config.json

{
  "_name_or_path": "docketanalyzer/smol-encoder-135m-base",
  "architectures": [
    "LlamaEncoderForMaskedLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "docketanalyzer/smol-encoder-135m-base--configuration_llama.LlamaEncoderConfig",
    "AutoModel": "docketanalyzer/smol-encoder-135m-base--modeling_llama.LlamaEncoderModel",
    "AutoModelForMaskedLM": "docketanalyzer/smol-encoder-135m-base--modeling_llama.LlamaEncoderForMaskedLM"
  },
  "bos_token_id": 0,
  "eos_token_id": 0,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 576,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama_encoder",
  "num_attention_heads": 9,
  "num_hidden_layers": 30,
  "num_key_value_heads": 3,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 49154
}