GGUF
English
Japanese
Edit model card

c4ai-command-r-plus-gguf

CohereForAIさんが公開しているc4ai-command-r-plusのggufフォーマット変換版です。

imatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。

分割されたファイルについて

q6_kやq8_0のファイルはサイズが大きく分割されているので結合する必要があります。

cat c4ai-command-r-plus-Q5_K_M.gguf.* > c4ai-command-r-plus-Q5_K_M.gguf

Usage

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'c4ai-command-r-plus-Q4_0.gguf' -p "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>あなたは日本語を話すCommand-Rです<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>こんにちわ<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" -n 128
Downloads last month
1,542
GGUF
Model size
104B params
Architecture
command-r
+4
Unable to determine this model's library. Check the docs .

Dataset used to train mmnga/c4ai-command-r-plus-gguf