GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nileshkendre
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
nileshkendre
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This repository contains a Parameter-Efficient Fine-Tuned (PEFT) version of Qwen2.5-3B-Instruct using the QLoRA (Quantized Low-Rank Adaptation) technique.
The objective of this project was to implement an end-to-end Large Language Model (LLM) fine-tuning pipeline using the Hugging Face ecosystem. The model was instruction-tuned on the Guanaco LLaMA2 1K dataset using TRL's SFTTrainer, 4-bit quantization, and LoRA adapters.
This project demonstrates practical experience with modern LLM fine-tuning techniques, efficient GPU utilization, and model publishing on Hugging Face Hub.
| Item | Value |
|---|---|
| Base Model | Qwen/Qwen2.5-3B-Instruct |
| Model Size | 3 Billion Parameters |
| Fine-Tuning Method | PEFT |
| Technique | QLoRA |
| Training Method | Supervised Fine-Tuning (SFT) |
| Framework | Hugging Face Transformers |
| Trainer | TRL SFTTrainer |
| Quantization | 4-bit NF4 |
| Dataset | mlabonne/guanaco-llama2-1k |
| Hardware | NVIDIA Tesla T4 GPU |
The primary objective of this project was to gain hands-on experience with parameter-efficient fine-tuning of Large Language Models while minimizing GPU memory consumption.
The project covers the complete workflow:
The model was fine-tuned using the public mlabonne/guanaco-llama2-1k instruction dataset.
Dataset characteristics:
The end-to-end workflow consisted of the following steps:
| Parameter | Value |
|---|---|
| Epochs | 1 |
| Batch Size | 1 |
| Gradient Accumulation | 2 |
| Learning Rate | 2e-4 |
| Optimizer | paged_adamw_8bit |
| Precision | BF16 |
| Quantization | 4-bit NF4 |
| Double Quantization | Enabled |
| Max Sequence Length | 1024 |
LoRA adapters were applied to the following transformer projection layers:
| Metric | Value |
|---|---|
| Total Parameters | 3.21 Billion |
| Trainable Parameters | 119.7 Million |
| Trainable Percentage | 3.74% |
Only LoRA adapter weights were updated during training while the original Qwen base model remained frozen.
Parameter-Efficient Fine-Tuning (PEFT) enables efficient adaptation of Large Language Models by training only a small subset of additional parameters instead of updating the entire model.
Benefits include:
QLoRA combines Low-Rank Adaptation (LoRA) with 4-bit quantization.
Advantages include:
markdown
adapter_config.jsonadapter_model.safetensorschat_template.jinjatokenizer.jsontokenizer_config.jsontraining_args.binREADME.md
python
from transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModelbase_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")model = PeftModel.from_pretrained(base_model,"nileshkendre/qwen2.5-3b-qlora-sft")
This repository contains only the LoRA adapter weights and does not include the original Qwen2.5-3B-Instruct base model.
The model was trained on the public mlabonne/guanaco-llama2-1k dataset containing approximately 1,000 instruction-response pairs. It is intended as an educational and portfolio project demonstrating the complete QLoRA fine-tuning workflow.
Additional domain-specific fine-tuning, evaluation, and safety testing would be required before production deployment.
Possible future enhancements include:
This project was built using the following open-source technologies:
Nilesh Kendre
AI / ML Engineer | Generative AI | LLMs | Agentic AI | RAG | NLP
This repository demonstrates hands-on implementation of modern Large Language Model fine-tuning using QLoRA, PEFT, TRL, and the Hugging Face ecosystem. The project showcases practical experience in parameter-efficient training, adapter-based fine-tuning, and model deployment workflows.
| LoRA Rank (r) | 64 |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.1 |