CoolFace
Modelpublic

adiiiii13/bubblesort-llm

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
0likes19downloads
Model Card

🫧 BubbleSort-LLM

A fine-tuned TinyLLaMA-1.1B model with company-specific knowledge about Bubblesort.in and its startups.

Model Details

Model Description

BubbleSort-LLM is a LoRA fine-tuned version of TinyLLaMA designed to answer questions about Bubblesort.in, a tech company and startup ecosystem founded by Aditya Routh. The model has been trained to provide accurate information about the company's various ventures and services.

  • —Developed by: Aditya Routh / Bubblesort.in
  • —Model type: Causal Language Model (LoRA Adapter)
  • —Language(s) (NLP): English
  • —License: Apache 2.0
  • —Finetuned from model: TinyLlama/TinyLlama-1.1B-Chat-v1.0

Model Sources

About Bubblesort.in

Bubblesort.in is the parent organization for multiple startups:

StartupDescriptionWebsite
🍛 Ghar Ka KhanaHomemade food service platformgharkakhana2026.in
💼 GKK InternInternship platform for studentsgkkintern.in
💚 PlutozSocial/NGO initiative for childrenplutoz1.netlify.app
🎨 APA CollectiveFreelancing agencyapacollective.netlify.app

Uses

Direct Use

This model can be used for:

  • —Answering questions about Bubblesort.in and its startups
  • —Customer support chatbots for Bubblesort.in services
  • —Information retrieval about company services

Out-of-Scope Use

  • —General knowledge questions (use base TinyLLaMA instead)
  • —Tasks requiring factual accuracy outside Bubblesort.in domain
  • —Production use without additional testing

How to Get Started with the Model

python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

# Load model
base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
model = PeftModel.from_pretrained(base_model, "adiiiii13/bubblesort-llm")
tokenizer = AutoTokenizer.from_pretrained("adiiiii13/bubblesort-llm")

# Create pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

# Chat format
messages = [
    {"role": "system", "content": "You are a helpful assistant for Bubblesort.in"},
    {"role": "user", "content": "What is Bubblesort.in?"}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
output = pipe(prompt, max_new_tokens=150, do_sample=True, temperature=0.7)
print(output[0]['generated_text'])

## Training Details

### Training Data

Custom dataset containing information about Bubblesort.in, its services, startups, and company details.

### Training Procedure

#### Training Hyperparameters

| Parameter | Value |
|-----------|-------|
| LoRA Rank (r) | 16 |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| Target Modules | q_proj, k_proj, v_proj, o_proj |
| Training regime | bf16 mixed precision |

## Technical Specifications

### Model Architecture and Objective

- **Architecture:** LLaMA-based transformer with LoRA adapters
- **Parameters:** ~18MB adapter weights
- **Objective:** Causal language modeling

### Compute Infrastructure

#### Hardware

- Kaggle GPU (T4/P100)

#### Software

- Transformers
- PEFT 0.18.1
- PyTorch

## Citation

@misc{bubblesort-llm, author = {Aditya Routh}, title = {BubbleSort-LLM: A Fine-tuned TinyLLaMA for Bubblesort.in}, year = {2026}, publisher = {HuggingFace}, url = {https://huggingface.co/adiiiii13/bubblesort-llm} }

Model Card Authors Aditya Routh (@adiiiii13)

Model Card Contact GitHub: aditya04slg Website: adityarouth.site Framework Versions PEFT: 0.18.1 Transformers: 4.x PyTorch: 2.x Made with 💜 by Bubblesort.in