Edit model card

aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf

aixsatoshiさんが公開しているLlama-3-8b-Cosmopedia-japanese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。

他のモデル

mmnga/aixsatoshi-Honyaku-13b-gguf
mmnga/aixsatoshi-Ex-karakuri-8x12B-chat-v1-gguf
mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf
mmnga/aixsatoshi-Honyaku-7b-v2-gguf
mmnga/aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-gguf
mmnga/aixsatoshi-Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-v2-gguf
mmnga/aixsatoshi-Mixtral-8x7B-ja-sft-ChatbotArenaJAcalm2-bnb4bit
mmnga/aixsatoshi-calm2-7b-chat-7b-moe-gguf

Usage

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'aixsatoshi-Llama-3-8b-Cosmopedia-japanese-q4_0.gguf' -n 128 -p "<|begin_of_text|><|start_header_id|>user <|end_header_id|>\n\nこんにちわ<|eot_id|><|start_header_id|>assistant <|end_header_id|>\n\n"
Downloads last month
2,299
GGUF
Model size
8.03B params
Architecture
llama

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf