{
  "_name_or_path": "sea-lion-3b",
  "architectures": [
    "MptForCausalLM"
  ],
  "attn_config": {
    "alibi": false,
    "model_type": ""
  },
  "auto_map": {
    "AutoConfig": "configuration_mpt.MPTConfig",
    "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
  },
  "d_model": 2560,
  "emb_pdrop": 0.0,
  "embedding_fraction": 1.0,
  "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_device": "cpu",
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "learned_pos_emb": true,
  "logit_scale": null,
  "max_seq_len": 2048,
  "model_type": "mpt",
  "n_heads": 20,
  "n_layers": 32,
  "no_bias": false,
  "norm_type": "low_precision_layernorm",
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "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"
  },
  "resid_pdrop": 0.0,
  "torch_dtype": "float16",
  "transformers_version": "4.47.1",
  "use_cache": false,
  "verbose": 0,
  "vocab_size": 256000
}