Daniel Fox PRO

:D

update: pre-training the model would need at least 300GB of ram/vram

No. I think.

Hi :)

Hey! I did manage to fine tune the model after all.

import os
import argparse
from transformers import (
    AutoTokenizer,
    AutoModelForCausalLM,
    Trainer,
    TrainingArguments,
)
from datasets import load_dataset
import torch

# === Disable W&B logging ===
os.environ["WANDB_DISABLED"] = "true"

# === Config ===
config = {
    "model_name": "FlameF0X/SnowflakeCore-G1-Tiny",
    "output_dir": "./snowflake-chatbot",
    "context_window": 512,
    "per_device_batch_size": 1,
    "gradient_accumulation_steps": 16,
    "max_steps": 500,
    "dataloader_workers": 4,
    "dataset_name": "tatsu-lab/alpaca",
    "dataset_split": "train[:10000]",
}

# === Derived ===
config["effective_batch_size"] = (
    config["per_device_batch_size"] * config["gradient_accumulation_steps"]
)

print(f"Effective batch size: {config['effective_batch_size']}")
print(f"Context window: {config['context_window']}")


# === 1. Load tokenizer and model ===
def load_model_and_tokenizer(config):
    print(f"Loading model and tokenizer from {config['model_name']}...")
    tokenizer = AutoTokenizer.from_pretrained(
        config["model_name"],
        trust_remote_code=True,
        force_download=True,
        use_safetensors=True,
        model_max_length=config["context_window"],
    )
    model = AutoModelForCausalLM.from_pretrained(
        config["model_name"],
        trust_remote_code=True,
        force_download=True,
        use_safetensors=True,
    )

    if hasattr(torch, "compile"):
        try:
            print("Compiling model with torch.compile...")
            model = torch.compile(model)
        except Exception as e:
            print(f"Compilation failed: {e}")
    return tokenizer, model


# === 2. Load dataset ===
def load_custom_dataset(name, split):
    print(f"Loading dataset: {name} ({split})...")
    return load_dataset(name, split=split)


# === 3. Format dataset ===
def format_example(example):
    """Update this function to work with different datasets."""
    return {
        "text": f"### Instruction:\n{example['instruction']}\n### Input:\n{example['input']}\n### Response:\n{example['output']}"
    }


# === 4. Tokenize ===
def tokenize_example(example, tokenizer, max_length):
    tokens = tokenizer(
        example["text"],
        truncation=True,
        padding="max_length",
        max_length=max_length,
    )
    tokens["labels"] = tokens["input_ids"].copy()
    return tokens


# === 5. Train ===
def train_model(model, tokenizer, tokenized_dataset, config):
    print("Preparing training arguments...")
    training_args = TrainingArguments(
        output_dir=config["output_dir"],
        per_device_train_batch_size=config["per_device_batch_size"],
        gradient_accumulation_steps=config["gradient_accumulation_steps"],
        max_steps=config["max_steps"],
        logging_dir="./logs",
        logging_steps=20,
        save_strategy="no",
        fp16=torch.cuda.is_available() and not torch.cuda.is_bf16_supported(),
        bf16=torch.cuda.is_available() and torch.cuda.is_bf16_supported(),
        overwrite_output_dir=True,
        report_to=[],
        dataloader_num_workers=config["dataloader_workers"],
        optim="adamw_torch_fused" if torch.cuda.is_available() and hasattr(torch, 'compile') else "adamw_torch",
        remove_unused_columns=False,
    )

    trainer = Trainer(
        model=model,
        args=training_args,
        train_dataset=tokenized_dataset,
    )

    print("Starting training...")
    trainer.train()
    print("Training completed.")


# === 6. Save ===
def save_model(model, tokenizer, output_dir):
    print(f"Saving model to {output_dir}...")
    model.save_pretrained(output_dir, safe_serialization=False)
    tokenizer.save_pretrained(output_dir)
    print("✅ Model saved.")


# === Main ===
def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--dataset", type=str, default=config["dataset_name"])
    parser.add_argument("--split", type=str, default=config["dataset_split"])
    args = parser.parse_args()

    tokenizer, model = load_model_and_tokenizer(config)
    dataset = load_custom_dataset(args.dataset, args.split)

    print("Formatting dataset...")
    dataset = dataset.map(format_example, num_proc=config["dataloader_workers"], load_from_cache_file=False)

    print("Tokenizing dataset...")
    tokenized = dataset.map(
        lambda x: tokenize_example(x, tokenizer, config["context_window"]),
        batched=True,
        num_proc=config["dataloader_workers"],
        load_from_cache_file=False,
    )
    tokenized.set_format(type="torch", columns=["input_ids", "attention_mask", "labels"])

    train_model(model, tokenizer, tokenized, config)
    save_model(model, tokenizer, config["output_dir"])


if __name__ == "__main__":
    main()

Hello kivenemi! Thanks for waiting! Here are the first metrics from SnowflakeCore-G1-Tiny (~355.87M params):

Performance

• Generation Speed: 57.26 tokens/sec
• Model Size: 1.36 GB
• Memory Usage: 6.35 GB (2048 tokens)

Benchmarks (After training)

• GSM8K: 20%
• MMLU: 0% (issues with the benchmark itself)
• HumanEval: 0% (issues with the benchmark itself)

The model is still under development. So the next versions would perform better.
You have the full benchmark at FlameF0X/SnowflakeCore-G1-Benchmark.

👀