config.json

{
  "_name_or_path": "ai-forever/mGPT",
  "activation_function": "gelu_new",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 0,
  "embd_pdrop": 0.1,
  "eos_token_id": 5,
  "gradient_checkpointing": false,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_ctx": 2048,
  "n_embd": 2048,
  "n_head": 16,
  "n_inner": null,
  "n_layer": 24,
  "n_positions": 2048,
  "pad_token_id": 1,
  "quantization_config": {
    "bnb_4bit_compute_dtype": "float32",
    "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": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "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,
  "torch_dtype": "float16",
  "transformers_version": "4.36.2",
  "use_cache": true,
  "vocab_size": 100000
}