| { | |
| "activation_function": "silu", | |
| "architectures": [ | |
| "GPT2ALMHeadModel" | |
| ], | |
| "attn_bias": false, | |
| "attn_pdrop": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_shrinkydink.GPT2AConfig", | |
| "AutoModelForCausalLM": "modeling_shrinkydink.GPT2ALMHeadModel" | |
| }, | |
| "bos_token_id": 1, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 2, | |
| "full_layer_repetitions": 1, | |
| "initializer_range": 0.02, | |
| "layer_dropout_prob": 0.1, | |
| "layer_norm_epsilon": 1e-06, | |
| "mlp_bias": false, | |
| "model_type": "gpt2a", | |
| "n_embd": 1024, | |
| "n_embd_true": 8192, | |
| "n_head": 16, | |
| "n_inner": 4096, | |
| "n_layer": 16, | |
| "n_positions": 8192, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.0, | |
| "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, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |