{
  "_name_or_path": "AI-Sweden-Models/gpt-sw3-40b",
  "activation_function": "gelu",
  "apply_query_key_layer_scaling": true,
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 2,
  "embd_pdrop": 0.1,
  "eos_token_id": 3,
  "initializer_range": 0.007,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_embd": 8192,
  "n_head": 64,
  "n_inner": 32768,
  "n_layer": 48,
  "n_positions": 2048,
  "normalize_attention_scores": true,
  "pad_token_id": 0,
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": "transformer.h",
    "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": 2048,
    "module_name_preceding_first_block": [
      "transformer.wte",
      "transformer.wpe",
      "transformer.drop"
    ],
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": true,
    "use_exllama": false
  },
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "tokenizer_class": "GPTSw3Tokenizer",
  "torch_dtype": "float16",
  "transformers_version": "4.36.0.dev0",
  "use_cache": true,
  "vocab_size": 64000
}