{
  "_name_or_path": "/leonardo/home/userexternal/tcarsten/work/converted_checkpoints/open-sci-ref_model-1.3b_data-HPLT-2.0_tokenizer-GPT-NeoX_samples-300B_global_bs-1008_context-4096_schedule-WSD_lr-4e-3_warmup-25000_machine-LEONARDO_13686118/hf/iter_0072661",
  "architectures": [
    "OpenSciForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_opensci.OpensciConfig",
    "AutoModel": "modeling_opensci.OpensciPreTrainedModel",
    "AutoModelForCausalLM": "modeling_opensci.OpensciForCausalLM"
  },
  "bos_token_id": 0,
  "eos_token_id": 0,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5440,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 4096,
  "mlp_bias": true,
  "model_type": "opensci",
  "num_attention_heads": 32,
  "num_hidden_layers": 24,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "qk_layernorm": true,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 50304
}