config.json

{
  "architectures": [
    "MPTForCausalLM"
  ],
  "attn_config": {
    "alibi": false,
    "alibi_bias_max": 8,
    "attn_impl": "torch",
    "attn_pdrop": 0.0,
    "attn_type": "multihead_attention",
    "attn_uses_sequence_id": false,
    "clip_qkv": null,
    "prefix_lm": false,
    "qk_ln": true,
    "softmax_scale": null
  },
  "auto_map": {
    "AutoConfig": "configuration_mpt.MPTConfig",
    "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
  },
  "d_model": 4096,
  "emb_pdrop": 0.0,
  "embedding_fraction": 0.1,
  "expansion_ratio": 4,
  "fc_type": "torch",
  "ffn_config": {
    "fc_type": "torch",
    "ffn_type": "mptmlp"
  },
  "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_config_defaults": {
    "init_std": 0.02
  },
  "init_device": "cpu",
  "learned_pos_emb": true,
  "logit_scale": "inv_sqrt_d_model",
  "max_seq_len": 2048,
  "model_type": "mpt",
  "n_heads": 32,
  "n_layers": 32,
  "no_bias": false,
  "norm_type": "low_precision_layernorm",
  "resid_pdrop": 0.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.34.1",
  "use_cache": false,
  "vocab_size": 256000
}