| { |
| "architectures": [ |
| "GptOssForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "eos_token_id": 200002, |
| "experts_per_token": 4, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2880, |
| "initial_context_length": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 2880, |
| "layer_types": [ |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 131072, |
| "model_type": "gpt_oss", |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 8, |
| "num_local_experts": 128, |
| "output_router_logits": false, |
| "pad_token_id": 199999, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 32.0, |
| "original_max_position_embeddings": 4096, |
| "rope_type": "yarn", |
| "truncate": false |
| }, |
| "rope_theta": 150000, |
| "router_aux_loss_coef": 0.9, |
| "sliding_window": 128, |
| "swiglu_limit": 7.0, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.6", |
| "use_cache": true, |
| "vocab_size": 201088, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "input_activations": { |
| "dynamic": false, |
| "num_bits": 4, |
| "type": "float", |
| "group_size": 16 |
| }, |
| "weights": { |
| "dynamic": false, |
| "num_bits": 4, |
| "type": "float", |
| "group_size": 16 |
| }, |
| "targets": [ |
| "Linear" |
| ] |
| } |
| }, |
| "ignore": [ |
| "lm_head", |
| "model.layers.0.self_attn*", |
| "model.layers.1.self_attn*", |
| "model.layers.10.self_attn*", |
| "model.layers.11.self_attn*", |
| "model.layers.12.self_attn*", |
| "model.layers.13.self_attn*", |
| "model.layers.14.self_attn*", |
| "model.layers.15.self_attn*", |
| "model.layers.16.self_attn*", |
| "model.layers.17.self_attn*", |
| "model.layers.18.self_attn*", |
| "model.layers.19.self_attn*", |
| "model.layers.2.self_attn*", |
| "model.layers.20.self_attn*", |
| "model.layers.21.self_attn*", |
| "model.layers.22.self_attn*", |
| "model.layers.23.self_attn*", |
| "model.layers.24.self_attn*", |
| "model.layers.25.self_attn*", |
| "model.layers.26.self_attn*", |
| "model.layers.27.self_attn*", |
| "model.layers.28.self_attn*", |
| "model.layers.29.self_attn*", |
| "model.layers.3.self_attn*", |
| "model.layers.30.self_attn*", |
| "model.layers.31.self_attn*", |
| "model.layers.32.self_attn*", |
| "model.layers.33.self_attn*", |
| "model.layers.34.self_attn*", |
| "model.layers.35.self_attn*", |
| "model.layers.4.self_attn*", |
| "model.layers.5.self_attn*", |
| "model.layers.6.self_attn*", |
| "model.layers.7.self_attn*", |
| "model.layers.8.self_attn*", |
| "model.layers.9.self_attn*" |
| ], |
| "quant_algo": "NVFP4", |
| "kv_cache_scheme": { |
| "dynamic": false, |
| "num_bits": 8, |
| "type": "float" |
| }, |
| "producer": { |
| "name": "modelopt", |
| "version": "0.45.0.dev40+g9d2e6087d" |
| }, |
| "quant_method": "modelopt" |
| } |
| } |
