config.json

{
  "architectures": [
    "Dots1ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "eos_token_id": 151645,
  "first_k_dense_replace": 1,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 10944,
  "max_position_embeddings": 32768,
  "max_window_layers": 62,
  "model_type": "dots1",
  "moe_intermediate_size": 1408,
  "moe_layer_freq": 1,
  "n_group": 1,
  "n_routed_experts": 128,
  "n_shared_experts": 2,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 62,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "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": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000000,
  "routed_scaling_factor": 2.5,
  "scoring_func": "sigmoid",
  "sliding_window": null,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "topk_method": "noaux_tc",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.0.dev0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}