import os
import gc
import torch

import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, BitsAndBytesConfig
from datasets import load_dataset
from peft import LoraConfig, PeftModel, get_peft_model, prepare_model_for_kbit_training
from trl import DPOTrainer
import bitsandbytes as bnb
from google.colab import userdata
import wandb

# Defined in the secrets tab in Google Colab
hf_token = userdata.get('huggingface')
wb_token = userdata.get('wandb')
wandb.login(key=wb_token)

model_name = "teknium/OpenHermes-2.5-Mistral-7B"
new_model = "NeuralHermes-2.5-Mistral-7B"

def chatml_format(example):
    # Format system
    if len(example['system']) > 0:
        message = {"role": "system", "content": example['system']}
        system = tokenizer.apply_chat_template([message], tokenize=False)
    else:
        system = ""

    # Format instruction
    message = {"role": "user", "content": example['question']}
    prompt = tokenizer.apply_chat_template([message], tokenize=False, add_generation_prompt=True)

    # Format chosen answer
    chosen = example['chosen'] + "<|im_end|>\n"

    # Format rejected answer
    rejected = example['rejected'] + "<|im_end|>\n"

    return {
        "prompt": system + prompt,
        "chosen": chosen,
        "rejected": rejected,
    }

# Load dataset
dataset = load_dataset("Intel/orca_dpo_pairs")['train']

# Save columns
original_columns = dataset.column_names

# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"

# Format dataset
dataset = dataset.map(
    chatml_format,
    remove_columns=original_columns
)

# Print sample
dataset[1]

# LoRA configuration
peft_config = LoraConfig(
    r=16,
    lora_alpha=16,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
    target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
)

# Model to fine-tune
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    load_in_4bit=True
)
model.config.use_cache = False

# Reference model
ref_model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    load_in_4bit=True
)

# Training arguments
training_args = TrainingArguments(
    per_device_train_batch_size=4,
    gradient_accumulation_steps=4,
    gradient_checkpointing=True,
    learning_rate=5e-5,
    lr_scheduler_type="cosine",
    max_steps=200,
    save_strategy="no",
    logging_steps=1,
    output_dir=new_model,
    optim="paged_adamw_32bit",
    warmup_steps=100,
    bf16=True,
    report_to="wandb",
)

# Create DPO trainer
dpo_trainer = DPOTrainer(
    model,
    ref_model,
    args=training_args,
    train_dataset=dataset,
    tokenizer=tokenizer,
    peft_config=peft_config,
    beta=0.1,
    max_prompt_length=1024,
    max_length=1536,
)

# Fine-tune model with DPO
dpo_trainer.train()

# Save artifacts
dpo_trainer.model.save_pretrained("final_checkpoint")
tokenizer.save_pretrained("final_checkpoint")

# Flush memory
del dpo_trainer, model, ref_model
gc.collect()
torch.cuda.empty_cache()

# Reload model in FP16 (instead of NF4)
base_model = AutoModelForCausalLM.from_pretrained(
    model_name,
    return_dict=True,
    torch_dtype=torch.float16,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Merge base model with the adapter
model = PeftModel.from_pretrained(base_model, "final_checkpoint")
model = model.merge_and_unload()

# Save model and tokenizer
model.save_pretrained(new_model)
tokenizer.save_pretrained(new_model)

# Push them to the HF Hub
model.push_to_hub(new_model, use_temp_dir=False, token=hf_token)
tokenizer.push_to_hub(new_model, use_temp_dir=False, token=hf_token)

# Format prompt
message = [
    {"role": "system", "content": "You are a helpful assistant chatbot."},
    {"role": "user", "content": "What is a Large Language Model?"}
]
tokenizer = AutoTokenizer.from_pretrained(new_model)
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)

# Create pipeline
pipeline = transformers.pipeline(
    "text-generation",
    model=new_model,
    tokenizer=tokenizer
)

# Generate text
sequences = pipeline(
    prompt,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    num_return_sequences=1,
    max_length=200,
)
print(sequences[0]['generated_text'])

!pip install -qqq datasets==3.2.0 transformers==4.47.1 trl==0.14.0 peft==0.14.0 accelerate==1.2.1 bitsandbytes==0.45.2 wandb==0.19.7 --progress-bar off
!pip install -qqq flash-attn --no-build-isolation --progress-bar off

import torch
from datasets import load_dataset
from peft import LoraConfig, get_peft_model
from transformers import AutoModelForCausalLM, AutoTokenizer
from trl import GRPOConfig, GRPOTrainer

import wandb

wandb.login()

dataset = load_dataset("mlabonne/smoltldr")
print(dataset)

model_id = "HuggingFaceTB/SmolLM-135M-Instruct"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    attn_implementation="flash_attention_2",
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Load LoRA
lora_config = LoraConfig(
    task_type="CAUSAL_LM",
    r=16,
    lora_alpha=32,
    target_modules="all-linear",
)
model = get_peft_model(model, lora_config)
print(model.print_trainable_parameters())

# Reward function
ideal_length = 50


def reward_len(completions, **kwargs):
    return [-abs(ideal_length - len(completion)) for completion in completions]

# Training arguments
training_args = GRPOConfig(
    output_dir="GRPO",
    learning_rate=2e-5,
    per_device_train_batch_size=8,
    gradient_accumulation_steps=2,
    max_prompt_length=512,
    max_completion_length=96,
    num_generations=8,
    optim="adamw_8bit",
    num_train_epochs=1,
    bf16=True,
    report_to=["wandb"],
    remove_unused_columns=False,
    logging_steps=1,
)

# Trainer
trainer = GRPOTrainer(
    model=model,
    reward_funcs=[reward_len],
    args=training_args,
    train_dataset=dataset["train"],
)

# Train model
wandb.init(project="GRPO")
trainer.train()

merged_model = trainer.model.merge_and_unload()
merged_model.push_to_hub(
    "SmolGRPO-135M", private=False, tags=["GRPO", "Reasoning-Course"]
)

prompt = """
# A long document about the Cat

The cat (Felis catus), also referred to as the domestic cat or house cat, is a small 
domesticated carnivorous mammal. It is the only domesticated species of the family Felidae.
Advances in archaeology and genetics have shown that the domestication of the cat occurred
in the Near East around 7500 BC. It is commonly kept as a pet and farm cat, but also ranges
freely as a feral cat avoiding human contact. It is valued by humans for companionship and
its ability to kill vermin. Its retractable claws are adapted to killing small prey species
such as mice and rats. It has a strong, flexible body, quick reflexes, and sharp teeth,
and its night vision and sense of smell are well developed. It is a social species,
but a solitary hunter and a crepuscular predator. Cat communication includes
vocalizations—including meowing, purring, trilling, hissing, growling, and grunting—as
well as body language. It can hear sounds too faint or too high in frequency for human ears,
such as those made by small mammals. It secretes and perceives pheromones.
"""

messages = [
    {"role": "user", "content": prompt},
]

# Generate text
from transformers import pipeline

generator = pipeline("text-generation", model="SmolGRPO-135M")

## Or use the model and tokenizer we defined earlier
# generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

generate_kwargs = {
    "max_new_tokens": 256,
    "do_sample": True,
    "temperature": 0.5,
    "min_p": 0.1,
}

generated_text = generator(messages, generate_kwargs=generate_kwargs)

print(generated_text)