Qwen-Instruct_Finetune_For_Docker_Commands

Model Card for Qwen-Instruct_Fine_For_Docker_Commands

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct, trained on the dockerNLcommands dataset. It specializes in converting natural-language instructions into accurate and efficient Docker commands. The fine-tuning process enhances the model’s ability to understand real-world Docker workflows, making it useful for developers, DevOps engineers, and anyone working with containerized environments.

Quick start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "azherali/Qwen-Instruct_Finetune_For_Docker_Commands"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)




# List all containers with Ubuntu as their ancestor.
# docker ps --filter 'ancestor=ubuntu'

prompt = "List all containers with Ubuntu as their ancestor."
messages = [
    {"role": "system", "content": "translate this sentence in docker command"},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.25.1
• Transformers: 4.57.1
• Pytorch: 2.8.0+cu126
• Datasets: 4.4.1
• Tokenizers: 0.22.1