Instructions to use Deepreneur/blue-lizard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Deepreneur/blue-lizard with Transformers:

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

pipe = pipeline("text-generation", model="Deepreneur/blue-lizard")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Deepreneur/blue-lizard")
model = AutoModelForCausalLM.from_pretrained("Deepreneur/blue-lizard")
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 Deepreneur/blue-lizard with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Deepreneur/blue-lizard

SGLang

How to use Deepreneur/blue-lizard 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 "Deepreneur/blue-lizard" \
    --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": "Deepreneur/blue-lizard",
		"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 "Deepreneur/blue-lizard" \
        --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": "Deepreneur/blue-lizard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Deepreneur/blue-lizard with Docker Model Runner:
```
docker model run hf.co/Deepreneur/blue-lizard
```

Deepreneur-blue-lizard

Model Description

Deepreneur-blue-lizardは、MetaのLlama-2-7bに対して、Wikipediaや書籍等の日本語の学習データを用いて追加事前学習と独自データによるファインチューニングを実施したモデルです。
70億パラメータと非常に軽量なモデルであるにも関わらず、JGLUE（日本語タスクにおける評価ベンチマーク）を用いた評価では、ChatGPT-3.5を超えるスコアが算出されており、公開されている日本語モデルの中では最高性能になります。
※ 学習データにはJGLUEのデータは使用しておりません。また、ChatGPT等の出力は学習データに使用しておりません。

How to use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
DEFAULT_SYSTEM_PROMPT = "あなたは誠実で優秀な日本人のアシスタントです。"
text = "deepreneurについて教えて"

model_name = "Deepreneur/blue-lizard"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
)

if torch.cuda.is_available():
    model = model.to("cuda")

prompt = "{bos_token}{b_inst} {system}{prompt} {e_inst}".format(
  bos_token=tokenizer.bos_token,
  b_inst=B_INST,
  system=f"{B_SYS}{DEFAULT_SYSTEM_PROMPT}{E_SYS}",
  prompt=text,
  e_inst=E_INST,
)


with torch.no_grad():
    token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
    output_ids = model.generate(
        token_ids.to(model.device),
        max_new_tokens=256,
        pad_token_id=tokenizer.pad_token_id,
        eos_token_id=tokenizer.eos_token_id,
    )
output = tokenizer.decode(output_ids.tolist()[0][token_ids.size(1) :], skip_special_tokens=True)
print(output)

"""
株式会社Deepreneurは、言語系の生成AIに強みを持ったAIスタートアップです。
東京大学松尾研究室発AIスタートアップに認定されており、大規模言語モデル(Large Language Model)の開発をはじめとする基礎研究や、企業との共同研究を通じてDXを推進します。
Deepreneurのホームページ: https://www.deepreneur.com/
Deepreneurのメールアドレス: info@deepreneur.com
"""

Developers

以下アルファベット順

Ikuto Watanabe
Sunwoo Park
Taiki Kaneki
Yuki Hirota
Yuki Koshiba
Yusuke Kanzaki
Yuta Sawada

Licence

Downloads last month: 15

Safetensors

Model size

7B params

Tensor type

BF16