---
license: mit
tags:
- unsloth
- legal
language:
- tk
base_model:
- meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: table-question-answering
datasets:
- maximilianshwarzmullers/hukukchy
metrics:
- bleu
new_version: maximilianshwarzmullers/tm-hukuk
library_name: allennlp
---
# Model Card for Model ID
maximilianshwarzmullers/tm-hukuk

### Model Description

This is Turkmen LLM Finetuned in Turkmen law data

- **Developed by:** [Annamyrat Saparow]
- **Funded date:** [30.04.2025]
- **Shared date:** [07.05.2025]
- **Model type:** [Instruction model]
- **Language(s) (NLP):** [Turkmen, English]
- **License:** [MIT]
- **Finetuned from model [optional]:** [llama 3.1 8b instruct ]

### Model Sources [optional]

- **Repository:** [maximilianshwarzmullers/tm-hukuk]

### Training Data

Training data is maximilianshwarzmullers/hukukchy for law
It is my own dataset

### Training Procedure

QLora

#### Preprocessing [optional]

alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN
def formatting_prompts_func(examples):
    instructions = examples["instruction"]
    inputs       = examples["question"]
    outputs      = examples["answer"]
    texts = []
    for instruction, input, output in zip(instructions, inputs, outputs):
        # Must add EOS_TOKEN, otherwise your generation will go on forever!
        text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN
        texts.append(text)
    return { "text" : texts, }
pass

from datasets import load_dataset
dataset = load_dataset("maximilianshwarzmullers/hukukchy", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)


#### Training Hyperparameters

from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported

trainer = SFTTrainer(
    model = model,
    tokenizer = tokenizer,
    train_dataset = dataset,
    dataset_text_field = "text",
    max_seq_length = max_seq_length,
    dataset_num_proc = 2,
    packing = False, # Can make training 5x faster for short sequences.
    args = TrainingArguments(
        per_device_train_batch_size = 2,
        gradient_accumulation_steps = 4,
        warmup_steps = 5,
        # num_train_epochs = 1, # Set this for 1 full training run.
        max_steps = 750,
        learning_rate = 3e-5,
        fp16 = not is_bfloat16_supported(),
        bf16 = is_bfloat16_supported(),
        logging_steps = 1,
        optim = "adamw_8bit",
        weight_decay = 0.01,
        lr_scheduler_type = "linear",
        seed = 3407,
        output_dir = "outputs",
        report_to = "none", # Use this for WandB etc
    ),
)