{
  "_name_or_path": "jbochi/madlad400-3b-mt",
  "architectures": [
    "T5ForConditionalGeneration"
  ],
  "classifier_dropout": 0.0,
  "d_ff": 8192,
  "d_kv": 128,
  "d_model": 1024,
  "decoder_start_token_id": 0,
  "dense_act_fn": "gelu_new",
  "dropout_rate": 0.1,
  "eos_token_id": 2,
  "feed_forward_proj": "gated-gelu",
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": true,
  "layer_norm_epsilon": 1e-06,
  "model_type": "t5",
  "n_positions": 512,
  "num_decoder_layers": 32,
  "num_heads": 16,
  "num_layers": 32,
  "output_past": true,
  "pad_token_id": 1,
  "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"
  },
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "task_specific_params": {},
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.39.3",
  "use_cache": true,
  "vocab_size": 256000
}