import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

assert transformers.__version__ >= "4.34.1"

model = AutoModelForCausalLM.from_pretrained("cyberagent/calm2-7b", device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("cyberagent/calm2-7b")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

prompt = "AIによって私達の暮らしは、"

token_ids = tokenizer.encode(prompt, return_tensors="pt")
output_ids = model.generate(
    input_ids=token_ids.to(model.device),
    max_new_tokens=100,
    do_sample=True,
    temperature=0.9,
    streamer=streamer,
)

Model Details

Model size: 7B
Trained tokens: 1.3T tokens
Context length: 4096
Model type: Transformer-based Language Model
Language(s): Japanese, English
Developed by: CyberAgent, Inc.
License: Apache-2.0

Author

Ryosuke Ishigami

Citations

tex

@article{touvron2023llama,
  title={LLaMA: Open and Efficient Foundation Language Models},
  author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
  journal={arXiv preprint arXiv:2302.13971},
  year={2023}
}