{ "activation_function": "gelu_new", "architectures": [ "GPTJForCausalLM" ], "attn_pdrop": 0.0, "bos_token_id": 50256, "embd_pdrop": 0.0, "eos_token_id": 50256, "hidden_act": "gelu", "initializer_range": 0.02, "intermediate_size": 1024, "layer_norm_epsilon": 1e-05, "model_type": "gptj", "n_embd": 256, "n_head": 4, "n_inner": null, "n_layer": 2, "n_positions": 2048, "num_key_value_heads": 4, "resid_pdrop": 0.0, "rotary_dim": 64, "tie_word_embeddings": true, "torch_dtype": "float32", "transformers_version": "4.42.4", "use_cache": true, "vocab_size": 2000 }