You can deploy this model and start earning money today!

newmindai/
Llama-3.1-8B-Instruct-intellectual-chat-template

Name: Llama-3.1-8B-Instruct-intellectual-chat-template
Availability: InStock

newmindai/EuroHPC-Legal

meta-llama/Llama-3.1-8B-Instruct

finetune

llama3.1

Views

No views yet

Model Card

This document describes a parameter-efficient fine-tuning setup using LoRA on the EuroHPC Karolina system. Axolotl provides flexible orchestration and Unsloth supplies optimized kernels for high-throughput training on the EuroHPC-Legal dataset. This model is fine-tuned using Parameter-Efficient Fine-Tuning (PEFT) with LoRA (Low-Rank Adaptation) on the EuroHPC dataset, specifically the intellectual subset. The fine-tuning leverages the Axolotl framework for orchestration and Unsloth library for optimized training kernels.

Hyperparameters

LoRA Rank: 16
LoRA Alpha: 32
LoRA Dropout: 0.05
Learning Rate: 3×10⁻⁵ with cosine scheduling
Training Epochs: 3 per domain
Batch Size: Optimized for A100 memory capacity

Architecture

Base Model: Llama-3.1-8B-Instruct (Meta)
Fine-tuning Method: LoRA (Low-Rank Adaptation)
Parameter Efficiency: Only trainable LoRA parameters, frozen base model
Model Size: 8B parameters (base) + LoRA adapters

Hardware and Software

Orchestration: Axolotl framework
Acceleration: Unsloth library
Backend: PyTorch with CUDA support
System: EuroHPC Karolina supercomputer
GPUs: NVIDIA A100 (8 × 40 GB per node, 320 GB HBM2 total)
Utilization: 85–90% GPU and memory efficiency
Total Compute: ~600 GPU hours

Data

Input Format

The dataset follows the Chat Template format with conversation structure:

json

{
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant specialized in Turkish legal matters."
    },
    {
      "role": "user",
      "content": "Question or task description"
    },
    {
      "role": "assistant",
      "content": "Response or answer"
    }
  ]
}

Dataset: newmindai/EuroHPC-Legal (intellectual subset)

How to Use

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "newmindai/Llama-3.1-8B-Instruct-intellectual-chat-template")

# Use chat template for formatting
messages = [
    {"role": "system", "content": "You are a helpful assistant specialized in Turkish legal matters."},
    {"role": "user", "content": "Explain the benefits of regular exercise"}
]

# Apply chat template
tokenizer.chat_template = tokenizer.default_chat_template
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Example usage
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Acknowledgments

This research was supported by the EuroHPC Joint Undertaking (EuroHPC JU) under the Benchmark Access grant agreement No EHPC-BEN-2024B11-003. The authors gratefully acknowledge the computational resources provided by the IT4Innovations National Supercomputing Center (Czech Republic) on the Karolina supercomputer, made available through the EuroHPC JU.

Citation

bibtex

@article{newmind2025,
  title={Tailoring AI for Turkish Law: Domain-Specific Fine-Tuning of Small Language Models for Legal Expertise},
  author={New Mind AI Team},
  journal={Procedia Computer Science},
  year={2025},
  volume={239},
  doi={10.1016/j.procs.2025.08.239},
  note={Available online 23 September 2025, Version of Record 23 September 2025}
}