mlx-community/multilingual-e5-large-mlx

1{2    "return_dict": true,3    "output_hidden_states": false,4    "output_attentions": false,5    "torchscript": false,6    "torch_dtype": "float32",7    "use_bfloat16": false,8    "tf_legacy_loss": false,9    "pruned_heads": {},10    "tie_word_embeddings": true,11    "is_encoder_decoder": false,12    "is_decoder": false,13    "cross_attention_hidden_size": null,14    "add_cross_attention": false,15    "tie_encoder_decoder": false,16    "max_length": 20,17    "min_length": 0,18    "do_sample": false,19    "early_stopping": false,20    "num_beams": 1,21    "num_beam_groups": 1,22    "diversity_penalty": 0.0,23    "temperature": 1.0,24    "top_k": 50,25    "top_p": 1.0,26    "typical_p": 1.0,27    "repetition_penalty": 1.0,28    "length_penalty": 1.0,29    "no_repeat_ngram_size": 0,30    "encoder_no_repeat_ngram_size": 0,31    "bad_words_ids": null,32    "num_return_sequences": 1,33    "chunk_size_feed_forward": 0,34    "output_scores": false,35    "return_dict_in_generate": false,36    "forced_bos_token_id": null,37    "forced_eos_token_id": null,38    "remove_invalid_values": false,39    "exponential_decay_length_penalty": null,40    "suppress_tokens": null,41    "begin_suppress_tokens": null,42    "architectures": [43        "XLMRobertaModel"44    ],45    "finetuning_task": null,46    "id2label": {47        "0": "LABEL_0",48        "1": "LABEL_1"49    },50    "label2id": {51        "LABEL_0": 0,52        "LABEL_1": 153    },54    "tokenizer_class": null,55    "prefix": null,56    "bos_token_id": 0,57    "pad_token_id": 1,58    "eos_token_id": 2,59    "sep_token_id": null,60    "decoder_start_token_id": null,61    "task_specific_params": null,62    "problem_type": null,63    "_name_or_path": "/Users/katopz/.cache/huggingface/hub/models--intfloat--multilingual-e5-large/snapshots/9f78368af0062735ba99812349c562316e29f719",64    "transformers_version": "4.36.2",65    "model_type": "xlm-roberta",66    "output_past": true,67    "vocab_size": 250002,68    "hidden_size": 1024,69    "num_hidden_layers": 24,70    "num_attention_heads": 16,71    "hidden_act": "gelu",72    "intermediate_size": 4096,73    "hidden_dropout_prob": 0.1,74    "attention_probs_dropout_prob": 0.1,75    "max_position_embeddings": 514,76    "type_vocab_size": 1,77    "initializer_range": 0.02,78    "layer_norm_eps": 1e-05,79    "position_embedding_type": "absolute",80    "use_cache": true,81    "classifier_dropout": null82}