddings": 262144,31 "mlp_bias": false,32 "mlp_hidden_act": "relu2",33 "model_type": "nemotron_h",34 "moe_intermediate_size": 1856,35 "moe_shared_expert_intermediate_size": 3712,36 "n_group": 1,37 "n_groups": 8,38 "n_routed_experts": 128,39 "n_shared_experts": 1,40 "norm_eps": 1e-05,41 "norm_topk_prob": true,42 "num_attention_heads": 32,43 "num_experts_per_tok": 6,44 "num_hidden_layers": 52,45 "num_key_value_heads": 2,46 "num_logits_to_keep": 1,47 "pad_token_id": 0,48 "partial_rotary_factor": 1.0,49 "rescale_prenorm_residual": true,50 "residual_in_fp32": false,51 "rope_theta": 10000,52 "routed_scaling_factor": 2.5,53 "sliding_window": null,54 "ssm_state_size": 128,55 "tie_word_embeddings": false,56 "time_step_floor": 0.0001,57 "time_step_limit": [58 0.0,59 {60 "__float__": "Infinity"61 }62 ],63 "time_step_max": 0.1,64 "time_step_min": 0.001,65 "topk_group": 1,66 "transformers_version": "5.5.4",67 "use_bias": false,68 "use_cache": true,69 "use_conv_bias": true,70 "use_mamba_kernels": true,71 "vocab_size": 13107272}73 