| { |
| "activation_function": "gelu_new", |
| "align": "left", |
| "architectures": [ |
| "RecurrentWrapper" |
| ], |
| "attn_pdrop": 0.1, |
| "bos_token_id": 50256, |
| "embd_pdrop": 0.1, |
| "eos_token_id": 50256, |
| "initializer_range": 0.02, |
| "input_seg_len": 1004, |
| "is_memory_all": false, |
| "layer_norm_epsilon": 1e-05, |
| "max_n_segments": 2, |
| "memory_size": 10, |
| "model_type": "rmt", |
| "n_ctx": 1024, |
| "n_embd": 768, |
| "n_head": 12, |
| "n_inner": null, |
| "n_layer": 12, |
| "n_positions": 1024, |
| "num_mem_tokens": 10, |
| "output_seg_len": 1004, |
| "reorder_and_upcast_attn": false, |
| "resid_pdrop": 0.1, |
| "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, |
| "task_specific_params": { |
| "text-generation": { |
| "do_sample": true, |
| "max_length": 50 |
| } |
| }, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.50.0.dev0", |
| "use_cache": false, |
| "vocab_size": 50257 |
| } |
|
|
