Team Ai
Modelpublic

CodeRosetta/CodeRosetta_cpp_cuda_base

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes25downloads
config.json237 linesDownload Raw Back to root
1{2  "add_cross_attention": true,3  "architectures": [4    "EncoderDecoderModel"5  ],6  "decoder": {7    "_name_or_path": "cudaizerV2_aer",8    "add_cross_attention": true,9    "architectures": [10      "RobertaForTokenClassification"11    ],12    "attention_probs_dropout_prob": 0.1,13    "bad_words_ids": null,14    "begin_suppress_tokens": null,15    "bos_token_id": 0,16    "chunk_size_feed_forward": 0,17    "classifier_dropout": null,18    "cross_attention_hidden_size": null,19    "decoder_start_token_id": null,20    "diversity_penalty": 0.0,21    "do_sample": false,22    "early_stopping": false,23    "encoder_no_repeat_ngram_size": 0,24    "eos_token_id": 2,25    "exponential_decay_length_penalty": null,26    "finetuning_task": null,27    "forced_bos_token_id": null,28    "forced_eos_token_id": null,29    "gradient_checkpointing": false,30    "hidden_act": "gelu",31    "hidden_dropout_prob": 0.1,32    "hidden_size": 1536,33    "id2label": {34      "0": "O",35      "1": "B-VAR",36      "2": "I-VAR",37      "3": "B-FUNC",38      "4": "I-FUNC",39      "5": "B-TYPE",40      "6": "I-TYPE",41      "7": "B-PRIM",42      "8": "I-PRIM",43      "9": "B-NUM",44      "10": "I-NUM",45      "11": "B-POIN",46      "12": "I-POIN",47      "13": "B-PDEC",48      "14": "I-PDEC",49      "15": "B-CONS",50      "16": "I-CONS"51    },52    "initializer_range": 0.02,53    "intermediate_size": 4096,54    "is_decoder": true,55    "is_encoder_decoder": false,56    "label2id": {57      "B-CONS": 15,58      "B-FUNC": 3,59      "B-NUM": 9,60      "B-PDEC": 13,61      "B-POIN": 11,62      "B-PRIM": 7,63      "B-TYPE": 5,64      "B-VAR": 1,65      "I-CONS": 16,66      "I-FUNC": 4,67      "I-NUM": 10,68      "I-PDEC": 14,69      "I-POIN": 12,70      "I-PRIM": 8,71      "I-TYPE": 6,72      "I-VAR": 2,73      "O": 074    },75    "layer_norm_eps": 1e-05,76    "length_penalty": 1.0,77    "max_length": 20,78    "max_position_embeddings": 1026,79    "min_length": 0,80    "model_type": "roberta",81    "no_repeat_ngram_size": 0,82    "num_attention_heads": 12,83    "num_beam_groups": 1,84    "num_beams": 1,85    "num_hidden_layers": 12,86    "num_return_sequences": 1,87    "output_attentions": false,88    "output_hidden_states": false,89    "output_past": true,90    "output_scores": false,91    "pad_token_id": 1,92    "position_embedding_type": "absolute",93    "prefix": null,94    "problem_type": null,95    "pruned_heads": {},96    "remove_invalid_values": false,97    "repetition_penalty": 1.0,98    "return_dict": true,99    "return_dict_in_generate": false,100    "sep_token_id": null,101    "suppress_tokens": null,102    "task_specific_params": null,103    "temperature": 1.0,104    "tf_legacy_loss": false,105    "tie_encoder_decoder": false,106    "tie_word_embeddings": true,107    "tokenizer_class": null,108    "top_k": 50,109    "top_p": 1.0,110    "torch_dtype": "float32",111    "torchscript": false,112    "type_vocab_size": 10,113    "typical_p": 1.0,114    "use_bfloat16": false,115    "use_cache": true,116    "vocab_size": 51418117  },118  "encoder": {119    "_name_or_path": "cudaizerV2_aer",120    "add_cross_attention": false,121    "architectures": [122      "RobertaForTokenClassification"123    ],124    "attention_probs_dropout_prob": 0.1,125    "bad_words_ids": null,126    "begin_suppress_tokens": null,127    "bos_token_id": 0,128    "chunk_size_feed_forward": 0,129    "classifier_dropout": null,130    "cross_attention_hidden_size": null,131    "decoder_start_token_id": null,132    "diversity_penalty": 0.0,133    "do_sample": false,134    "early_stopping": false,135    "encoder_no_repeat_ngram_size": 0,136    "eos_token_id": 2,137    "exponential_decay_length_penalty": null,138    "finetuning_task": null,139    "forced_bos_token_id": null,140    "forced_eos_token_id": null,141    "gradient_checkpointing": false,142    "hidden_act": "gelu",143    "hidden_dropout_prob": 0.1,144    "hidden_size": 1536,145    "id2label": {146      "0": "O",147      "1": "B-VAR",148      "2": "I-VAR",149      "3": "B-FUNC",150      "4": "I-FUNC",151      "5": "B-TYPE",152      "6": "I-TYPE",153      "7": "B-PRIM",154      "8": "I-PRIM",155      "9": "B-NUM",156      "10": "I-NUM",157      "11": "B-POIN",158      "12": "I-POIN",159      "13": "B-PDEC",160      "14": "I-PDEC",161      "15": "B-CONS",162      "16": "I-CONS"163    },164    "initializer_range": 0.02,165    "intermediate_size": 4096,166    "is_decoder": false,167    "is_encoder_decoder": false,168    "label2id": {169      "B-CONS": 15,170      "B-FUNC": 3,171      "B-NUM": 9,172      "B-PDEC": 13,173      "B-POIN": 11,174      "B-PRIM": 7,175      "B-TYPE": 5,176      "B-VAR": 1,177      "I-CONS": 16,178      "I-FUNC": 4,179      "I-NUM": 10,180      "I-PDEC": 14,181      "I-POIN": 12,182      "I-PRIM": 8,183      "I-TYPE": 6,184      "I-VAR": 2,185      "O": 0186    },187    "layer_norm_eps": 1e-05,188    "length_penalty": 1.0,189    "max_length": 20,190    "max_position_embeddings": 1026,191    "min_length": 0,192    "model_type": "roberta",193    "no_repeat_ngram_size": 0,194    "num_attention_heads": 12,195    "num_beam_groups": 1,196    "num_beams": 1,197    "num_hidden_layers": 12,198    "num_return_sequences": 1,199    "output_attentions": false,200    "output_hidden_states": false,201    "output_past": true,202    "output_scores": false,203    "pad_token_id": 1,204    "position_embedding_type": "absolute",205    "prefix": null,206    "problem_type": null,207    "pruned_heads": {},208    "remove_invalid_values": false,209    "repetition_penalty": 1.0,210    "return_dict": true,211    "return_dict_in_generate": false,212    "sep_token_id": null,213    "suppress_tokens": null,214    "task_specific_params": null,215    "temperature": 1.0,216    "tf_legacy_loss": false,217    "tie_encoder_decoder": false,218    "tie_word_embeddings": true,219    "tokenizer_class": null,220    "top_k": 50,221    "top_p": 1.0,222    "torch_dtype": "float32",223    "torchscript": false,224    "type_vocab_size": 10,225    "typical_p": 1.0,226    "use_bfloat16": false,227    "use_cache": true,228    "vocab_size": 51418229  },230  "eos_token_id": 2,231  "is_encoder_decoder": true,232  "model_type": "encoder-decoder",233  "pad_token_id": 1,234  "torch_dtype": "float32",235  "transformers_version": "4.40.1"236}237