|
{ |
|
"_name_or_path": "models/qwen/base", |
|
"architecture_type": "uni-encoder", |
|
"architectures": [ |
|
"GLiClassModel" |
|
], |
|
"class_token_index": 151646, |
|
"contrastive_loss_coef": 0.03, |
|
"embed_class_token": true, |
|
"encoder_config": { |
|
"_name_or_path": "knowledgator/Qwen-encoder-0.5B", |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"Qwen2ForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": 151643, |
|
"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": 151643, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"hidden_act": "silu", |
|
"hidden_size": 896, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 4864, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"max_position_embeddings": 131072, |
|
"max_window_layers": 24, |
|
"min_length": 0, |
|
"model_type": "qwen2", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 14, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_hidden_layers": 24, |
|
"num_key_value_heads": 2, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"rms_norm_eps": 1e-06, |
|
"rope_theta": 1000000.0, |
|
"sep_token_id": null, |
|
"sliding_window": 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": "float32", |
|
"torchscript": false, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"use_cache": true, |
|
"use_sliding_window": false, |
|
"vocab_size": 151648 |
|
}, |
|
"encoder_model_name": "knowledgator/Qwen-encoder-0.5B", |
|
"extract_text_features": true, |
|
"focal_loss_alpha": -1, |
|
"focal_loss_gamma": 2, |
|
"hidden_size": 896, |
|
"ignore_index": -100, |
|
"initializer_range": 0.03, |
|
"logit_scale_init_value": 2.6592, |
|
"max_num_classes": 25, |
|
"model_type": "GLiClass", |
|
"normalize_features": false, |
|
"pooling_strategy": "avg", |
|
"problem_type": "multi_label_classification", |
|
"projector_hidden_act": "gelu", |
|
"prompt_first": true, |
|
"scorer_type": "simple", |
|
"squeeze_layers": false, |
|
"text_token_index": 151647, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.44.1", |
|
"use_lstm": false, |
|
"vocab_size": 151648 |
|
} |
|
|