Instructions to use realPCH/ko-solra-platusv3-koprompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use realPCH/ko-solra-platusv3-koprompt with Transformers:

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

pipe = pipeline("text-generation", model="realPCH/ko-solra-platusv3-koprompt")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("realPCH/ko-solra-platusv3-koprompt")
model = AutoModelForCausalLM.from_pretrained("realPCH/ko-solra-platusv3-koprompt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use realPCH/ko-solra-platusv3-koprompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "realPCH/ko-solra-platusv3-koprompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "realPCH/ko-solra-platusv3-koprompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/realPCH/ko-solra-platusv3-koprompt

SGLang

How to use realPCH/ko-solra-platusv3-koprompt 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 "realPCH/ko-solra-platusv3-koprompt" \
    --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": "realPCH/ko-solra-platusv3-koprompt",
		"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 "realPCH/ko-solra-platusv3-koprompt" \
        --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": "realPCH/ko-solra-platusv3-koprompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use realPCH/ko-solra-platusv3-koprompt with Docker Model Runner:
```
docker model run hf.co/realPCH/ko-solra-platusv3-koprompt
```

Developed by chPark

Training Strategy

We fine-tuned this model based on yanolja/KoSOLAR-10.7B-v0.1

Run the model

from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "realPCH/ko_solra_merge"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "[INST] Put instruction here. [/INST]"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 17

Safetensors

Model size

11B params

Tensor type

F16

realPCH
/

ko-solra-platusv3-koprompt

Developed by chPark

Training Strategy

Run the model

Dataset used to train realPCH/ko-solra-platusv3-koprompt