Instructions to use maywell/Synatra-kiqu-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maywell/Synatra-kiqu-7B with Transformers:

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

pipe = pipeline("text-generation", model="maywell/Synatra-kiqu-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-kiqu-7B")
model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-kiqu-7B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maywell/Synatra-kiqu-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maywell/Synatra-kiqu-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maywell/Synatra-kiqu-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maywell/Synatra-kiqu-7B

SGLang

How to use maywell/Synatra-kiqu-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 "maywell/Synatra-kiqu-7B" \
    --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": "maywell/Synatra-kiqu-7B",
		"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 "maywell/Synatra-kiqu-7B" \
        --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": "maywell/Synatra-kiqu-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maywell/Synatra-kiqu-7B with Docker Model Runner:
```
docker model run hf.co/maywell/Synatra-kiqu-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Join our discord

Server Link

License

cc-by-sa-4.0

Model Details

Base Model
maywell/Synatra-7B-v0.3-dpo

Trained On
A100 80GB * 8

Sionic AI에서 GPU 자원을 지원받아 제작되었습니다.

Instruction format

It follows ChatML format.

Model Benchmark

TBD

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/Synatra-kiqu-7B")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-kiqu-7B")

messages = [
    {"role": "user", "content": "사회적 합의는 어떤 맥락에서 사용되는 말이야?"},
]

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])

Downloads last month: 14

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for maywell/Synatra-kiqu-7B

Quantizations

1 model