git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'ELYZA-japanese-CodeLlama-7b-instruct-q4_0.gguf' -n 256 -p '[INST] <<SYS>>あなたは誠実で優秀な日本人のアシスタントです。<</SYS>>エラトステネスの篩についてサンプルコードを示し、解説してください。 [/INST]'

ggufへの変換

llama.cppのconvert.pyで変換するとエラーになってしまうので、下記の方法で変換できます。

tokenizer.model を持ってきてモデルディレクトリに配置してください。
added_tokens.jsonに下記内容で保存してモデルディレクトリに配置してください。

javascript

{
    "<SU": 32000,
    "<SUF": 32001,
    "<PRE": 32002,
    "<M": 32003,
    "<MID": 32004,
    "<E": 32005,
    "<EOT": 32006,
    "<PRE>": 32007,
    "<SUF>": 32008,
    "<MID>": 32009,
    "<EOT>": 32010,
    "<EOT><EOT>": 32011,
    "<EOT><EOT><EOT>": 32012,
    "<EOT><EOT><EOT><EOT>": 32013,
    "<EOT><EOT><EOT><EOT><EOT>": 32014,
    "<EOT><EOT><EOT><EOT><EOT><EOT>": 32015
}

convert.py "<path_to_model>" --outtype f16

で変換できます。

Licence

引用 Citations

tex

@misc{elyzacodellama2023, 
      title={ELYZA-japanese-CodeLlama-7b}, 
      url={https://huggingface.co/elyza/ELYZA-japanese-CodeLlama-7b}, 
      author={Akira Sasaki and Masato Hirakawa and Shintaro Horie and Tomoaki Nakamura},
      year={2023},
}

@misc{rozière2023code,
      title={Code Llama: Open Foundation Models for Code}, 
      author={Baptiste Rozière and Jonas Gehring and Fabian Gloeckle and Sten Sootla and Itai Gat and Xiaoqing Ellen Tan and Yossi Adi and Jingyu Liu and Tal Remez and Jérémy Rapin and Artyom Kozhevnikov and Ivan Evtimov and Joanna Bitton and Manish Bhatt and Cristian Canton Ferrer and Aaron Grattafiori and Wenhan Xiong and Alexandre Défossez and Jade Copet and Faisal Azhar and Hugo Touvron and Louis Martin and Nicolas Usunier and Thomas Scialom and Gabriel Synnaeve},
      year={2023},
      eprint={2308.12950},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{touvron2023llama,
      title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, 
      author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
      year={2023},
      eprint={2307.09288},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}