config.json

{
  "_name_or_path": "maddi99/blm_g4_16",
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "BloomForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attention_softmax_in_fp32": true,
  "bias_dropout_fusion": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_dropout": 0.0,
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "masked_softmax_fusion": true,
  "model_type": "bloom",
  "n_head": 32,
  "n_inner": null,
  "n_layer": 30,
  "offset_alibi": 100,
  "pad_token_id": 3,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "damp_percent": 0.01,
    "desc_act": false,
    "group_size": 128,
    "is_marlin_format": false,
    "model_file_base_name": null,
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": true
  },
  "skip_bias_add": true,
  "skip_bias_add_qkv": false,
  "slow_but_exact": false,
  "torch_dtype": "float16",
  "transformers_version": "4.40.0",
  "unk_token_id": 0,
  "use_cache": true,
  "vocab_size": 250880
}