config.json

{
  "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"
  ],
  "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": {
        "format": "int-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "token",
          "symmetric": false,
          "type": "int",
          "zp_dtype": "torch.int8"
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "channel",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        }
      }
    },
    "format": "int-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.13.1.dev0+g797d301.d20251217"
  },
  "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": "4.57.0",
  "use_cache": true,
  "vocab_size": 201088
}