{
  "_name_or_path": "/home/alexm/models/marlin_24/tinyllama-24-gptq-8bit-channelwise-src",
  "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,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 8,
    "checkpoint_format": "marlin_24",
    "damp_percent": 0.1,
    "desc_act": false,
    "group_size": -1,
    "model_file_base_name": "model",
    "model_name_or_path": "/home/alexm/models/marlin_24/tinyllama-24-gptq-8bit-channelwise-src",
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": false
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.40.1",
  "use_cache": true,
  "vocab_size": 32000
}