config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "meta-llama/Llama-2-70b-hf",
  "anyprec": {
    "arch_config": {
      "layers_name": "layers",
      "model_name": "model",
      "module_names": [
        "self_attn.q_proj",
        "self_attn.k_proj",
        "self_attn.v_proj",
        "self_attn.o_proj",
        "mlp.gate_proj",
        "mlp.up_proj",
        "mlp.down_proj"
      ]
    },
    "group_count": 1,
    "parent_precision": 4,
    "seed_precision": 4
  },
  "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,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 32000
}