Instructions to use ganchengguang/Yoko-7B-Japanese-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ganchengguang/Yoko-7B-Japanese-v1 with Transformers:

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

pipe = pipeline("text-generation", model="ganchengguang/Yoko-7B-Japanese-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ganchengguang/Yoko-7B-Japanese-v1")
model = AutoModelForCausalLM.from_pretrained("ganchengguang/Yoko-7B-Japanese-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ganchengguang/Yoko-7B-Japanese-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ganchengguang/Yoko-7B-Japanese-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ganchengguang/Yoko-7B-Japanese-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ganchengguang/Yoko-7B-Japanese-v1

SGLang

How to use ganchengguang/Yoko-7B-Japanese-v1 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 "ganchengguang/Yoko-7B-Japanese-v1" \
    --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": "ganchengguang/Yoko-7B-Japanese-v1",
		"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 "ganchengguang/Yoko-7B-Japanese-v1" \
        --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": "ganchengguang/Yoko-7B-Japanese-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ganchengguang/Yoko-7B-Japanese-v1 with Docker Model Runner:
```
docker model run hf.co/ganchengguang/Yoko-7B-Japanese-v1
```

This model is traned with guanaco dataset. And this model used whole guanaco dataset by 49000 chat samples and 280000 non chat samples.
Improved performance in Chinese and Japanese.
Use the QLoRA to fine-tune the vanilla LLaMA2-7B.
And you can use test.py to test the model.

Recommend Generation parameters:

temperature: 0.5~0.7
top p: 0.65~1.0
top k: 30~50
repeat penalty: 1.03~1.17

Contribute by Yokohama Nationaly University Mori Lab.

Downloads last month: 10