{
  "_name_or_path": "/mnt/beegfs/mixed-tier/share/projects/fastdraft/project_finetuned_models/llama3.1-draft-base-150M-fineweb5bt-CP-5bt_code-2.5bt_text/combi_alpaca_oig_code-evol__alpaca_llama3.1",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 1792,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 8,
  "num_hidden_layers": 6,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.44.0",
  "use_cache": true,
  "vocab_size": 128256
}