Instructions to use maywell/koOpenChat-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maywell/koOpenChat-sft with Transformers:

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

pipe = pipeline("text-generation", model="maywell/koOpenChat-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maywell/koOpenChat-sft")
model = AutoModelForCausalLM.from_pretrained("maywell/koOpenChat-sft")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maywell/koOpenChat-sft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/maywell/koOpenChat-sft

SGLang

How to use maywell/koOpenChat-sft 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 "maywell/koOpenChat-sft" \
    --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": "maywell/koOpenChat-sft",
		"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 "maywell/koOpenChat-sft" \
        --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": "maywell/koOpenChat-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use maywell/koOpenChat-sft with Docker Model Runner:
```
docker model run hf.co/maywell/koOpenChat-sft
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

koOpenChat-sft🐧

Support Me

시나트라는 개인 프로젝트로, 1인의 자원으로 개발되고 있습니다. 모델이 마음에 드셨다면 약간의 연구비 지원은 어떨까요?

Wanna be a sponser? (Please) Contact me on Telegram AlzarTakkarsen

Model Details

Base Model
OpenChat3.5

Trained On
A100 80GB * 1

Instruction format

It follows ChatML format and Alpaca(No-Input) format.

Model Benchmark

None

Implementation Code

Since, chat_template already contains insturction format above. You can use the code below.

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("maywell/koOpenChat-sft")
tokenizer = AutoTokenizer.from_pretrained("maywell/koOpenChat-sft")

messages = [
    {"role": "user", "content": "바나나는 원래 하얀색이야?"},
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	51.36
ARC (25-shot)	59.81
HellaSwag (10-shot)	78.73
MMLU (5-shot)	61.32
TruthfulQA (0-shot)	51.24
Winogrande (5-shot)	76.4
GSM8K (5-shot)	24.18
DROP (3-shot)	7.82

Downloads last month: 819

Model tree for maywell/koOpenChat-sft

Quantizations

3 models

maywell
/

koOpenChat-sft