Instructions to use yellowback/gpt-neo-japanese-1.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yellowback/gpt-neo-japanese-1.3B with Transformers:

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

pipe = pipeline("text-generation", model="yellowback/gpt-neo-japanese-1.3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yellowback/gpt-neo-japanese-1.3B")
model = AutoModelForCausalLM.from_pretrained("yellowback/gpt-neo-japanese-1.3B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yellowback/gpt-neo-japanese-1.3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yellowback/gpt-neo-japanese-1.3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yellowback/gpt-neo-japanese-1.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yellowback/gpt-neo-japanese-1.3B

SGLang

How to use yellowback/gpt-neo-japanese-1.3B 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 "yellowback/gpt-neo-japanese-1.3B" \
    --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": "yellowback/gpt-neo-japanese-1.3B",
		"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 "yellowback/gpt-neo-japanese-1.3B" \
        --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": "yellowback/gpt-neo-japanese-1.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yellowback/gpt-neo-japanese-1.3B with Docker Model Runner:
```
docker model run hf.co/yellowback/gpt-neo-japanese-1.3B
```

GPT-Neo 1.3B pre-trained model for Japanese

Model Description

GPT2/GPT3 like model trained on Japanese.corpus.

Training data

cc100 ja
oscar ja
wikipedia ja

How to use

from transformers import pipeline
>>> generator = pipeline('text-generation', model='yellowback/gpt-neo-japanese-1.3B')
>>> generator("こんばんは、徳川家康です。", do_sample=True, max_length=50, num_return_sequences=3)

[{'generated_text': 'こんばんは、徳川家康です。 世の中を見渡してみても、残念なことだけれども、まぎれもなく「世のなか...\n5月になりました、家康です。 ゴールデンウィークも終ってしまい、世間では'},
 {'generated_text': 'こんばんは、徳川家康です。さあ今日は昨晩から降り続いた雨は上がりましたが、まだまだ雨脚は強いですが、晴れるところは晴れて欲しいですね。昨日の夜は仕事だったので、今日の夕'},
 {'generated_text': 'こんばんは、徳川家康です。 今回は、『世界史再考──日本史再考』という本を書いたあと、『世界史再考──日本史再考』の6~8章'}]

Downloads last month: 11

Model tree for yellowback/gpt-neo-japanese-1.3B

Finetunes

1 model

yellowback
/

gpt-neo-japanese-1.3B

GPT-Neo 1.3B pre-trained model for Japanese

Model Description

Training data

How to use

Model tree for yellowback/gpt-neo-japanese-1.3B

Datasets used to train yellowback/gpt-neo-japanese-1.3B

Space using yellowback/gpt-neo-japanese-1.3B 1