config.json

{
  "_name_or_path": "inceptionai/jais-family-30b-16k-chat",
  "activation_function": "swiglu",
  "alibi_scaling": null,
  "architectures": [
    "JAISLMHeadModel"
  ],
  "attn_pdrop": 0.0,
  "auto_map": {
    "AutoConfig": "inceptionai/jais-family-30b-16k-chat--configuration_jais.JAISConfig",
    "AutoModel": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISModel",
    "AutoModelForCausalLM": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISLMHeadModel",
    "AutoModelForQuestionAnswering": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISForQuestionAnswering",
    "AutoModelForSequenceClassification": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISForSequenceClassification",
    "AutoModelForTokenClassification": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISForTokenClassification"
  },
  "bos_token_id": 0,
  "embd_pdrop": 0.0,
  "eos_token_id": 0,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "jais",
  "mup_embeddings_scale": 14.6,
  "mup_output_alpha": 2.22,
  "mup_scale_qk_dot_by_d": true,
  "mup_width_scale": 0.03571428571428571,
  "n_embd": 7168,
  "n_head": 56,
  "n_inner": 19114,
  "n_layer": 48,
  "n_positions": 16384,
  "pad_token_id": 0,
  "position_embedding_type": "alibi",
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "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": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.0,
  "rotary_dim": null,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "torch_dtype": "float16",
  "transformers_version": "4.44.0",
  "use_cache": true,
  "vocab_size": 84992
}