brxce/ gliner-small-2.1:latest

9 1 month ago

... /
json
15dc8e9bd3b9 ยท 5.0kB
{
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": null,
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"architectures": [
"GLiNER"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": null,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "",
"_attn_implementation_autoset": false,
"transformers_version": "4.51.3",
"size_sup": -1,
"shuffle_types": true,
"random_drop": true,
"lr_encoder": "1e-5",
"lr_others": "5e-5",
"num_steps": 30000,
"warmup_ratio": 3000,
"train_batch_size": 8,
"eval_every": 5000,
"encoder_config": {
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": null,
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"architectures": null,
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": 0,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "microsoft/deberta-v3-small",
"_attn_implementation_autoset": true,
"transformers_version": "4.51.3",
"model_type": "deberta-v2",
"position_buckets": 256,
"norm_rel_ebd": "layer_norm",
"share_att_key": true,
"hidden_size": 768,
"num_hidden_layers": 6,
"num_attention_heads": 12,
"intermediate_size": 3072,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"attention_probs_dropout_prob": 0.1,
"max_position_embeddings": 512,
"type_vocab_size": 0,
"initializer_range": 0.02,
"relative_attention": true,
"max_relative_positions": -1,
"position_biased_input": false,
"pos_att_type": [
"p2c",
"c2p"
],
"vocab_size": 128004,
"layer_norm_eps": 1e-07,
"pooler_hidden_size": 768,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"legacy": true
},
"labels_encoder_config": null,
"model_name": "microsoft/deberta-v3-small",
"labels_encoder": null,
"name": "correct",
"max_width": 12,
"hidden_size": 512,
"dropout": 0.4,
"fine_tune": true,
"subtoken_pooling": "first",
"span_mode": "markerV0",
"post_fusion_schema": "",
"num_post_fusion_layers": 1,
"vocab_size": 128004,
"max_neg_type_ratio": 1,
"max_types": 25,
"max_len": 384,
"words_splitter_type": "whitespace",
"has_rnn": true,
"fuse_layers": false,
"class_token_index": 128002,
"embed_ent_token": true,
"ent_token": "<<ENT>>",
"sep_token": "<<SEP>>",
"model_type": "gliner"
}