| { | |
| "_name_or_path": "/nlp/scr3/nlp/llms-in-llms/babylm_models/babylm_shuffle_deterministic57_100M_randinit_no_positional_encodings/babylm_shuffle_deterministic57_100M_randinit_no_positional_encodings_seed0/runs/babylm_shuffle_deterministic57_100M_randinit_no_positional_encodings_seed0/checkpoint-3000", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2NoPositionalEncodingLMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "auto_map": { | |
| "AutoModelForCausalLM": "modeling_gpt2_no_pos.GPT2NoPositionalEncodingLMHeadModel" | |
| }, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_inner": null, | |
| "n_layer": 12, | |
| "n_positions": 1024, | |
| "reorder_and_upcast_attn": true, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": true, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.2, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 1024 | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2", | |
| "use_cache": false, | |
| "vocab_size": 50257 | |
| } | |