Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
- ja
|
| 7 |
+
datasets:
|
| 8 |
+
- TFMC/imatrix-dataset-for-japanese-llm
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# aya-23-8B-gguf
|
| 12 |
+
[CohereForAIさんが公開しているaya-23-8B](https://huggingface.co/CohereForAI/aya-23-8B)のggufフォーマット変換版です。
|
| 13 |
+
|
| 14 |
+
imatrixのデータは[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)を使用して作成しました。
|
| 15 |
+
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
```
|
| 19 |
+
git clone https://github.com/ggerganov/llama.cpp.git
|
| 20 |
+
cd llama.cpp
|
| 21 |
+
make -j
|
| 22 |
+
./main -m 'aya-23-8B-Q4_0.gguf' -n 128 -p 'こんにちわ'
|
| 23 |
+
```
|