{
  "_name_or_path": "/cluster/work/sachan/NLF/quark/model/iter_10/model_ckp_25600",
  "activation_function": "gelu_new",
  "architectures": [
    "GPTJForCausalLM"
  ],
  "attn_pdrop": 0.0,
  "bos_token_id": 50256,
  "embd_pdrop": 0.0,
  "eos_token_id": 50256,
  "gradient_checkpointing": false,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gptj",
  "n_embd": 4096,
  "n_head": 16,
  "n_inner": null,
  "n_layer": 28,
  "n_positions": 2048,
  "resid_pdrop": 0.0,
  "rotary": true,
  "rotary_dim": 64,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 50,
      "temperature": 1.0
    }
  },
  "tie_word_embeddings": false,
  "tokenizer_class": "GPT2Tokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "use_cache": false,
  "vocab_size": 50405
}