Instructions to use millat/Qwen2.5-7B-BDLAW-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use millat/Qwen2.5-7B-BDLAW-LoRA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "millat/Qwen2.5-7B-BDLAW-LoRA")

llama-cpp-python

How to use millat/Qwen2.5-7B-BDLAW-LoRA with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="millat/Qwen2.5-7B-BDLAW-LoRA",
	filename="gguf/qwen25_7b_bdlaw_f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use millat/Qwen2.5-7B-BDLAW-LoRA with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Use Docker

docker model run hf.co/millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

LM Studio
Jan
Ollama
How to use millat/Qwen2.5-7B-BDLAW-LoRA with Ollama:
```
ollama run hf.co/millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M
```

Unsloth Studio

How to use millat/Qwen2.5-7B-BDLAW-LoRA with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for millat/Qwen2.5-7B-BDLAW-LoRA to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for millat/Qwen2.5-7B-BDLAW-LoRA to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for millat/Qwen2.5-7B-BDLAW-LoRA to start chatting

How to use millat/Qwen2.5-7B-BDLAW-LoRA with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use millat/Qwen2.5-7B-BDLAW-LoRA with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use millat/Qwen2.5-7B-BDLAW-LoRA with Docker Model Runner:
```
docker model run hf.co/millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M
```

Lemonade

How to use millat/Qwen2.5-7B-BDLAW-LoRA with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull millat/Qwen2.5-7B-BDLAW-LoRA:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-7B-BDLAW-LoRA-Q4_K_M

List all available models

lemonade list

Qwen 2.5 7B Instruct - Bangladesh Legal LoRA Adapter

A fine-tuned LoRA adapter for Qwen 2.5 7B Instruct specialized in Bangladesh legal reasoning and legal document analysis.

📋 Model Details

Property	Value
Base Model	Qwen/Qwen2.5-7B-Instruct
Adapter Type	LoRA (Low-Rank Adaptation)
LoRA Rank (r)	64
LoRA Alpha (α)	128
Target Modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Training Dataset	BDLawCorpus Dataset V1
Training Examples	4,710 Bangla legal documents
Training Epochs	3
Training Hours	~6.5 hours on 2x T4 GPU
Precision	FP16 mixed precision + 4-bit quantization
Batch Size	8 (per device)
Learning Rate	2e-4
Quantization	4-bit NF4 (train) / Optional for inference

🚀 Quick Start

Installation

pip install transformers peft torch accelerate

Loading the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel

# Base model
model_id = "Qwen/Qwen2.5-7B-Instruct"
adapter_id = "millat/qwen-2.5-7b-instruct-bdlaw-lora"

# Load base model (with optional 4-bit quantization)
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16
)

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    quantization_config=bnb_config,
    torch_dtype=torch.float16,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_id)

# Attach LoRA adapter
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

Inference Example

# Bangla legal query
prompt = "বাংলাদেশে চুক্তি আইন কী এবং এর প্রধান বৈশিষ্ট্য কি?"

# Format with chat template
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Generate response
inputs = tokenizer(text, return_tensors="pt").to("cuda")
outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    temperature=0.7,
    do_sample=True,
    top_p=0.95,
    pad_token_id=tokenizer.eos_token_id,
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

📊 Training Details

Dataset

BDLawCorpus Dataset V1 contains:

4,710 Bangla legal documents and case studies
Multi-format: Chat templates with conversation pairs
Topics: Contract Law, Criminal Law, Constitutional Law, Property Law, Labor Law
Quality: Manually validated and cleaned

Training Configuration

# Quantization (4-bit)
load_in_4bit=True
bnb_4bit_use_double_quant=True
bnb_4bit_quant_type="nf4"
bnb_4bit_compute_dtype=torch.float16

# LoRA Configuration
r=64                    # Rank
lora_alpha=128         # Scaling factor
lora_dropout=0.05
bias="none"
task_type="CAUSAL_LM"

# Training Arguments
num_train_epochs=3
per_device_train_batch_size=8
gradient_accumulation_steps=2
learning_rate=2e-4
weight_decay=0.01
warmup_steps=100
save_steps=200
save_total_limit=3
logging_steps=10
fp16=True
gradient_checkpointing=True
ddp_find_unused_parameters=False

Training Environment

Hardware: Kaggle 2x T4 GPU (15GB each)
Framework: Hugging Face Transformers + PEFT + Accelerate
Parallelism: Distributed Data Parallel (DDP)
Total Training Time: ~6.5 hours
Final Loss: 0.112

💡 Use Cases

This model is optimized for:

Legal Document Summarization - Summarize Bangla legal texts and acts
Legal Question Answering - Answer questions about Bangladesh law
Contract Analysis - Analyze and explain contract clauses
Case Law Explanation - Provide insights into court decisions
Regulatory Compliance - Advise on Bangladesh legal compliance
Document Classification - Categorize legal documents
Legal Research - Retrieve relevant case law and precedents

📈 Performance Metrics

Metric	Value
Training Loss	0.112
Samples/Second	0.608
Steps/Second	0.076
Total Training Steps	1,764
Memory Used (per GPU)	~14.4 GB
Model Size (Adapter only)	~131 MB

⚖️ Limitations

Language-specific: Optimized for Bangla legal documents; English queries may have lower accuracy
Domain-specific: Trained on Bangladesh legal corpus; may not generalize to other domains
Knowledge cutoff: Based on training data; may not reflect recent legal changes
LLM limitations: Can hallucinate; always verify outputs with official sources
No real-time updates: Requires retraining for new laws or amendments

🔧 Fine-tuning & Adaptation

To further fine-tune this adapter on your own data:

from transformers import TrainingArguments, Trainer

training_args = TrainingArguments(
    output_dir="./my_adapter",
    num_train_epochs=2,
    per_device_train_batch_size=8,
    learning_rate=1e-4,
    save_steps=100,
    logging_steps=10,
    fp16=True,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=your_dataset,
    data_collator=data_collator,
)

trainer.train()

📝 Citation

If you use this model, please cite:

@model{qwen_bdlaw_lora_2025,
  title={Qwen 2.5 7B Instruct - Bangladesh Legal LoRA Adapter},
  author={MD Millat Hosen},
  organization={BDLaw Corpus Project},
  year={2025},
  howpublished={\url{https://huggingface.co/millat/qwen-2.5-7b-instruct-bdlaw-lora}},
}

📄 License

This adapter is provided under the Creative Commons Attribution 4.0 International (CC-BY-4.0) license.

The base model (Qwen 2.5 7B) is licensed under the Qwen License Agreement. Please refer to the original model card for details.

👥 Contact & Support

Model Developer: MD Millat Hosen
Project: BDLawCorpus
Email: Contact via GitHub issues
Repository: BDLawCorpus GitHub

🙏 Acknowledgments

Qwen Team for the excellent base model architecture
Hugging Face for the transformers library and model hosting
Kaggle for providing free GPU compute
Bangladesh Legal Community for data and domain expertise

⚠️ Disclaimer

This model is provided for educational and research purposes. While we strive for accuracy, legal advice should always be verified with qualified legal professionals. The model authors assume no responsibility for any consequences arising from the use of this model for legal decision-making.

🔄 Model Updates

Version	Date	Notes
v1.0	May 2025	Initial release - 4,710 training examples

Last Updated: May 9, 2025
Model Version: 1.0
Status: ✅ Production Ready

Downloads last month: 70

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for millat/Qwen2.5-7B-BDLAW-LoRA

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2185)

this model

millat
/

Qwen2.5-7B-BDLAW-LoRA