fastfit_rng / config.json
yasirdemircan's picture
Upload config.json with huggingface_hub
7824fb0 verified
{
"_commit_hash": null,
"all_docs": [
[
[
0,
5001,
2
],
[
0,
3897,
2
]
],
[
[
1,
1,
1
],
[
1,
1,
1
]
]
],
"architectures": [
"FastFitTrainable"
],
"clf_dim": 2,
"clf_doc": false,
"clf_factor": 0.1,
"clf_level": "cls",
"clf_loss_factor": 0.5,
"clf_query": true,
"encoder": {
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
"add_cross_attention": false,
"architectures": [
"MPNetForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 514,
"min_length": 0,
"model_type": "mpnet",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 1,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"relative_attention_num_buckets": 32,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.41.1",
"typical_p": 1.0,
"use_bfloat16": false,
"vocab_size": 30527
},
"encoder_dropout": null,
"encoding_type": "dual",
"hidden_size": 768,
"id2label": {
"0": "negative",
"1": "positive"
},
"inference_direction": "doc",
"inference_type": "sim",
"init_freeze": "all",
"label2id": {
"negative": 0,
"positive": 1
},
"length_norm": true,
"length_norm_at_inference": false,
"mask_prob": 0.0,
"mask_zeros_in_doc": false,
"mask_zeros_in_query": false,
"mlm_factor": 0.0,
"mlm_prob": 0.0,
"model_type": "FastFit",
"num_repeats": 4,
"pretrain_mode": false,
"proj_dim": 128,
"rep_tokens": "all",
"scores_temp": 0.07,
"sim_factor": 1.0,
"similarity_metric": "cosine",
"symetric_mode": true,
"torch_dtype": "float32",
"transformers_version": null
}