Instructions to use cyberagent/calm3-22b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyberagent/calm3-22b-chat with Transformers:

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

pipe = pipeline("text-generation", model="cyberagent/calm3-22b-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cyberagent/calm3-22b-chat")
model = AutoModelForCausalLM.from_pretrained("cyberagent/calm3-22b-chat")
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 cyberagent/calm3-22b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyberagent/calm3-22b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyberagent/calm3-22b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cyberagent/calm3-22b-chat

SGLang

How to use cyberagent/calm3-22b-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/calm3-22b-chat" \
    --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": "cyberagent/calm3-22b-chat",
		"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 "cyberagent/calm3-22b-chat" \
        --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": "cyberagent/calm3-22b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cyberagent/calm3-22b-chat with Docker Model Runner:
```
docker model run hf.co/cyberagent/calm3-22b-chat
```

CyberAgentLM3-22B-Chat (CALM3-22B-Chat)

Model Description

CyberAgentLM3 is a decoder-only language model pre-trained on 2.0 trillion tokens from scratch.
CyberAgentLM3-Chat is a fine-tuned model specialized for dialogue use cases.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model = AutoModelForCausalLM.from_pretrained("cyberagent/calm3-22b-chat", device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("cyberagent/calm3-22b-chat")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

messages = [
    {"role": "system", "content": "あなたは親切なAIアシスタントです。"},
    {"role": "user", "content": "AIによって私たちの暮らしはどのように変わりますか？"}
]

input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
output_ids = model.generate(input_ids,
                            max_new_tokens=1024,
                            temperature=0.5,
                            streamer=streamer)

Prompt Format

CALM3-Chat uses ChatML as the prompt format.

<|im_start|>system
あなたは親切なAIアシスタントです。<|im_end|>
<|im_start|>user
AIによって私たちの暮らしはどのように変わりますか？<|im_end|>
<|im_start|>assistant

Model Details

Model size: 22B
Context length: 16384
Model type: Transformer-based Language Model
Language(s): Japanese, English
Developed by: CyberAgent, Inc.
License: Apache-2.0

Author

Ryosuke Ishigami

How to cite

@misc{cyberagent-calm3-22b-chat,
      title={cyberagent/calm3-22b-chat},
      url={https://huggingface.co/cyberagent/calm3-22b-chat},
      author={Ryosuke Ishigami},
      year={2024},
}

Downloads last month: 431

Safetensors

Model size

23B params

Tensor type

BF16

Model tree for cyberagent/calm3-22b-chat

Finetunes

4 models

Merges

1 model

cyberagent
/

calm3-22b-chat