Instructions to use VeriUs/VeriUS-LLM-8b-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VeriUs/VeriUS-LLM-8b-v0.2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="VeriUs/VeriUS-LLM-8b-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VeriUs/VeriUS-LLM-8b-v0.2")
model = AutoModelForCausalLM.from_pretrained("VeriUs/VeriUS-LLM-8b-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use VeriUs/VeriUS-LLM-8b-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VeriUs/VeriUS-LLM-8b-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VeriUs/VeriUS-LLM-8b-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VeriUs/VeriUS-LLM-8b-v0.2

SGLang

How to use VeriUs/VeriUS-LLM-8b-v0.2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "VeriUs/VeriUS-LLM-8b-v0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VeriUs/VeriUS-LLM-8b-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "VeriUs/VeriUS-LLM-8b-v0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VeriUs/VeriUS-LLM-8b-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VeriUs/VeriUS-LLM-8b-v0.2 with Docker Model Runner:
```
docker model run hf.co/VeriUs/VeriUS-LLM-8b-v0.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

VeriUS LLM 8b v0.2

VeriUS LLM is a instruct following large language model supporting Turkish language based on llama3-8B.

Model Details

Base Model: unsloth/llama-3-8b-bnb-4bit

Training Dataset: A carefully curated general domain Turkish instruction dataset.

Training Method: Fine-tuned using QLoRA and ORPO

#TrainingArguments
PER_DEVICE_BATCH_SIZE: 2
GRADIENT_ACCUMULATION_STEPS: 4
WARMUP_RATIO: 0.03
NUM_EPOCHS: 2
LR: 0.000008
OPTIM: "adamw_8bit"
WEIGHT_DECAY: 0.01
LR_SCHEDULER_TYPE: "linear"
BETA: 0.1

#PEFT Arguments
RANK: 128
TARGET_MODULES:

"q_proj"
"k_proj"
"v_proj"
"o_proj"
"gate_proj"
"up_proj"
"down_proj"

LORA_ALPHA: 256
LORA_DROPOUT: 0
BIAS: "none"
GRADIENT_CHECKPOINT: 'unsloth'
USE_RSLORA: false\

Usage

This model is trained used Unsloth and uses it for fast inference. For Unsloth installation please refer to: https://github.com/unslothai/unsloth

This model can also be loaded with AutoModelForCausalLM

How to load with unsloth:

from unsloth import FastLanguageModel

max_seq_len = 1024
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="VeriUs/VeriUS-LLM-8b-v0.2",
    max_seq_length=max_seq_len,
    dtype=None
)
FastLanguageModel.for_inference(model)  # Enable native 2x faster inference

prompt_tempate = """Aşağıda, görevini açıklayan bir talimat ve daha fazla bağlam sağlayan bir girdi verilmiştir. İsteği uygun bir şekilde tamamlayan bir yanıt yaz.

### Talimat:
{}

### Girdi:
{}

### Yanıt:
"""


def generate_output(instruction, user_input):
    input_ids = tokenizer(
        [
            prompt_tempate.format(instruction, user_input)
        ], return_tensors="pt").to("cuda")

    outputs = model.generate(**input_ids, max_length=max_seq_len, do_sample=True)

    # removes prompt, comment this out if you want to see it.
    outputs = [output[len(input_ids[i].ids):] for i, output in enumerate(outputs)]

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


response = generate_output("Türkiye'nin en kalabalık şehri hangisidir?", "")
print(response)

Bias, Risks, and Limitations

Limitations and Known Biases Primary Function and Application: VeriUS LLM, an autoregressive language model, is primarily designed to predict the next token in a text string. While often used for various applications, it is important to note that it has not undergone extensive real-world application testing. Its effectiveness and reliability across diverse scenarios remain largely unverified.

Language Comprehension and Generation: The base model is primarily trained in standard English. Even though it fine-tuned with and Turkish dataset, its performance in understanding and generating slang, informal language, or other languages may be limited, leading to potential errors or misinterpretations.

Generation of False Information: Users should be aware that VeriUS LLM may produce inaccurate or misleading information. Outputs should be considered as starting points or suggestions rather than definitive answers.