{
  "_name_or_path": "debisoft/mpt-7b-8k-peft-compatible",
  "architectures": [
    "MptForCausalLM"
  ],
  "attn_config": {
    "model_type": ""
  },
  "auto_map": {
    "AutoConfig": "debisoft/mpt-7b-8k-peft-compatible--configuration_mpt.MPTConfig",
    "AutoModelForCausalLM": "debisoft/mpt-7b-8k-peft-compatible--modeling_mpt.MPTForCausalLM"
  },
  "d_model": 4096,
  "emb_pdrop": 0,
  "embedding_fraction": 1.0,
  "expansion_ratio": 4,
  "init_config": {
    "emb_init_std": null,
    "emb_init_uniform_lim": null,
    "fan_mode": "fan_in",
    "init_div_is_residual": true,
    "init_gain": 0.0,
    "init_nonlinearity": "relu",
    "init_std": null,
    "name": "kaiming_normal_",
    "verbose": 0
  },
  "init_device": "cpu",
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "learned_pos_emb": true,
  "logit_scale": null,
  "max_seq_len": 8192,
  "model_type": "mpt",
  "n_heads": 32,
  "n_layers": 32,
  "no_bias": true,
  "norm_type": "low_precision_layernorm",
  "resid_pdrop": 0,
  "tokenizer_name": "EleutherAI/gpt-neox-20b",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.35.2",
  "use_cache": false,
  "verbose": 0,
  "vocab_size": 50432
}