| { |
| "architectures": [ |
| "NemotronHForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_nemotron_h.NemotronHConfig", |
| "AutoModel": "modeling_nemotron_h.NemotronHForCausalLM", |
| "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "chunk_size": 128, |
| "conv_kernel": 4, |
| "dtype": null, |
| "eos_token_id": 2, |
| "expand": 2, |
| "head_dim": 128, |
| "hidden_dropout": 0.0, |
| "hidden_size": 2688, |
| "hybrid_override_pattern": "MEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEMEM*EMEMEMEME", |
| "initializer_range": 0.02, |
| "intermediate_size": 1856, |
| "layer_norm_epsilon": 1e-05, |
| "mamba_head_dim": 64, |
| "mamba_hidden_act": "silu", |
| "mamba_num_heads": 64, |
| "mamba_proj_bias": false, |
| "mamba_ssm_cache_dtype": "float32", |
| "max_position_embeddings": 262144, |
| "mlp_bias": false, |
| "mlp_hidden_act": "relu2", |
| "model_type": "nemotron_h", |
| "moe_intermediate_size": 1856, |
| "moe_shared_expert_intermediate_size": 3712, |
| "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": 32, |
| "num_experts_per_tok": 6, |
| "num_hidden_layers": 52, |
| "num_key_value_heads": 2, |
| "num_logits_to_keep": 1, |
| "pad_token_id": 0, |
| "partial_rotary_factor": 1.0, |
| "quantization_config": { |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": true, |
| "dynamic": { |
| "down_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "experts.down_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "experts.gate_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "experts.up_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "gate_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "mixer.conv1d": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "mixer.dt_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "mixer.experts": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "mixer.in_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "mixer.k_proj": { |
| "bits": 8, |
| "group_size": 128 |
| }, |
| "mixer.o_proj": { |
| "bits": 8, |
| "group_size": 128 |
| }, |
| "mixer.out_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "mixer.q_proj": { |
| "bits": 8, |
| "group_size": 128 |
| }, |
| "mixer.shared_experts": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "mixer.v_proj": { |
| "bits": 8, |
| "group_size": 128 |
| }, |
| "mixer.x_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "shared_experts.down_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "shared_experts.gate_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "shared_experts.up_proj": { |
| "bits": 4, |
| "group_size": 128 |
| }, |
| "up_proj": { |
| "bits": 4, |
| "group_size": 128 |
| } |
| }, |
| "format": "gptq", |
| "group_size": 128, |
| "lm_head": false, |
| "meta": { |
| "act_group_aware": false, |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.01, |
| "gptaq": false, |
| "gptaq_alpha": 0.25, |
| "mse": 0.0, |
| "quantizer": [ |
| "gptqmodel:5.6.12" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel" |
| }, |
| "pack_dtype": "int32", |
| "pack_impl": "cpu", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "rescale_prenorm_residual": true, |
| "residual_in_fp32": false, |
| "rope_theta": 10000, |
| "routed_scaling_factor": 2.5, |
| "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, |
| "topk_group": 1, |
| "transformers_version": "4.57.3", |
| "use_bias": false, |
| "use_cache": true, |
| "use_conv_bias": true, |
| "use_mamba_kernels": true, |
| "vocab_size": 131072 |
| } |
|
|
