{
  "_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--allenai--OLMoE-1B-7B-0924-Instruct/snapshots/7f1c97f440f06ce36705e4f2b843edb5925f4498",
  "architectures": [
    "OlmoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "clip_qkv": null,
  "eos_token_id": 50279,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 1024,
  "max_position_embeddings": 4096,
  "model_type": "olmoe",
  "norm_topk_prob": false,
  "num_attention_heads": 16,
  "num_experts": 64,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 16,
  "num_key_value_heads": 16,
  "output_router_logits": false,
  "pad_token_id": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.01,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.0.dev0",
  "use_cache": true,
  "vocab_size": 50304,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor",
          "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": "tensor",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": 1.5859487566941963,
    "ignore": [
      "model.layers.0.mlp.gate",
      "model.layers.1.mlp.gate",
      "model.layers.2.mlp.gate",
      "model.layers.3.mlp.gate",
      "model.layers.4.mlp.gate",
      "model.layers.5.mlp.gate",
      "model.layers.6.mlp.gate",
      "model.layers.7.mlp.gate",
      "model.layers.8.mlp.gate",
      "model.layers.9.mlp.gate",
      "model.layers.10.mlp.gate",
      "model.layers.11.mlp.gate",
      "model.layers.12.mlp.gate",
      "model.layers.13.mlp.gate",
      "model.layers.14.mlp.gate",
      "model.layers.15.mlp.gate",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  }
}