Text Generation
Transformers
Safetensors
PyTorch
nvidia
suhara's picture
Update config.json
c690720 verified
{
"architectures": [
"NemotronHForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_nemotron_h.NemotronHConfig",
"AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
},
"bos_token_id": 1,
"chunk_size": 128,
"conv_kernel": 4,
"eos_token_id": 2,
"head_dim": 128,
"hidden_dropout": 0.0,
"hidden_size": 5120,
"hybrid_override_pattern": "M-M-M-M*-M-M-M-M*-M-M-M-M*-M-M-M-M*-M-M-M-M*-M-M-M-M*-M-M-M-M-",
"initializer_range": 0.02,
"intermediate_size": 20480,
"layer_norm_epsilon": 1e-05,
"mamba_head_dim": 80,
"mamba_hidden_act": "silu",
"mamba_num_groups": 8,
"mamba_num_heads": 128,
"mamba_proj_bias": false,
"mamba_state_dim": 128,
"max_position_embeddings": 131072,
"mlp_bias": false,
"mlp_hidden_act": "relu2",
"model_type": "nemotron_h",
"n_groups": 8,
"num_attention_heads": 40,
"num_hidden_layers": 62,
"num_key_value_heads": 8,
"num_logits_to_keep": 1,
"num_query_groups": 8,
"pad_token_id": 0,
"rescale_prenorm_residual": true,
"residual_in_fp32": false,
"rms_norm_eps": 1e-05,
"sliding_window": null,
"ssm_state_size": 128,
"tie_word_embeddings": false,
"time_step_floor": 0.0001,
"time_step_limit": [
0.0,
Infinity
],
"time_step_max": 0.1,
"time_step_min": 0.001,
"time_step_rank": 256,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.2",
"use_bias": false,
"use_cache": true,
"use_conv_bias": true,
"use_mamba_kernels": true,
"vocab_size": 131072
}