{
  "_name_or_path": "/fsx/ckpts/3b_tok=starcoder_data=star_coder_model=stable-code-no-fim-specific-langs/global_step150000_hf",
  "architectures": [
    "GPTNeoXForCausalLM"
  ],
  "bos_token_id": 0,
  "classifier_dropout": 0.1,
  "eos_token_id": 0,
  "hidden_act": "gelu",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 10240,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 4096,
  "model_type": "gpt_neox",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "rotary_emb_base": 10000,
  "rotary_pct": 0.25,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.30.2",
  "use_cache": true,
  "use_parallel_residual": true,
  "vocab_size": 49152,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 8,
    "group_size": 64,
    "damp_percent": 0.1,
    "desc_act": true,
    "sym": true,
    "true_sequential": true,
    "model_name_or_path": null,
    "model_file_base_name": "model",
    "quant_method": "gptq"
  }
}