Text Generation
Transformers
PyTorch
Safetensors
Japanese
English
llama
japanese
causal-lm
text-generation-inference
Instructions to use cyberagent/calm2-7b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cyberagent/calm2-7b-chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cyberagent/calm2-7b-chat")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cyberagent/calm2-7b-chat") model = AutoModelForCausalLM.from_pretrained("cyberagent/calm2-7b-chat") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use cyberagent/calm2-7b-chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cyberagent/calm2-7b-chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cyberagent/calm2-7b-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/cyberagent/calm2-7b-chat
- SGLang
How to use cyberagent/calm2-7b-chat 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 "cyberagent/calm2-7b-chat" \ --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": "cyberagent/calm2-7b-chat", "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 "cyberagent/calm2-7b-chat" \ --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": "cyberagent/calm2-7b-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use cyberagent/calm2-7b-chat with Docker Model Runner:
docker model run hf.co/cyberagent/calm2-7b-chat
text-generation-webuiを使う時はuse_fastがONにすること
#1
by alfredplpl - opened
いろんな人から報告があったので.READMEに明記した方がいいと思いました。
transformersのモデルに表示されている、fastのチェックボックスにチェックを入れたら無事にロードできたようです。
tokenizer_config.jsonで「tokenizer_class」:「GPTNeoXTokenizer」を「tokenizer_class」:「GPTNeoXTokenizerFast」に変更することでも解決できるそうです
It appears that this issue has been resolved with https://huggingface.co/cyberagent/calm2-7b-chat/discussions/2.
rishigami changed discussion status to closed