Upload folder using huggingface_hub

README.md

@@ -1,12 +1,21 @@
----
-title: D1337 Cipher Simple
-emoji: 🦀
-colorFrom: green
-colorTo: red
-sdk: gradio
-sdk_version: 6.4.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: D1337 CIPHER Training
+emoji: 🔥
+colorFrom: red
+colorTo: gray
+sdk: gradio
+sdk_version: "5.0.0"
+python_version: "3.10"
+app_file: app.py
+pinned: false
+---
+
+# D1337 CIPHER C2 V.1 - Training
+
+One-click training setup.
+
+**Click "START TRAINING"** → Done in 15-30 minutes.
+
+---
+
+**D1337 SOVEREIGN LABS - CEO Desorden**

app.py

@@ -0,0 +1,85 @@
+import gradio as gr
+import subprocess
+import os
+import threading
+
+def start_training():
+    """Start D1337 CIPHER training"""
+    
+    def run_training():
+        try:
+            os.system("pip install torch transformers datasets accelerate huggingface-hub --quiet")
+            
+            # Simple training script
+            training_code = '''
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments
+from datasets import load_dataset
+
+# Load model
+model_name = "huihui-ai/Huihui-GLM-4.7-Flash-abliterated"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+
+# Load dataset
+dataset = load_dataset("Desorden1337/d1337-cipher-dataset", split="train")
+
+# Simple tokenize
+def tokenize(examples):
+    return tokenizer(examples["text"], truncation=True, padding="max_length", max_length=512)
+
+dataset = dataset.map(tokenize, batched=True)
+
+# Training args - FAST
+training_args = TrainingArguments(
+    output_dir="./d1337-cipher",
+    num_train_epochs=1,  # Quick training
+    per_device_train_batch_size=4,
+    learning_rate=1e-4,
+    logging_steps=5,
+    save_steps=50,
+    push_to_hub=True,
+    hub_model_id="Desorden1337/d1337-cipher-v1",
+    hub_private_repo=True
+)
+
+# Train
+trainer = Trainer(model=model, args=training_args, train_dataset=dataset, tokenizer=tokenizer)
+trainer.train()
+trainer.push_to_hub()
+
+print("TRAINING COMPLETE!")
+'''
+            
+            with open("train.py", "w") as f:
+                f.write(training_code)
+            
+            # Execute
+            result = subprocess.run(["python", "train.py"], capture_output=True, text=True)
+            
+            return f"Training started!\n{result.stdout}\n{result.stderr}"
+            
+        except Exception as e:
+            return f"Error: {e}"
+    
+    # Run in background
+    thread = threading.Thread(target=run_training)
+    thread.start()
+    
+    return "🔥 D1337 CIPHER TRAINING STARTED!\n\nCheck logs below..."
+
+# UI
+with gr.Blocks(title="D1337 CIPHER Training") as demo:
+    gr.Markdown("# 🔥 D1337 CIPHER C2 V.1 - TRAINING")
+    gr.Markdown("**Base**: GLM-4.7-Flash-abliterated (31B)")
+    gr.Markdown("**Dataset**: 92 samples")
+    
+    with gr.Row():
+        train_btn = gr.Button("🚀 START TRAINING", variant="primary")
+        output = gr.Textbox(label="Training Output", lines=10)
+    
+    train_btn.click(start_training, outputs=output)
+    
+    gr.Markdown("**Expected time: 15-30 minutes on GPU**")
+
+demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,6 @@
+torch>=2.0.0
+transformers>=4.36.0
+datasets>=2.15.0
+accelerate>=0.25.0
+huggingface-hub>=0.20.0
+gradio>=5.0.0