Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/x/.venv/lib/python3.10/site-packages/unsloth/save.py", line 1211, in unsloth_push_to_hub_merged
    unsloth_save_model(**arguments)
  File "/x/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/x/.venv/lib/python3.10/site-packages/unsloth/save.py", line 686, in unsloth_save_model
    internal_model.save_pretrained(**save_pretrained_settings)
  File "/x/.venv/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2634, in save_pretrained
    model_card = create_and_tag_model_card(
  File "/x/projects/mistral-finetune/.venv/lib/python3.10/site-packages/transformers/utils/hub.py", line 1144, in create_and_tag_model_card
    if model_tag not in model_card.data.tags:
TypeError: argument of type 'NoneType' is not iterable

from unsloth import FastLanguageModel
import torch
from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported


from utils import dataset 

max_seq_length = 1048

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/mistral-7b-instruct-v0.3", # Choose ANY! eg teknium/OpenHermes-2.5-Mistral-7B
    max_seq_length = 1048,
    dtype = None,
    load_in_4bit = True,
    )

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 = 239,
    use_rslora = False,  # We support rank stabilized LoRA
    loftq_config = None, # And LoftQ
    )


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 = 10,
        gradient_accumulation_steps = 4,
        warmup_steps = 5,
        #num_train_epochs = 1, 
        max_steps = 1, # Set num_train_epochs = 1 for full training runs
        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 = 239,
        output_dir = "outputs",
    ),
)

trainer_stats = trainer.train()


model.push_to_hub_merged("user/this-is-my-project", tokenizer, save_method = "merged_16bit", token)

model.push_to_hub("user/this-is-my-project", token = token) 
tokenizer.push_to_hub("user/this-is-my-project", token = token) 

accelerate==0.31.0
aiohttp==3.9.5
aiosignal==1.3.1
async-timeout==4.0.3
attrs==23.2.0
bitsandbytes==0.43.1
certifi==2024.6.2
charset-normalizer==3.3.2
datasets==2.20.0
dill==0.3.7
docstring_parser==0.16
einops==0.8.0
filelock==3.15.1
flash-attn==2.5.9.post1
frozenlist==1.4.1
fsspec==2024.5.0
huggingface-hub==0.23.4
idna==3.7
Jinja2==3.1.4
markdown-it-py==3.0.0
MarkupSafe==2.1.5
mdurl==0.1.2
mpmath==1.3.0
multidict==6.0.5
multiprocess==0.70.15
networkx==3.3
ninja==1.11.1.1
numpy==2.0.0
nvidia-cublas-cu12==12.1.3.1
nvidia-cuda-cupti-cu12==12.1.105
nvidia-cuda-nvrtc-cu12==12.1.105
nvidia-cuda-runtime-cu12==12.1.105
nvidia-cudnn-cu12==8.9.2.26
nvidia-cufft-cu12==11.0.2.54
nvidia-curand-cu12==10.3.2.106
nvidia-cusolver-cu12==11.4.5.107
nvidia-cusparse-cu12==12.1.0.106
nvidia-nccl-cu12==2.20.5
nvidia-nvjitlink-cu12==12.5.40
nvidia-nvtx-cu12==12.1.105
packaging==24.1
pandas==2.2.2
peft==0.11.1
protobuf==3.20.3
psutil==5.9.8
pyarrow==16.1.0
pyarrow-hotfix==0.6
Pygments==2.18.0
python-dateutil==2.9.0.post0
pytz==2024.1
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
rich==13.7.1
safetensors==0.4.3
sentencepiece==0.2.0
shtab==1.7.1
six==1.16.0
sympy==1.12.1
tokenizers==0.19.1
torch==2.3.0
tqdm==4.66.4
transformers==4.41.2
triton==2.3.0
trl==0.8.6
typing_extensions==4.12.2
tyro==0.8.4
tzdata==2024.1
unsloth @ git+https://github.com/unslothai/unsloth.git@87703089fa0ad60f008b7a7990f5cf3e77ccd26e
urllib3==2.2.2
xformers==0.0.26.post1
xxhash==3.4.1
yarl==1.9.4