{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "float16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": null,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default",
    "type": "default"
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.11.0",
  "use_cache": true,
  "vocab_size": 32000,
  "base_model": "meta-llama/Llama-2-7b-hf",
  "quantization": {
    "method": "rl-mpq",
    "format": "fake-quant-fp16",
    "scenario": "Balanced",
    "avg_bits": 4.375,
    "description": "Per-layer mixed bit-width via PPO-trained policy (not GPTQ/AWQ)"
  },
  "rlmpq": {
    "framework": "RL-NMP-Model-Quantasation",
    "scenario": "Balanced",
    "scenario_label": "Balanced",
    "repo_id": "AvoCahDoe/llama-2-7b-rlmpq-balanced",
    "grouped_repo": "AvoCahDoe/llama-2-7b-rlmpq",
    "collection_title": "RL-MPQ \u2014 Llama 2 7B"
  }
}