You can deploy this model and start earning money today!

Abdelatif94/
abdelatif-abualya-c7b863-lora

Name: abdelatif-abualya-c7b863-lora
Availability: InStock

peft

safetensors

Qwen/Qwen2.5-Coder-14B-Instruct

adapter

apache-2.0

Views

No views yet

Abdelatif-Abualya Fine-Tuned Model

This model is a LoRA fine-tuned adapter based on Qwen2.5-Coder-14B-Instruct. It has been trained on additional data to improve performance in specific coding-related tasks.

Acknowledgements

This model was fine-tuned using multiple datasets and resources, including:

AWS SageMaker Example Guides (Licensed under Apache 2.0)
DeepSeek-SM-Deploy-Options Notebook from the "host-deepseek-distilled-models-on-aws" repository (Licensed under MIT No Attribution)

⚠️ Disclaimer This model is provided "as is" without warranty of any kind. While efforts have been made to fine-tune and optimize it for coding-related tasks, results may vary depending on input prompts.

🛠️ How to Use

To use this fine-tuned LoRA adapter, first load the base model and then apply the adapter:

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = "Qwen/Qwen2.5-Coder-14B-Instruct"
adapter_model = "Abdelatif94/abdelatif-abualya-c7b863-lora"

model = AutoModelForCausalLM.from_pretrained(base_model)
model = PeftModel.from_pretrained(model, adapter_model)
tokenizer = AutoTokenizer.from_pretrained(base_model)

# Test inference
input_text = "Write a Python function to reverse a string."
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))