config.json

{
  "architectures": [
    "LlamaForCausalLMEagle3"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "fc_norm": true,
  "norm_output": true,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 6144,
  "initializer_range": 0.02,
  "intermediate_size": 18432,
  "max_position_embeddings": 1048576,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 1,
  "num_key_value_heads": 64,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 200064,
  "draft_vocab_size": 200064,
  "_torchspec_version": "0.1.0",
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "format": "pack-quantized",
    "quantization_status": "compressed",
    "config_groups": {
      "group_0": {
        "targets": [
          "Linear"
        ],
        "weights": {
          "num_bits": 4,
          "type": "int",
          "symmetric": true,
          "strategy": "group",
          "group_size": 128,
          "dynamic": false
        }
      },
      "group_embed": {
        "targets": [
          "Embedding"
        ],
        "weights": {
          "num_bits": 4,
          "type": "int",
          "symmetric": true,
          "strategy": "group",
          "group_size": 64,
          "dynamic": false
        }
      },
      "group_lmhead": {
        "targets": [
          "re:.*lm_head.*"
        ],
        "weights": {
          "num_bits": 4,
          "type": "int",
          "symmetric": true,
          "strategy": "group",
          "group_size": 128,
          "dynamic": false
        }
      }
    },
    "ignore": [
      "re:.*norm.*"
    ]
  }
}