Instructions to use Markr-AI/pub-llama-13B-v6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Markr-AI/pub-llama-13B-v6 with Transformers:

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

pipe = pipeline("text-generation", model="Markr-AI/pub-llama-13B-v6")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Markr-AI/pub-llama-13B-v6")
model = AutoModelForCausalLM.from_pretrained("Markr-AI/pub-llama-13B-v6")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Markr-AI/pub-llama-13B-v6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Markr-AI/pub-llama-13B-v6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Markr-AI/pub-llama-13B-v6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Markr-AI/pub-llama-13B-v6

SGLang

How to use Markr-AI/pub-llama-13B-v6 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 "Markr-AI/pub-llama-13B-v6" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Markr-AI/pub-llama-13B-v6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Markr-AI/pub-llama-13B-v6" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Markr-AI/pub-llama-13B-v6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Markr-AI/pub-llama-13B-v6 with Docker Model Runner:
```
docker model run hf.co/Markr-AI/pub-llama-13B-v6
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다
The license is cc-by-nc-sa.

Model Details

Model Developers SeungyooLee (DopeorNope)

Input Models input text only.

Output Models generate text only.

Model Architecture
pub-llama-13b-v6 is an auto-regressive language model based on the LLaMA2 transformer architecture.

Base Model : beomi/llama-2-koen-13b

Training Dataset
DopeorNope/OpenOrca-near-dedup-v1 dataset was created by Near dedup algorithm to reduce similarity. We will open it soon.

Downloads last month: 5

Safetensors

Model size

13B params

Tensor type

F32

Model tree for Markr-AI/pub-llama-13B-v6

Quantizations

3 models

Space using Markr-AI/pub-llama-13B-v6 1

Paper for Markr-AI/pub-llama-13B-v6

Deduplicating Training Data Makes Language Models Better

Paper • 2107.06499 • Published Jul 14, 2021 • 4