From ae1a9b11c0a0f28eb1b0e1c34c2e134787daac34 Mon Sep 17 00:00:00 2001
From: ajokar <ajokar91@yahoo.com>
Date: Tue, 15 Jul 2025 17:39:08 +0330
Subject: [PATCH] send editions to git

---
 check_tokenizers.py                                 |  2 +-
 .../huggingface-fa-models.txt                       |  0
 models_info.json => data/models_info.json           |  0
 .../tokenizer-fa-models-logs.txt                    |  0
 get_persian_nlp_models.py                           | 13 ++++++-------
 5 files changed, 7 insertions(+), 8 deletions(-)
 rename huggingface-fa-models.txt => data/huggingface-fa-models.txt (100%)
 rename models_info.json => data/models_info.json (100%)
 rename fokenizer-fa-models-logs.txt => data/tokenizer-fa-models-logs.txt (100%)

diff --git a/check_tokenizers.py b/check_tokenizers.py
index 573a505..b4e9322 100644
--- a/check_tokenizers.py
+++ b/check_tokenizers.py
@@ -1,7 +1,7 @@
 from transformers import AutoTokenizer
 import json
 
-file = open('models_info.json', 'r')
+file = open('./data/models_info.json', 'r')
 models = json.load(file)
 
 # Strips the newline character
diff --git a/huggingface-fa-models.txt b/data/huggingface-fa-models.txt
similarity index 100%
rename from huggingface-fa-models.txt
rename to data/huggingface-fa-models.txt
diff --git a/models_info.json b/data/models_info.json
similarity index 100%
rename from models_info.json
rename to data/models_info.json
diff --git a/fokenizer-fa-models-logs.txt b/data/tokenizer-fa-models-logs.txt
similarity index 100%
rename from fokenizer-fa-models-logs.txt
rename to data/tokenizer-fa-models-logs.txt
diff --git a/get_persian_nlp_models.py b/get_persian_nlp_models.py
index 2f5d9ba..619b846 100644
--- a/get_persian_nlp_models.py
+++ b/get_persian_nlp_models.py
@@ -1,16 +1,15 @@
 from huggingface_hub import HfApi, ModelFilter
 import json
 
-# Initialize the Hugging Face API
 api = HfApi()
 
-# Define the languages you're interested in
+# persian languages tags
 languages = ['pes', 'fas', 'fa']  # Language codes for Persian, Pashto, and Turkish
 nlp_tasks = ['text-classification', 'token-classification','table-question-answering','question-answering','zero-shot-classification','translation','summarization','feature-extraction','text-generation','text2text-generation','fill-mask','sentence-similarity']
-# Initialize a list to store the model information
+# list of model information
 models_info = []
 
-# Iterate over each language
+# Iterate languages
 for lang in languages:
     # Filter models by language
     models = api.list_models(filter=ModelFilter(language=lang))
@@ -30,8 +29,8 @@ for lang in languages:
         }
         models_info.append(model_info)
 
-# Save the collected data to a JSON file
-with open('models_info.json', 'w', encoding='utf-8') as f:
+# Save models_info
+with open('./data/models_info.json', 'w', encoding='utf-8') as f:
     json.dump(models_info, f, ensure_ascii=False, indent=4)
 
-print("Data collection complete. Saved to models_info.json")
\ No newline at end of file
+print("Finished!")
\ No newline at end of file