Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,26 @@
|
|
1 |
---
|
2 |
license: llama3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: llama3
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- ja
|
6 |
+
tags:
|
7 |
+
- llama3
|
8 |
+
datasets:
|
9 |
+
- TFMC/imatrix-dataset-for-japanese-llm
|
10 |
---
|
11 |
+
# haqishen-Llama-3-8B-Japanese-Instruct-gguf
|
12 |
+
[haqishenさんが公開しているLlama-3-8B-Japanese-Instruct](https://huggingface.co/haqishen/Llama-3-8B-Japanese-Instruct)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 |
+
## 他のモデル
|
17 |
+
[mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf](https://huggingface.co/mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf)
|
18 |
+
|
19 |
+
## Usage
|
20 |
+
|
21 |
+
```
|
22 |
+
git clone https://github.com/ggerganov/llama.cpp.git
|
23 |
+
cd llama.cpp
|
24 |
+
make -j
|
25 |
+
./main -m 'haqishen-Llama-3-8B-Japanese-Instruct-Q4_0.gguf' -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" -n 128
|
26 |
+
```
|