{
  "architectures": [
    "MptForQuestionAnswering"
  ],
  "attention_dropout": 0.1,
  "attn_config": {
    "alibi": true,
    "alibi_bias_max": 8,
    "attn_impl": "torch",
    "attn_pdrop": 0,
    "attn_type": "multihead_attention",
    "attn_uses_sequence_id": false,
    "clip_qkv": null,
    "model_type": "",
    "prefix_lm": false,
    "qk_ln": false,
    "softmax_scale": null
  },
  "bos_token_id": 0,
  "d_model": 48,
  "dtype": "float32",
  "emb_pdrop": 0.0,
  "embedding_fraction": 1.0,
  "eos_token_id": 0,
  "expansion_ratio": 4,
  "gradient_checkpointing": false,
  "hidden_dropout": 0.1,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_device": "cpu",
  "initializer_range": 0.02,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "layer_norm_epsilon": 1e-05,
  "learned_pos_emb": true,
  "logit_scale": null,
  "max_seq_len": 2048,
  "model_type": "mpt",
  "n_heads": 4,
  "n_layers": 2,
  "n_positions": 512,
  "no_bias": true,
  "norm_type": "low_precision_layernorm",
  "pad_token_id": 1,
  "resid_pdrop": 0.0,
  "seq_length": 7,
  "tie_word_embeddings": true,
  "transformers_version": "5.16.0.dev0",
  "type_vocab_size": 16,
  "use_cache": true,
  "vocab_size": 50277
}