config.json

{
  "_name_or_path": "/tmp/tmpsjdscbbu",
  "activation_function": "gelu_new",
  "architectures": [
    "GPTNeoForCausalLM"
  ],
  "attention_dropout": 0,
  "attention_layers": [
    "global",
    "local",
    "global",
    "local",
    "global",
    "local",
    "global",
    "local"
  ],
  "attention_types": [
    [
      [
        "global",
        "local"
      ],
      4
    ]
  ],
  "bos_token_id": 50256,
  "classifier_dropout": 0.1,
  "embed_dropout": 0,
  "eos_token_id": 50256,
  "gradient_checkpointing": false,
  "hidden_size": 128,
  "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": 8,
  "quantization_config": {
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "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": "4.37.1",
  "use_cache": true,
  "vocab_size": 50257,
  "window_size": 256
}