config.json

{
  "_name_or_path": "Deci/DeciLM-7B",
  "architectures": [
    "DeciLMForCausalLM"
  ],
  "attention_bias": false,
  "auto_map": {
    "AutoConfig": "Deci/DeciLM-7B--configuration_decilm.DeciLMConfig",
    "AutoModelForCausalLM": "Deci/DeciLM-7B--modeling_decilm.DeciLMForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "model_type": "deci",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_key_value_heads_per_layer": [
    4,
    4,
    4,
    4,
    4,
    2,
    2,
    2,
    2,
    2,
    4,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    4
  ],
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 2.0,
    "type": "dynamic"
  },
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "tokenizer_class": "LlamaTokenizer",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.0.dev0",
  "use_bfloat16": true,
  "use_cache": true,
  "vocab_size": 32000
}