{ "architectures": [ "GptOssForCausalLM" ], "attention_bias": true, "attention_dropout": 0.0, "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, "quantization_config": { "algo_config": [], "exclude": [ "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.v_proj", "model.layers.0.self_attn.o_proj", "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.v_proj", "model.layers.1.self_attn.o_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.v_proj", "model.layers.2.self_attn.o_proj", "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.v_proj", "model.layers.3.self_attn.o_proj", "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.v_proj", "model.layers.4.self_attn.o_proj", "model.layers.5.self_attn.q_proj", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.v_proj", "model.layers.5.self_attn.o_proj", "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.v_proj", "model.layers.6.self_attn.o_proj", "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.v_proj", "model.layers.7.self_attn.o_proj", "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.v_proj", "model.layers.8.self_attn.o_proj", "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.v_proj", "model.layers.9.self_attn.o_proj", "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.v_proj", "model.layers.10.self_attn.o_proj", "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.v_proj", "model.layers.11.self_attn.o_proj", "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.v_proj", "model.layers.12.self_attn.o_proj", "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.v_proj", "model.layers.13.self_attn.o_proj", "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.v_proj", "model.layers.14.self_attn.o_proj", "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.v_proj", "model.layers.15.self_attn.o_proj", "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.v_proj", "model.layers.16.self_attn.o_proj", "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.v_proj", "model.layers.17.self_attn.o_proj", "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.v_proj", "model.layers.18.self_attn.o_proj", "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.v_proj", "model.layers.19.self_attn.o_proj", "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.v_proj", "model.layers.20.self_attn.o_proj", "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.v_proj", "model.layers.21.self_attn.o_proj", "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.v_proj", "model.layers.22.self_attn.o_proj", "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.v_proj", "model.layers.23.self_attn.o_proj", "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.v_proj", "model.layers.24.self_attn.o_proj", "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.v_proj", "model.layers.25.self_attn.o_proj", "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.v_proj", "model.layers.26.self_attn.o_proj", "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.v_proj", "model.layers.27.self_attn.o_proj", "model.layers.28.self_attn.q_proj", "model.layers.28.self_attn.k_proj", "model.layers.28.self_attn.v_proj", "model.layers.28.self_attn.o_proj", "model.layers.29.self_attn.q_proj", "model.layers.29.self_attn.k_proj", "model.layers.29.self_attn.v_proj", "model.layers.29.self_attn.o_proj", "model.layers.30.self_attn.q_proj", "model.layers.30.self_attn.k_proj", "model.layers.30.self_attn.v_proj", "model.layers.30.self_attn.o_proj", "model.layers.31.self_attn.q_proj", "model.layers.31.self_attn.k_proj", "model.layers.31.self_attn.v_proj", "model.layers.31.self_attn.o_proj", "model.layers.32.self_attn.q_proj", "model.layers.32.self_attn.k_proj", "model.layers.32.self_attn.v_proj", "model.layers.32.self_attn.o_proj", "model.layers.33.self_attn.q_proj", "model.layers.33.self_attn.k_proj", "model.layers.33.self_attn.v_proj", "model.layers.33.self_attn.o_proj", "model.layers.34.self_attn.q_proj", "model.layers.34.self_attn.k_proj", "model.layers.34.self_attn.v_proj", "model.layers.34.self_attn.o_proj", "model.layers.35.self_attn.q_proj", "model.layers.35.self_attn.k_proj", "model.layers.35.self_attn.v_proj", "model.layers.35.self_attn.o_proj", "lm_head" ], "export": { "kv_cache_group": [], "min_kv_scale": 0.0, "pack_method": "reorder", "weight_format": "real_quantized", "weight_merge_groups": null }, "global_quant_config": { "bias": null, "input_tensors": { "ch_axis": null, "dtype": "fp8_e4m3", "group_size": null, "is_dynamic": false, "is_scale_quant": false, "mx_element_dtype": null, "observer_cls": "PerTensorMinMaxObserver", "qscheme": "per_tensor", "round_method": "half_even", "scale_calculation_mode": null, "scale_format": null, "scale_type": null, "symmetric": true }, "output_tensors": null, "target_device": null, "weight": { "ch_axis": -1, "dtype": "fp4", "group_size": 32, "is_dynamic": false, "is_scale_quant": false, "mx_element_dtype": null, "observer_cls": "PerBlockMXObserver", "qscheme": "per_group", "round_method": "half_even", "scale_calculation_mode": "even", "scale_format": "e8m0", "scale_type": "float", "symmetric": null } }, "kv_cache_quant_config": {}, "layer_quant_config": {}, "layer_type_quant_config": {}, "quant_method": "quark", "quant_mode": "eager_mode", "softmax_quant_spec": null, "version": "0.10+cdd93fc33d" }, "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, "torch_dtype": "bfloat16", "transformers_version": "4.55.1", "use_cache": true, "vocab_size": 201088 }