phi3_5_finetuning.py

from unsloth import FastLanguageModel, is_bfloat16_supported
from unsloth.chat_templates import get_chat_template
from datasets import load_dataset
from trl import SFTTrainer
from transformers import TrainingArguments, TextStreamer
import torch

max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.

# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
fourbit_models = [
    "unsloth/Meta-Llama-3.1-8B-bnb-4bit",      # Llama-3.1 15 trillion tokens model 2x faster!
    "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
    "unsloth/Meta-Llama-3.1-70B-bnb-4bit",
    "unsloth/Meta-Llama-3.1-405B-bnb-4bit",    # We also uploaded 4bit for 405b!
    "unsloth/Mistral-Nemo-Base-2407-bnb-4bit", # New Mistral 12b 2x faster!
    "unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit",
    "unsloth/mistral-7b-v0.3-bnb-4bit",        # Mistral v3 2x faster!
    "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
    "unsloth/Phi-3.5-mini-instruct",           # Phi-3.5 2x faster!
    "unsloth/Phi-3-medium-4k-instruct",
    "unsloth/gemma-2-9b-bnb-4bit",
    "unsloth/gemma-2-27b-bnb-4bit",            # Gemma 2x faster!
] # More models at https://huggingface.co/unsloth

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/Phi-3.5-mini-instruct",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
)

"""We now add LoRA adapters so we only need to update 1 to 10% of all parameters!"""

model = FastLanguageModel.get_peft_model(
    model,
    r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj",],
    lora_alpha = 16,
    lora_dropout = 0, # Supports any, but = 0 is optimized
    bias = "none",    # Supports any, but = "none" is optimized
    # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
    random_state = 3407,
    use_rslora = False,  # We support rank stabilized LoRA
    loftq_config = None, # And LoftQ
)

"""<a name="Data"></a>
### Data Prep
We now use the `Phi-3` format for conversation style finetunes. We use [Open Assistant conversations](https://huggingface.co/datasets/philschmid/guanaco-sharegpt-style) in ShareGPT style. Phi-3 renders multi turn conversations like below:

```
<|user|>
Hi!<|end|>
<|assistant|>
Hello! How are you?<|end|>
<|user|>
I'm doing great! And you?<|end|>

```

**[NOTE]** To train only on completions (ignoring the user's input) read Unsloth's docs [here](https://github.com/unslothai/unsloth/wiki#train-on-completions--responses-only-do-not-train-on-inputs).

We use our `get_chat_template` function to get the correct chat template. We support `zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old` and our own optimized `unsloth` template.

Note ShareGPT uses `{"from": "human", "value" : "Hi"}` and not `{"role": "user", "content" : "Hi"}`, so we use `mapping` to map it.

For text completions like novel writing, try this [notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing).
"""

tokenizer = get_chat_template(
    tokenizer,
    chat_template = "phi-3", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth
    mapping = {"role" : "from", "content" : "value", "user" : "human", "assistant" : "gpt"}, # ShareGPT style
)

def formatting_prompts_func(examples):
    convos = examples["conversations"]
    texts = [tokenizer.apply_chat_template(convo, tokenize = False, add_generation_prompt = False) for convo in convos]
    return { "text" : texts, }
pass

dataset = load_dataset("philschmid/guanaco-sharegpt-style", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)

"""Let's see how the `Phi-3` format works by printing the 5th element"""

dataset[5]["conversations"]

print(dataset[5]["text"])

"""If you're looking to make your own chat template, that also is possible! You must use the Jinja templating regime. We provide our own stripped down version of the `Unsloth template` which we find to be more efficient, and leverages ChatML, Zephyr and Alpaca styles.

More info on chat templates on [our wiki page!](https://github.com/unslothai/unsloth/wiki#chat-templates)
"""

unsloth_template = \
    "{{ bos_token }}"\
    "{{ 'You are a helpful assistant to the user\n' }}"\
    "{% for message in messages %}"\
        "{% if message['role'] == 'user' %}"\
            "{{ '>>> User: ' + message['content'] + '\n' }}"\
        "{% elif message['role'] == 'assistant' %}"\
            "{{ '>>> Assistant: ' + message['content'] + eos_token + '\n' }}"\
        "{% endif %}"\
    "{% endfor %}"\
    "{% if add_generation_prompt %}"\
        "{{ '>>> Assistant: ' }}"\
    "{% endif %}"
unsloth_eos_token = "eos_token"

if False:
    tokenizer = get_chat_template(
        tokenizer,
        chat_template = (unsloth_template, unsloth_eos_token,), # You must provide a template and EOS token
        mapping = {"role" : "from", "content" : "value", "user" : "human", "assistant" : "gpt"}, # ShareGPT style
        map_eos_token = True, # Maps <|im_end|> to </s> instead
    )

