Hub Saving

SFTConfig(
    push_to_hub=True,                    # Enable Hub push
    hub_model_id="username/model-name",   # Target repository
)

hf_jobs("uv", {
    "script": "train.py",
    "secrets": {"HF_TOKEN": "$HF_TOKEN"}  # Provide authentication
})

# train.py
# /// script
# dependencies = ["trl"]
# ///

from trl import SFTTrainer, SFTConfig
from datasets import load_dataset

dataset = load_dataset("trl-lib/Capybara", split="train")

# Configure with Hub push
config = SFTConfig(
    output_dir="my-model",
    num_train_epochs=3,
    
    # ✅ CRITICAL: Hub push configuration
    push_to_hub=True,
    hub_model_id="myusername/my-trained-model",
    
    # Optional: Push strategy
    push_to_hub_model_id="myusername/my-trained-model",
    push_to_hub_organization=None,
    push_to_hub_token=None,  # Uses environment token
)

trainer = SFTTrainer(
    model="Qwen/Qwen2.5-0.5B",
    train_dataset=dataset,
    args=config,
)

trainer.train()

# ✅ Push final model
trainer.push_to_hub()

print("✅ Model saved to: https://huggingface.co/myusername/my-trained-model")

hf_jobs("uv", {
    "script": "train.py",
    "flavor": "a10g-large",
    "timeout": "2h",
    "secrets": {"HF_TOKEN": "$HF_TOKEN"}  # ✅ Required!
})

SFTConfig(
    output_dir="my-model",
    push_to_hub=True,
    hub_model_id="username/my-model",
    
    # Checkpoint configuration
    save_strategy="steps",
    save_steps=100,              # Save every 100 steps
    save_total_limit=3,          # Keep only last 3 checkpoints
)

"secrets": {"HF_TOKEN": "$HF_TOKEN"}

"secrets": {"HF_TOKEN": "hf_abc123..."}

"env": {"HF_TOKEN": "hf_abc123..."}

from huggingface_hub import HfApi

api = HfApi()
api.create_repo(
    repo_id="username/model-name",
    repo_type="model",
    private=False,  # or True for private repo
)

from transformers import AutoModel, AutoTokenizer

# Load from local checkpoint
model = AutoModel.from_pretrained("./output_dir")
tokenizer = AutoTokenizer.from_pretrained("./output_dir")

# Push to Hub
model.push_to_hub("username/model-name", token="hf_abc123...")
tokenizer.push_to_hub("username/model-name", token="hf_abc123...")

hf_jobs("logs", {"job_id": "your-job-id"})

Pushing model to username/model-name...
Upload file pytorch_model.bin: 100%
✅ Model pushed successfully

# production_train.py
# /// script
# dependencies = ["trl>=0.12.0", "peft>=0.7.0"]
# ///

from datasets import load_dataset
from peft import LoraConfig
from trl import SFTTrainer, SFTConfig
import os

# Verify token is available
assert "HF_TOKEN" in os.environ, "HF_TOKEN not found in environment!"

# Load dataset
dataset = load_dataset("trl-lib/Capybara", split="train")
print(f"✅ Dataset loaded: {len(dataset)} examples")

# Configure with comprehensive Hub settings
config = SFTConfig(
    output_dir="qwen-capybara-sft",
    
    # Hub configuration
    push_to_hub=True,
    hub_model_id="myusername/qwen-capybara-sft",
    hub_strategy="checkpoint",  # Push checkpoints
    
    # Checkpoint configuration
    save_strategy="steps",
    save_steps=100,
    save_total_limit=3,
    
    # Training settings
    num_train_epochs=3,
    per_device_train_batch_size=4,
    
    # Logging
    logging_steps=10,
    logging_first_step=True,
)

# Train with LoRA
trainer = SFTTrainer(
    model="Qwen/Qwen2.5-0.5B",
    train_dataset=dataset,
    args=config,
    peft_config=LoraConfig(r=16, lora_alpha=32),
)

print("🚀 Starting training...")
trainer.train()

print("💾 Pushing final model to Hub...")
trainer.push_to_hub()

print("✅ Training complete!")
print(f"Model available at: https://huggingface.co/myusername/qwen-capybara-sft")

hf_jobs("uv", {
    "script": "production_train.py",
    "flavor": "a10g-large",
    "timeout": "6h",
    "secrets": {"HF_TOKEN": "$HF_TOKEN"}
})