dataset = load_dataset(dataset_name, split=“train”)
compute_dtype = getattr(torch, bnb_4bit_compute_dtype)
bnb_config = BitsAndBytesConfig(
load_in_4bit=use_4bit,
bnb_4bit_quant_type=bnb_4bit_quant_type,
bnb_4bit_compute_dtype=compute_dtype,
bnb_4bit_use_double_quant=use_nested_quant,
)
if compute_dtype == torch.float16 and use_4bit:
major, _ = torch.cuda.get_device_capability()
if major >= 8:
print(“=” * 80)
print(“Your GPU supports bfloat16: accelerate training with bf16=True”)
print(“=” * 80)
model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=bnb_config,
device_map=device_map
)
model.config.use_cache = False
model.config.pretraining_tp = 1
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = “right”
peft_config = LoraConfig(
lora_alpha=lora_alpha,
lora_dropout=lora_dropout,
r=lora_r,
bias=“none”,
task_type=“CAUSAL_LM”,
)
training_arguments = TrainingArguments(
output_dir=output_dir,
num_train_epochs=num_train_epochs,
per_device_train_batch_size=per_device_train_batch_size,
gradient_accumulation_steps=gradient_accumulation_steps,
optim=optim,
save_steps=save_steps,
logging_steps=logging_steps,
learning_rate=learning_rate,
weight_decay=weight_decay,
fp16=fp16,
bf16=bf16,
max_grad_norm=max_grad_norm,
max_steps=max_steps,
warmup_ratio=warmup_ratio,
group_by_length=group_by_length,
lr_scheduler_type=lr_scheduler_type,
report_to=“tensorboard”
)
trainer = SFTTrainer(
model=model,
train_dataset=dataset,
peft_config=peft_config,
dataset_text_field=“text”,
max_seq_length=max_seq_length,
tokenizer=tokenizer,
args=training_arguments,
packing=packing,
)
trainer.train()
trainer.model.save_pretrained(new_model)
ValueError Traceback (most recent call last)
in <cell line: 32>()
30
31 # Load LLaMA tokenizer
—> 32 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
33 tokenizer.pad_token = tokenizer.eos_token
34 tokenizer.padding_side = “right”
4 frames
/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_fast.py in init(self, *args, **kwargs)
118 fast_tokenizer = convert_slow_tokenizer(slow_tokenizer)
119 else:
→ 120 raise ValueError(
121 “Couldn’t instantiate the backend tokenizer from one of: \n”
122 “(1) a tokenizers library serialization file, \n”
ValueError: Couldn’t instantiate the backend tokenizer from one of:
(1) a tokenizers library serialization file,
(2) a slow tokenizer instance to convert or
(3) an equivalent slow tokenizer class to instantiate and convert.
You need to have sentencepiece installed to convert a slow tokenizer to a fast one.
This code worked fine with the 7B version of this model. All I did was change it to the 13B version and now I’m getting this error. Please let me know what you think is wrong. Thanks.