{
  "_name_or_path": "/model/TinyLlama-1.1B-Chat-v1.0",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "damp_percent": 0.01,
    "desc_act": true,
    "group_size": 128,
    "lm_head": false,
    "meta": {
      "amp": true,
      "batch_size": 1,
      "data_type": "int",
      "dynamic_max_gap": -1,
      "enable_full_range": false,
      "enable_minmax_tuning": true,
      "enable_quanted_input": true,
      "gradient_accumulate_steps": 1,
      "iters": 200,
      "low_gpu_mem_usage": true,
      "lr": null,
      "lr_scheduler": null,
      "minmax_lr": null,
      "nblocks": 1,
      "not_use_best_mse": false,
      "nsamples": 512,
      "quantizer": "gptqmodel:0.9.8-dev0",
      "sampler": "rand",
      "scale_dtype": "fp16",
      "seed": 42,
      "seqlen": 2048
    },
    "model_file_base_name": null,
    "model_name_or_path": null,
    "quant_method": "auto_round",
    "static_groups": false,
    "sym": true,
    "true_sequential": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}