Instructions to use PracticeLLM/KoSOLAR-Platypus-10.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticeLLM/KoSOLAR-Platypus-10.7B with Transformers:

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

pipe = pipeline("text-generation", model="PracticeLLM/KoSOLAR-Platypus-10.7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PracticeLLM/KoSOLAR-Platypus-10.7B")
model = AutoModelForCausalLM.from_pretrained("PracticeLLM/KoSOLAR-Platypus-10.7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PracticeLLM/KoSOLAR-Platypus-10.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PracticeLLM/KoSOLAR-Platypus-10.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PracticeLLM/KoSOLAR-Platypus-10.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PracticeLLM/KoSOLAR-Platypus-10.7B

SGLang

How to use PracticeLLM/KoSOLAR-Platypus-10.7B 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 "PracticeLLM/KoSOLAR-Platypus-10.7B" \
    --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": "PracticeLLM/KoSOLAR-Platypus-10.7B",
		"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 "PracticeLLM/KoSOLAR-Platypus-10.7B" \
        --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": "PracticeLLM/KoSOLAR-Platypus-10.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PracticeLLM/KoSOLAR-Platypus-10.7B with Docker Model Runner:
```
docker model run hf.co/PracticeLLM/KoSOLAR-Platypus-10.7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

PracticeLLM/KoSOLAR-Platypus-10.7B

Model Details

Model Developers Kyujin Han (kyujinpy)

Method
LoRA with quantization.

Base Model
yanolja/KoSOLAR-10.7B-v0.2

Dataset
kyujinpy/KOR-OpenOrca-Platypus-v3.

Hyperparameters

python finetune.py \
    --base_model yanolja/KoSOLAR-10.7B-v0.2 \
    --data-path  kyujinpy/KOR-OpenOrca-Platypus-v3 \
    --output_dir ./Ko-PlatypusSOLAR-10.7B \
    --batch_size 64 \
    --micro_batch_size 1 \
    --num_epochs 5 \
    --learning_rate 2e-5 \
    --cutoff_len 2048 \
    --val_set_size 0 \
    --lora_r 64 \
    --lora_alpha 64 \
    --lora_dropout 0.05 \
    --lora_target_modules '[embed_tokens, q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj, lm_head]' \
    --train_on_inputs False \
    --add_eos_token False \
    --group_by_length False \
    --prompt_template_name en_simple \
    --lr_scheduler 'cosine' \

Share all of things. It is my belief.

Model Benchmark

Open Ko-LLM leaderboard & lm-evaluation-harness(zero-shot)

Follow up as Ko-link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Ko-CommonGenV2
PracticeLLM/KoSOLAR-Platypus-10.7B	---	---	---	---	---	---
LDCC/LDCC-SOLAR-10.7B	59.34	55.38	65.56	53.38	64.39	57.97
yanolja/KoSOLAR-10.7B-v0.2	55.62	50.51	62.29	53.76	47.31	64.23
megastudyedu/M-SOLAR-10.7B-v1.3	56.64	51.37	60.93	54.91	48.45	67.53

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "PracticeLLM/KoSOLAR-Platypus-10.7B"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Downloads last month: 5

Safetensors

Model size

11B params

Tensor type

F16

Model tree for PracticeLLM/KoSOLAR-Platypus-10.7B

Quantizations

1 model

PracticeLLM
/

KoSOLAR-Platypus-10.7B