| { | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "moe": true, | |
| "moe_layer_freq": 2, | |
| "n_embd": 256, | |
| "n_head": 8, | |
| "n_inner": 512, | |
| "n_layer": 6, | |
| "n_positions": 512, | |
| "num_experts": 4, | |
| "num_experts_per_tok": 2, | |
| "output_router_logits": true, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "router_aux_loss_coef": 0.01, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "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, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.49.0", | |
| "use_cache": true, | |
| "vocab_size": 50257 | |
| } | |