fix

models/test2tags/README.md

@@ -1,3 +0,0 @@
----
-license: unlicense
----

models/test2tags/config.json

@@ -1,61 +0,0 @@
-{
-  "_name_or_path": "google-t5/t5-small",
-  "architectures": [
-    "T5ForConditionalGeneration"
-  ],
-  "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 512,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "relu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": false,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.1",
-  "use_cache": true,
-  "vocab_size": 32128
-}

models/test2tags/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.41.1"
-}

models/test2tags/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2491d3581a1d2646e28ef810ae61754e6eab5da0588486cec78edbb3b3baff48
-size 242041896

models/test2tags/special_tokens_map.json

@@ -1,23 +0,0 @@
-{
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

models/test2tags/spiece.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
-size 791656

models/test2tags/tokenizer_config.json

@@ -1,38 +0,0 @@
-{
-  "add_prefix_space": true,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "extra_ids": 100,
-  "legacy": true,
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "T5Tokenizer",
-  "unk_token": "<unk>"
-}

utils/summary_utils.py

@@ -4,7 +4,7 @@ from transformers import pipeline
 AiSummaryVersion = 1
 summarization_pipeline = pipeline("summarization", model="csebuetnlp/mT5_multilingual_XLSum", max_length=512, min_length=50)
 en_translation_pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-mul-en")
-text_to_tags_pipe = pipeline('text2text-generation', model='youfengy/t5-small-test-tags')
+text_to_tags_pipe = pipeline('text2text-generation', model='PageOrg/t5-small-tagging-text')
 
 
 def summarize(id: str, text: str):