Instructions to use tokyotech-llm/Swallow-7b-instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tokyotech-llm/Swallow-7b-instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="tokyotech-llm/Swallow-7b-instruct-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tokyotech-llm/Swallow-7b-instruct-hf")
model = AutoModelForCausalLM.from_pretrained("tokyotech-llm/Swallow-7b-instruct-hf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tokyotech-llm/Swallow-7b-instruct-hf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tokyotech-llm/Swallow-7b-instruct-hf

SGLang

How to use tokyotech-llm/Swallow-7b-instruct-hf 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 "tokyotech-llm/Swallow-7b-instruct-hf" \
    --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": "tokyotech-llm/Swallow-7b-instruct-hf",
		"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 "tokyotech-llm/Swallow-7b-instruct-hf" \
        --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": "tokyotech-llm/Swallow-7b-instruct-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tokyotech-llm/Swallow-7b-instruct-hf with Docker Model Runner:
```
docker model run hf.co/tokyotech-llm/Swallow-7b-instruct-hf
```

tokenizer.chat_template

by leonardlin - opened Dec 21, 2023

Discussion

leonardlin

Dec 21, 2023

If anyone wants to use HF's new chat templates here's the formatting exactly matching the output docs:

tokenizer.chat_template = "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% elif message['role'] == 'user' %}{{'### 指示:\n' + message['content'] + '\n\n'}}{% elif message['role'] == 'assistant' %}{{'### 応答:\n' + message['content'] + '\n\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### 応答:' }}{% endif %}"

The roles are system, user, and assistant, and you could start with the suggested prompt:

PROMPT = "以下に、あるタスクを説明する指示があります。リクエストを適切に完了するための回答を記述してください。"
chat = []
chat.append({"role": "system", "content": PROMPT})

leonardlin

Dec 21, 2023

For those looking for MT-Bench formatting, I also made a version that's close (not sure if the ADD_COLON_SINGLE adds the appropriate \n or not): https://github.com/AUGMXNT/shisa/wiki/Evals-:-JA-MT%E2%80%90Bench#swallow

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment