Upload folder using huggingface_hub

keo_ai_studio_package.py

@@ -0,0 +1,187 @@
+# keo_ai_studio package (single-file view)
+# Save this structure locally as shown in README below.
+
+# setup.py
+setup_py = r"""
+from setuptools import setup, find_packages
+
+setup(
+    name="keo-ai-studio",
+    version="0.1.0",
+    packages=find_packages(),
+    install_requires=[
+        "transformers>=4.30.0",
+        "torch>=1.12.0"
+    ],
+    entry_points={
+        'console_scripts': [
+            'keo-chat=keo_ai_studio.cli:main'
+        ]
+    },
+    author="العبقري كريم حسين",
+    description="keo ai studio - thin python wrapper for local LLMs with optional fine-tune helpers",
+    url="",
+)
+"""
+
+# keo_ai_studio/__init__.py
+init_py = r"""
+"""
+from .model import KeoAI
+from .trainer import finetune
+
+__all__ = ["KeoAI", "finetune"]
+"""
+
+# keo_ai_studio/model.py
+model_py = r"""
+import os
+from typing import Optional
+
+try:
+    from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+except Exception:
+    # lazy import fallback: useful so package imports even if transformers not installed
+    AutoTokenizer = None
+    AutoModelForCausalLM = None
+    pipeline = None
+
+class KeoAI:
+    """Thin wrapper that loads a Hugging Face compatible model or local folder.
+    Usage:
+        k = KeoAI(model_name_or_path="path_or_hf_id")
+        k.chat("السؤال هنا؟")
+    If transformers is not installed, the object will raise when used.
+    """
+    def __init__(self, model_name_or_path: Optional[str] = None, alias: str = "keo ai studio"):
+        self.alias = alias
+        self.model_name_or_path = model_name_or_path or os.getcwd()
+        if AutoTokenizer is None:
+            raise RuntimeError("transformers not installed. Run: pip install transformers torch")
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name_or_path)
+        self.model = AutoModelForCausalLM.from_pretrained(self.model_name_or_path)
+        # convenience pipeline
+        self._pipe = pipeline("text-generation", model=self.model, tokenizer=self.tokenizer)
+
+    def chat(self, prompt: str, max_new_tokens: int = 128, do_sample: bool = True):
+        """Generate a reply for given prompt."""
+        full = self._pipe(prompt, max_new_tokens=max_new_tokens, do_sample=do_sample)
+        return full[0]["generated_text"]
+
+    def reply_author(self):
+        return "العبقري كريم حسين"
+
+    def smart_answer(self, question: str):
+        q_low = question.strip().lower()
+        if any(x in q_low for x in ["مين عملك","من صنعك","من انشأك","who made you","who created you"]):
+            return self.reply_author()
+        return self.chat(question)
+"""
+
+# keo_ai_studio/trainer.py
+trainer_py = r"""
+# Very small helper functions to fine-tune a causal LM using Hugging Face Trainer.
+# This file expects transformers, datasets, accelerate installed and a prepared dataset.
+
+def finetune(model_path_or_id, dataset_path, output_dir, epochs=1, batch_size=2, lr=2e-5):
+    from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments, DataCollatorForLanguageModeling
+    from datasets import load_dataset
+
+    tokenizer = AutoTokenizer.from_pretrained(model_path_or_id)
+    model = AutoModelForCausalLM.from_pretrained(model_path_or_id)
+
+    ds = load_dataset('text', data_files={'train': dataset_path})
+    def tokf(ex):
+        return tokenizer(ex['text'], truncation=True, max_length=1024)
+    tokenized = ds.map(tokf, batched=True, remove_columns=['text'])
+
+    data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
+    training_args = TrainingArguments(
+        output_dir=output_dir,
+        num_train_epochs=epochs,
+        per_device_train_batch_size=batch_size,
+        save_total_limit=2,
+        logging_steps=200,
+        fp16=False,
+    )
+    trainer = Trainer(model=model, args=training_args, train_dataset=tokenized['train'], data_collator=data_collator)
+    trainer.train()
+    trainer.save_model(output_dir)
+    tokenizer.save_pretrained(output_dir)
+"""
+
+# keo_ai_studio/cli.py
+cli_py = r"""
+import argparse
+from .model import KeoAI
+
+def main():
+    parser = argparse.ArgumentParser(prog='keo-chat')
+    parser.add_argument('--model', '-m', default=None, help='model id or local path')
+    args = parser.parse_args()
+    k = KeoAI(args.model)
+    print('keo ai studio interactive. type exit to quit')
+    while True:
+        try:
+            q = input('> ')
+        except EOFError:
+            break
+        if not q: continue
+        if q.strip().lower() in ('exit','quit','خروج'): break
+        print('\n' + k.smart_answer(q) + '\n')
+
+if __name__ == '__main__':
+    main()
+"""
+
+# README.md
+readme = r"""
+keo-ai-studio
+=============
+
+Lightweight Python package that wraps a Hugging Face compatible causal LM.
+
+Installation (from local folder):
+
+```bash
+pip install .
+```
+
+Usage:
+
+```python
+from keo_ai_studio import KeoAI
+k = KeoAI(model_name_or_path='path_or_hf_id')
+print(k.smart_answer('من عملك؟'))  # returns the author line
+print(k.smart_answer('اشرح بايثون'))
+```
+
+Fine-tune helper:
+
+```python
+from keo_ai_studio import finetune
+finetune('gpt2', 'data/my_corpus.txt', './keo_finetuned', epochs=1)
+```
+"""
+
+# Combined package writer - instruct user to create files
+package_files = {
+    'setup.py': setup_py,
+    'keo_ai_studio/__init__.py': init_py,
+    'keo_ai_studio/model.py': model_py,
+    'keo_ai_studio/trainer.py': trainer_py,
+    'keo_ai_studio/cli.py': cli_py,
+    'README.md': readme,
+}
+
+print('Files to create in your project:')
+for p in package_files:
+    print('-', p)
+
+# For convenience, write them to a zip in current working dir for user to download locally
+import zipfile, os
+zipname = os.path.join('/mnt/data', 'keo_ai_studio_package.zip')
+with zipfile.ZipFile(zipname, 'w') as z:
+    for p, content in package_files.items():
+        z.writestr(p, content)
+print('Created package zip at:', zipname)