Update README.md
Browse files
README.md
CHANGED
@@ -4,11 +4,6 @@ license: apache-2.0
|
|
4 |
|
5 |
# llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-gguf
|
6 |
[llm-jpさんが公開しているllm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0](https://huggingface.co/llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0)のggufフォーマット変換版です。
|
7 |
-
|
8 |
-
注意:こちらはブランチで試用になります。llama.cpp本家にgpt2が実装された時に、このggufファイルが使用できない可能性があります。
|
9 |
-
|
10 |
-
***[GitHubリポジトリの readme はこちら](https://github.com/mmnga/llama.cpp/tree/mmnga-dev-merge)***
|
11 |
-
|
12 |
|
13 |
モデル一覧
|
14 |
[mmnga/llm-jp-13b-v1.0-4bit-g128-GPTQ-calib-ja-1k](https://huggingface.co/mmnga/llm-jp-13b-v1.0-4bit-g128-GPTQ-calib-ja-1k)
|
@@ -16,6 +11,7 @@ license: apache-2.0
|
|
16 |
[mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-GPTQ-calib-ja-1k](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-GPTQ-calib-ja-1k)
|
17 |
|
18 |
GGUF版
|
|
|
19 |
[mmnga/llm-jp-13b-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-v1.0-gguf)
|
20 |
[mmnga/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-gguf)
|
21 |
[mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-gguf)
|
@@ -23,12 +19,12 @@ GGUF版
|
|
23 |
[mmnga/llm-jp-1.3b-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-1.3b-v1.0-gguf)
|
24 |
|
25 |
## Convert Script
|
26 |
-
[変換スクリプトはこちら](https://github.com/mmnga/
|
27 |
|
28 |
## Usage
|
29 |
|
30 |
```
|
31 |
-
git clone
|
32 |
cd llama.cpp
|
33 |
make -j
|
34 |
./main -m 'llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-q4_0.gguf' -n 128 -p '今日の夕食のレシピを教えて ### 回答:' --top_p 0.9 --temp 0.7 --repeat-penalty 1.2
|
|
|
4 |
|
5 |
# llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-gguf
|
6 |
[llm-jpさんが公開しているllm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0](https://huggingface.co/llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0)のggufフォーマット変換版です。
|
|
|
|
|
|
|
|
|
|
|
7 |
|
8 |
モデル一覧
|
9 |
[mmnga/llm-jp-13b-v1.0-4bit-g128-GPTQ-calib-ja-1k](https://huggingface.co/mmnga/llm-jp-13b-v1.0-4bit-g128-GPTQ-calib-ja-1k)
|
|
|
11 |
[mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-GPTQ-calib-ja-1k](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-GPTQ-calib-ja-1k)
|
12 |
|
13 |
GGUF版
|
14 |
+
[mmnga/llm-jp-13b-instruct-dolly-en-ja-oasst-v1.1-gguf](https://huggingface.co/mmnga/llm-jp-13b-instruct-dolly-en-ja-oasst-v1.1-gguf)
|
15 |
[mmnga/llm-jp-13b-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-v1.0-gguf)
|
16 |
[mmnga/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-gguf)
|
17 |
[mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-dolly-oasst-v1.0-gguf)
|
|
|
19 |
[mmnga/llm-jp-1.3b-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-1.3b-v1.0-gguf)
|
20 |
|
21 |
## Convert Script
|
22 |
+
[変換スクリプトはこちら](https://gist.github.com/mmnga/bcde6bab59132682307112fef0472b80#file-llm-jp_convert-hf-to-gguf-py)
|
23 |
|
24 |
## Usage
|
25 |
|
26 |
```
|
27 |
+
git clone https://github.com/ggerganov/llama.cpp.git
|
28 |
cd llama.cpp
|
29 |
make -j
|
30 |
./main -m 'llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0-q4_0.gguf' -n 128 -p '今日の夕食のレシピを教えて ### 回答:' --top_p 0.9 --temp 0.7 --repeat-penalty 1.2
|