Instructions to use falche/opennovel_oc2_01a_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use falche/opennovel_oc2_01a_7b with Transformers:

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

pipe = pipeline("text-generation", model="falche/opennovel_oc2_01a_7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("falche/opennovel_oc2_01a_7b")
model = AutoModelForCausalLM.from_pretrained("falche/opennovel_oc2_01a_7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use falche/opennovel_oc2_01a_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "falche/opennovel_oc2_01a_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "falche/opennovel_oc2_01a_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/falche/opennovel_oc2_01a_7b

SGLang

How to use falche/opennovel_oc2_01a_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 "falche/opennovel_oc2_01a_7b" \
    --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": "falche/opennovel_oc2_01a_7b",
		"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 "falche/opennovel_oc2_01a_7b" \
        --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": "falche/opennovel_oc2_01a_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use falche/opennovel_oc2_01a_7b with Docker Model Runner:
```
docker model run hf.co/falche/opennovel_oc2_01a_7b
```

Model description

Cyberagent様のcyberagent/calm2-7b-chatを追加学習した、作家さん用アシスタントAIのアルファ版です。文章を入れると、続きを書いてくれます。まだまだトレーニングの途中ですけど、概念実証のためHFにアップロードしました。これからどんどんクオリティーを向上させていく予定です。 (もし興味のある方がいれば、safetensors形式のものも作りますので、Communityタブでご連絡ください。)

Intended uses & limitations

まだアルファ版ですけど、こちらの実験では十分アシスタントの役割を果たすことができることがわかりましたので、興味がある人はぜひお試しください。 TextGen-WebUIで使えます。プロンプトは以下をお使いください。

あなたは誠実で優秀な日本人の書き手です。USERが書いた文章の続きを書いてください。
USER: (続きを書いてほしい文章)
ASSISTANT:

一例を添付します。

opennovel-alpha-screenshot

Training and evaluation data

約150Mトークンの小説テキストをShareGPT形式に変換して、追加学習しました。

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 3
gradient_accumulation_steps: 2
total_train_batch_size: 6
total_eval_batch_size: 3
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1

Framework versions

Transformers 4.34.1
Pytorch 2.0.1+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Downloads last month: 8

Model tree for falche/opennovel_oc2_01a_7b

Base model

cyberagent/calm2-7b-chat

Finetuned

(4)

this model

Merges

1 model