{
  "_name_or_path": "roneneldan/TinyStories-33M",
  "activation_function": "gelu_new",
  "architectures": [
    "GPTNeoForCausalLM"
  ],
  "attention_dropout": 0,
  "attention_layers": [
    "global",
    "local",
    "global",
    "local"
  ],
  "attention_types": [
    [
      [
        "global",
        "local"
      ],
      2
    ]
  ],
  "bos_token_id": 50256,
  "classifier_dropout": 0.1,
  "embed_dropout": 0,
  "eos_token_id": 50256,
  "gradient_checkpointing": false,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": null,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "gpt_neo",
  "num_heads": 16,
  "num_layers": 4,
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": null,
    "cache_block_outputs": true,
    "damp_percent": 0.1,
    "dataset": "c4",
    "desc_act": false,
    "exllama_config": {
      "version": 1
    },
    "group_size": 128,
    "max_input_length": null,
    "model_seqlen": null,
    "module_name_preceding_first_block": null,
    "modules_in_block_to_quantize": null,
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": false,
    "use_exllama": true
  },
  "resid_dropout": 0,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "torch_dtype": "float16",
  "transformers_version": "4.37.0.dev0",
  "use_cache": true,
  "vocab_size": 50257,
  "window_size": 256
}