| { |
| "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 |
| } |
|
|
