Upload model

config.json

@@ -0,0 +1,259 @@
+{
+  "_name_or_path": "models/gliclas-hu-audio-base-emo-4/checkpoint-24",
+  "architecture_type": "audio-encoder",
+  "architectures": [
+    "GLiClassModel"
+  ],
+  "audio_model_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "facebook/hubert-large-ls960-ft",
+    "activation_dropout": 0.1,
+    "add_cross_attention": false,
+    "apply_spec_augment": true,
+    "architectures": [
+      "HubertForCTC"
+    ],
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "classifier_proj_size": 256,
+    "conv_bias": true,
+    "conv_dim": [
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512
+    ],
+    "conv_kernel": [
+      10,
+      3,
+      3,
+      3,
+      3,
+      2,
+      2
+    ],
+    "conv_pos_batch_norm": false,
+    "conv_stride": [
+      5,
+      2,
+      2,
+      2,
+      2,
+      2,
+      2
+    ],
+    "cross_attention_hidden_size": null,
+    "ctc_loss_reduction": "sum",
+    "ctc_zero_infinity": false,
+    "decoder_start_token_id": null,
+    "diversity_loss_weight": 0.1,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "do_stable_layer_norm": true,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "feat_extract_activation": "gelu",
+    "feat_extract_dropout": 0.0,
+    "feat_extract_norm": "layer",
+    "feat_proj_dropout": 0.1,
+    "feat_proj_layer_norm": true,
+    "final_dropout": 0.1,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout": 0.1,
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.1,
+    "length_penalty": 1.0,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.05,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "hubert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_conv_pos_embedding_groups": 16,
+    "num_conv_pos_embeddings": 128,
+    "num_feat_extract_layers": 7,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 32
+  },
+  "audio_model_name": "facebook/hubert-large-ls960-ft",
+  "audio_token_index": 128003,
+  "class_token_index": 128001,
+  "contrastive_loss_coef": 0.0,
+  "embed_class_token": true,
+  "encoder_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "microsoft/deberta-v3-base",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "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": null,
+    "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-07,
+    "legacy": true,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "max_relative_positions": -1,
+    "min_length": 0,
+    "model_type": "deberta-v2",
+    "no_repeat_ngram_size": 0,
+    "norm_rel_ebd": "layer_norm",
+    "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": 0,
+    "pooler_dropout": 0,
+    "pooler_hidden_act": "gelu",
+    "pooler_hidden_size": 768,
+    "pos_att_type": [
+      "p2c",
+      "c2p"
+    ],
+    "position_biased_input": false,
+    "position_buckets": 256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "share_att_key": true,
+    "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,
+    "type_vocab_size": 0,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 128004
+  },
+  "encoder_model_name": "microsoft/deberta-v3-base",
+  "extract_text_features": false,
+  "focal_loss_alpha": 0.6,
+  "focal_loss_gamma": 2,
+  "hidden_size": 768,
+  "ignore_index": -100,
+  "init_from_larger_clap": false,
+  "initializer_range": 0.03,
+  "label_model_config": null,
+  "label_model_name": null,
+  "logit_scale_init_value": 2.6592,
+  "max_num_classes": 25,
+  "model_type": "GLiClass",
+  "normalize_features": true,
+  "pooling_strategy": "first",
+  "projection_dim": 512,
+  "projector_hidden_act": "gelu",
+  "prompt_first": true,
+  "scorer_type": "audio-token-dot",
+  "shuffle_labels": true,
+  "squeeze_layers": false,
+  "text_token_index": 128002,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "use_lstm": false,
+  "vocab_size": 128004
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac964ed2e64c39b5b8f51210a5b6f3d8053d38fc5d258df995d995d1793166b
+size 2011832292