Downloads · 30 days
5
24% of all-time downloads
Abdelatif94/abdelatif-abualya-c7b863-lora
abdelatif-abualya-c7b863-lora is a machine learning model from Abdelatif94. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
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.
Downloads · 30 days
5
24% of all-time downloads
All-time downloads
21
Public
Repo size
275 MB
Likes
0
Public
Click a slice to open those files.
.safetensors275 MB · 100%
From the Hugging Face model README
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.
This model was fine-tuned using multiple datasets and resources, including:
⚠️ 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.
To use this fine-tuned LoRA adapter, first load the base model and then apply the adapter:
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]))