{
  "_name_or_path": "meta-llama/Llama-2-70b-hf",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quip_params": {
    "codebook": "E8P12",
    "codebook_version": 1,
    "codesz": 8,
    "harp": {
      "chunk_size": 1048576,
      "early_stop_min_rel_improve": 0.01,
      "early_stop_window": 0,
      "fixed_mixer": "had_or_qr",
      "grad_clip": null,
      "harp_b": 8,
      "harp_max_b": 8,
      "harp_passes": 1,
      "hbd_block": 8,
      "hbd_lambda": 0.1,
      "kron_fallback": false,
      "lr_u": 0.03,
      "lr_v": 0.03,
      "ordering_mode": "stride",
      "q_recompute_every": 1,
      "reg_theta": 0.0,
      "steps": 1200,
      "strategy": "proxy",
      "theta_clip": null,
      "theta_init_scale": 0.0,
      "use_givens_b2": false
    },
    "idx_dtype": "torch.int64",
    "incoh_mode": "harp",
    "lora_rank": 0,
    "model_version": 1,
    "packsz": 4,
    "quant_layers": null,
    "rescale_WH": false,
    "resid_scale_override": -1
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "vocab_size": 32000
}