| { |
| "activation_function": "gelu_new", |
| "add_cross_attention": false, |
| "architectures": [ |
| "GPT2LMHeadModel" |
| ], |
| "attn_pdrop": 0.1, |
| "bos_token_id": 50256, |
| "created_by": "Inserloft Research", |
| "description": "Modelo de 200M de par\u00e1metros enfocado en autocompletado r\u00e1pido de c\u00f3digo.", |
| "dtype": "float16", |
| "embd_pdrop": 0.1, |
| "eos_token_id": 50256, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "model_name": "Parrot Coder", |
| "model_type": "gpt2", |
| "n_embd": 1024, |
| "n_head": 16, |
| "n_inner": null, |
| "n_layer": 16, |
| "n_positions": 2048, |
| "pad_token_id": null, |
| "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, |
| "tags": [ |
| "code-generation", |
| "autocompletion", |
| "inserloft" |
| ], |
| "tie_word_embeddings": true, |
| "transformers_version": "5.16.1", |
| "use_cache": false, |
| "vocab_size": 50257, |
| "web": "Research.Inserloft.com", |
| "n_ctx": 2048 |
| } |