"""<a name="Train"></a>
### Train the model
Now let's use Huggingface TRL's `SFTTrainer`! More docs here: [TRL SFT docs](https://huggingface.co/docs/trl/sft_trainer). We do 60 steps to speed things up, but you can set `num_train_epochs=1` for a full run, and turn off `max_steps=None`. We also support TRL's `DPOTrainer`!
"""

trainer = SFTTrainer(
    model = model,
    tokenizer = tokenizer,
    train_dataset = dataset,
    dataset_text_field = "text",
    max_seq_length = max_seq_length,
    dataset_num_proc = 2,
    packing = False, # Can make training 5x faster for short sequences.
    args = TrainingArguments(
        per_device_train_batch_size = 2,
        gradient_accumulation_steps = 4,
        warmup_steps = 5,
        max_steps = 60,
        learning_rate = 2e-4,
        fp16 = not is_bfloat16_supported(),
        bf16 = is_bfloat16_supported(),
        logging_steps = 1,
        optim = "adamw_8bit",
        weight_decay = 0.01,
        lr_scheduler_type = "linear",
        seed = 3407,
        output_dir = "outputs",
        report_to = "none", # Use this for WandB etc
    ),
)

#@title Show current memory stats
gpu_stats = torch.cuda.get_device_properties(0)
start_gpu_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)
max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3)
print(f"GPU = {gpu_stats.name}. Max memory = {max_memory} GB.")
print(f"{start_gpu_memory} GB of memory reserved.")

trainer_stats = trainer.train()

#@title Show final memory and time stats
used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)
used_memory_for_lora = round(used_memory - start_gpu_memory, 3)
used_percentage = round(used_memory         /max_memory*100, 3)
lora_percentage = round(used_memory_for_lora/max_memory*100, 3)
print(f"{trainer_stats.metrics['train_runtime']} seconds used for training.")
print(f"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.")
print(f"Peak reserved memory = {used_memory} GB.")
print(f"Peak reserved memory for training = {used_memory_for_lora} GB.")
print(f"Peak reserved memory % of max memory = {used_percentage} %.")
print(f"Peak reserved memory for training % of max memory = {lora_percentage} %.")

"""<a name="Inference"></a>
### Inference
Let's run the model! Since we're using `Phi-3`, use `apply_chat_template` with `add_generation_prompt` set to `True` for inference.
"""

tokenizer = get_chat_template(
    tokenizer,
    chat_template = "phi-3", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth
    mapping = {"role" : "from", "content" : "value", "user" : "human", "assistant" : "gpt"}, # ShareGPT style
)

FastLanguageModel.for_inference(model) # Enable native 2x faster inference

messages = [
    {"from": "human", "value": "Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,"},
]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True, # Must add for generation
    return_tensors = "pt",
).to("cuda")

outputs = model.generate(input_ids = inputs, max_new_tokens = 64, use_cache = True)
tokenizer.batch_decode(outputs)

""" You can also use a `TextStreamer` for continuous inference - so you can see the generation token by token, instead of waiting the whole time!"""

FastLanguageModel.for_inference(model) # Enable native 2x faster inference

messages = [
    {"from": "human", "value": "Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,"},
]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True, # Must add for generation
    return_tensors = "pt",
).to("cuda")

text_streamer = TextStreamer(tokenizer, skip_prompt = True)
_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 128, use_cache = True)

"""<a name="Save"></a>
### Saving, loading finetuned models
To save the final model as LoRA adapters, either use Huggingface's `push_to_hub` for an online save or `save_pretrained` for a local save.

