QwQ-0.5B-Distilled

12

6

license:apache-2.0

by

kz919

Language Model

OTHER

0.5B params

New

12 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

2GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

1GB+ RAM

Code Examples

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Training Progress:pythontransformers

from datasets import Dataset
from trl import GKDConfig, GKDTrainer
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)
from datasets import load_dataset
from peft import LoraConfig

parser = argparse.ArgumentParser()
parser.add_argument("--temperature", type=float, default = 0.9)
parser.add_argument("--lmbda", type=float, default = 0.5)
parser.add_argument("--beta", type=float, default = 0.5)
parser.add_argument("--max_new_tokens", type=int, default = 4096)
parser.add_argument("--output_dir", type=str, default="gkd-model")
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
parser.add_argument("--lora", action="store_true")
args = parser.parse_args()

qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K", split = "train")
messages = []
for each in qwq_dataset:
    msg = [
        {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
        {"role": "user", "content": each["problem"]},
        {"role": "assistant", "content": each["qwq"]},
    ]
    messages.append(msg)

TRAIN_SPLIT_RATIO = 0.9
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
eval_size = len(messages) - train_size

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")




# The teacher model to calculate the KL divergence against
teacher_model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", torch_dtype=torch.bfloat16, device_map="auto") 
teacher_model.lm_head.weight.data = teacher_model.lm_head.weight.data[:151936, :]
teacher_model.lm_head.out_features = 151936



# The model to optimise
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") 



### Real Dataset
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
training_args = GKDConfig(
    output_dir=args.output_dir,
    temperature=args.temperature,
    lmbda=args.lmbda,
    beta=args.beta,
    max_new_tokens=args.max_new_tokens,
    per_device_train_batch_size=args.per_device_train_batch_size,
    gradient_accumulation_steps=args.gradient_accumulation_steps,
    gradient_checkpointing = args.gradient_checkpointing,
    save_steps = 100,
    save_total_limit = 5
    )

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)

trainer = GKDTrainer(
    model=model,
    teacher_model=teacher_model,
    args=training_args,
    processing_class=tokenizer,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    peft_config=lora_config if args.lora else None
)
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Dataset:pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Model name
model_name = "kz919/QwQ-0.5B-Distilled"

# Load the model
print(f"Starting to load the model {model_name} into memory")
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt
prompt = "How many r in strawberry."
messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": prompt}
]

# Tokenize the input
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate a response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

# Decode the response
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.