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

Libraries

How to use lightblue/karasu-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-7B")
model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-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 lightblue/karasu-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lightblue/karasu-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": "lightblue/karasu-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lightblue/karasu-7B

SGLang

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

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

drawing

Evaluation

How to use

Hugggingface

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-7B")
model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-7B", torch_dtype=torch.bfloat16, device_map="auto")

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})

prompt = tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)

pipe(prompt, max_new_tokens=100, do_sample=False, temperature=0.0, return_full_text=False)

VLLM

from vllm import LLM, SamplingParams

sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
llm = LLM(model="lightblue/karasu-7B")

messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
prompt = llm.llm_engine.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
prompts = [prompt]

outputs = llm.generate(prompts, sampling_params)
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

Base checkpoint

augmxnt/shisa-7b-v1

Mistral-7B base
Pre-trained on 8B of MADLAD-Ja
Finetuned on Japanese instructions
Highest scoring 7B model on conversation benchmark (JA MT-Bench)

Training datasets (total ~7B)

Aozora Bunko
Japanese Law Precedent Dataset
Japanese Wikipedia
.lg.jp, .go.jp, .ac.jp domain webscrapes from CulturaX (Any documents with same first 25 characters were de-duplicated)
English Ultrachat200K-gen (So that it doesn't forget English and chatting ability learned in the base checkpoint)

Developed by

Engineers

Peter Devine

Sho Higuchi

Advisors

Yuuki Yamanaka

Atom Sonoda

Project manager

Shunichi Taniguchi

Dataset evaluator

Renju Aoki

Downloads last month: 62

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for lightblue/karasu-7B

Quantizations

1 model

Datasets used to train lightblue/karasu-7B

Collection including lightblue/karasu-7B

Karasu

Collection

The models trained under our Karasu and Qarasu project • 9 items • Updated Oct 10, 2024 • 1