**[NOTE]** This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!
"""

model.save_pretrained("phi_3_5_lora_model") # Local saving
tokenizer.save_pretrained("phi_3_5_lora_model")
# model.push_to_hub("your_name/lora_model", token = "...") # Online saving
# tokenizer.push_to_hub("your_name/lora_model", token = "...") # Online saving

"""Now if you want to load the LoRA adapters we just saved for inference, set `False` to `True`:"""

if False:
    from unsloth import FastLanguageModel
    model, tokenizer = FastLanguageModel.from_pretrained(
        model_name = "phi_3_5_lora_model", # YOUR MODEL YOU USED FOR TRAINING
        max_seq_length = max_seq_length,
        dtype = dtype,
        load_in_4bit = load_in_4bit,
    )
    FastLanguageModel.for_inference(model) # Enable native 2x faster inference

messages = [
    {"from": "human", "value": "What is a famous tall tower in Paris?"},
]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True, # Must add for generation
    return_tensors = "pt",
).to("cuda")

text_streamer = TextStreamer(tokenizer, skip_prompt = True)
_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 128, use_cache = True)

"""You can also use Hugging Face's `AutoModelForPeftCausalLM`. Only use this if you do not have `unsloth` installed. It can be hopelessly slow, since `4bit` model downloading is not supported, and Unsloth's **inference is 2x faster**."""

if False:
    # I highly do NOT suggest - use Unsloth if possible
    from peft import AutoPeftModelForCausalLM
    from transformers import AutoTokenizer
    model = AutoPeftModelForCausalLM.from_pretrained(
        "lora_model", # YOUR MODEL YOU USED FOR TRAINING
        load_in_4bit = load_in_4bit,
    )
    tokenizer = AutoTokenizer.from_pretrained("lora_model")

"""### Saving to float16 for VLLM

We also support saving to `float16` directly. Select `merged_16bit` for float16 or `merged_4bit` for int4. We also allow `lora` adapters as a fallback. Use `push_to_hub_merged` to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens.
"""

# Merge to 16bit
if False: model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)
if False: model.push_to_hub_merged("hf/model", tokenizer, save_method = "merged_16bit", token = "")

# Merge to 4bit
if False: model.save_pretrained_merged("model", tokenizer, save_method = "merged_4bit",)
if False: model.push_to_hub_merged("hf/model", tokenizer, save_method = "merged_4bit", token = "")

# Just LoRA adapters
if False: model.save_pretrained_merged("model", tokenizer, save_method = "lora",)
if False: model.push_to_hub_merged("hf/model", tokenizer, save_method = "lora", token = "")

"""### GGUF / llama.cpp Conversion
To save to `GGUF` / `llama.cpp`, we support it natively now! We clone `llama.cpp` and we default save it to `q8_0`. We allow all methods like `q4_k_m`. Use `save_pretrained_gguf` for local saving and `push_to_hub_gguf` for uploading to HF.

Some supported quant methods (full list on our [Wiki page](https://github.com/unslothai/unsloth/wiki#gguf-quantization-options)):
* `q8_0` - Fast conversion. High resource use, but generally acceptable.
* `q4_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.
* `q5_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.

[**NEW**] To finetune and auto export to Ollama, try our [Ollama notebook](https://colab.research.google.com/drive/1WZDi7APtQ9VsvOrQSSC5DDtxq159j8iZ?usp=sharing)
"""

# Save to 8bit Q8_0
if False: model.save_pretrained_gguf("model", tokenizer,)
# Remember to go to https://huggingface.co/settings/tokens for a token!
# And change hf to your username!
if False: model.push_to_hub_gguf("hf/model", tokenizer, token = "")

# Save to 16bit GGUF
if False: model.save_pretrained_gguf("model", tokenizer, quantization_method = "f16")
if False: model.push_to_hub_gguf("hf/model", tokenizer, quantization_method = "f16", token = "")

# Save to q4_k_m GGUF
if False: model.save_pretrained_gguf("model", tokenizer, quantization_method = "q4_k_m")
if False: model.push_to_hub_gguf("hf/model", tokenizer, quantization_method = "q4_k_m", token = "")

# Save to multiple GGUF options - much faster if you want multiple!
if False:
    model.push_to_hub_gguf(
        "hf/model", # Change hf to your username!
        tokenizer,
        quantization_method = ["q4_k_m", "q8_0", "q5_k_m",],
        token = "", # Get a token at https://huggingface.co/settings/tokens
    )

# Now, use the `model-unsloth.gguf` file or `model-unsloth-Q4_K_M.gguf` file in `llama.cpp` or a UI based system like `GPT4All`. You can install GPT4All by going [here](https://gpt4all.io/index.html).