| { | |
| "_name_or_path": "data/hf/gpt2-small-italian", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 0, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 0, | |
| "gradient_checkpointing": false, | |
| "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, | |
| "pad_token_id": 0, | |
| "resid_pdrop": 0.1, | |
| "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": 100, | |
| "no_repeat_ngram_size": 4, | |
| "num_beams": 10, | |
| "repetition_penalty": 10.0, | |
| "temperature": 2.0, | |
| "top_k": 20, | |
| "top_p": 0.9 | |
| } | |
| }, | |
| "use_cache": true, | |
| "vocab_size": 30001 | |
| } | |