{
  "architectures": [
    "StableLmForSequenceClassification"
  ],
  "attention_dropout": 0.0,
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "eos_token_id": 0,
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 37,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 512,
  "model_type": "stablelm",
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "partial_rotary_factor": 0.25,
  "qk_layernorm": false,
  "rope_scaling": null,
  "rope_theta": 10000,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.40.0.dev0",
  "type_vocab_size": 16,
  "use_cache": true,
  "use_parallel_residual": false,
  "use_qkv_bias": false,
  "vocab_size": 1024
}