Instructions to use alfredplpl/gemma-2b-it-ja-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alfredplpl/gemma-2b-it-ja-poc with Transformers:

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

pipe = pipeline("text-generation", model="alfredplpl/gemma-2b-it-ja-poc")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alfredplpl/gemma-2b-it-ja-poc")
model = AutoModelForCausalLM.from_pretrained("alfredplpl/gemma-2b-it-ja-poc")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use alfredplpl/gemma-2b-it-ja-poc with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alfredplpl/gemma-2b-it-ja-poc"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alfredplpl/gemma-2b-it-ja-poc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alfredplpl/gemma-2b-it-ja-poc

SGLang

How to use alfredplpl/gemma-2b-it-ja-poc 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 "alfredplpl/gemma-2b-it-ja-poc" \
    --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": "alfredplpl/gemma-2b-it-ja-poc",
		"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 "alfredplpl/gemma-2b-it-ja-poc" \
        --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": "alfredplpl/gemma-2b-it-ja-poc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alfredplpl/gemma-2b-it-ja-poc with Docker Model Runner:
```
docker model run hf.co/alfredplpl/gemma-2b-it-ja-poc
```

Note

このモデルはマージに失敗してバグっているため、こちらをおすすめします。

Google Colab

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# トークナイザーとモデルの準備
tokenizer = AutoTokenizer.from_pretrained(
  "alfredplpl/gemma-2b-it-ja-poc"
)
model = AutoModelForCausalLM.from_pretrained(
  "alfredplpl/gemma-2b-it-ja-poc"
)

# プロンプトの準備
prompt="""
あなたは親切なアシスタントです。英語は喋らず、日本語だけ喋ってください。
<start_of_turn>user
人生で大切なことはなんですか？<end_of_turn>
<start_of_turn>model"""

# 推論の実行
input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **input_ids,
    max_new_tokens=128,
    do_sample=True,
    top_p=0.95,
    temperature=0.2,
    repetition_penalty=1.1,
)
print(tokenizer.decode(outputs[0]))

Result

<bos>
あなたは親切なアシスタントです。英語は喋らず、日本語だけ喋ってください。
<start_of_turn>user
人生で大切なことはなんですか？<end_of_turn>
<start_of_turn>model
人生で大切なことはたくさんある。しかし、最も重要なのは、愛する人を大切にし、その人と幸せになることだ。<end_of_turn>
<eos>

Chat Templete

<bos>
{{system prompt}}
<start_of_turn>user
{{prompt}}<end_of_turn>
<start_of_turn>model
{{response}}<end_of_turn>
<eos>

Base model

free-ai-ltd/ja-aozora-wikipedia-gemmba-2b (private)

Dataset for Instruct tuning

llm-jp/databricks-dolly-15k-ja
llm-jp/oasst1-21k-ja
kunishou/oasst1-chat-44k-ja
kunishou/oasst2-chat-68k-ja
kunishou/cnn-dailymail-27k-ja
kunishou/databricks-dolly-69k-ja-en-translation
kunishou/databricks-dolly-15k-ja

How to make this model

LoRA

Downloads last month: 9

Safetensors

Model size

3B params

Tensor type

BF16