{ "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" ], "max_position_embeddings": 131072, "model_type": "gpt_oss", "num_attention_heads": 64, "num_experts_per_tok": 4, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_local_experts": 32, "output_router_logits": false, "pad_token_id": 199999, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "float" } } }, "format": "float-quantized", "global_compression_ratio": null, "ignore": [ "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", "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.10.3.dev27+g0731aa5" }, "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": "4.55.0", "use_cache": true, "vocab_size": 201088 }