Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,40 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- ja
|
6 |
+
tags:
|
7 |
+
- llama
|
8 |
+
---
|
9 |
+
|
10 |
+
# llm-jp-13b-v2.0-gguf
|
11 |
+
[llm-jpさんが公開しているllm-jp-13b-v2.0](https://huggingface.co/llm-jp/llm-jp-13b-v2.0)のggufフォーマット変換版です。
|
12 |
+
|
13 |
+
モデル一覧
|
14 |
+
|
15 |
+
GGUF V2.0系
|
16 |
+
[mmnga/llm-jp-13b-v2.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-v2.0-gguf)
|
17 |
+
[mmnga/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-gguf)
|
18 |
+
[mmnga/llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-gguf ](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-gguf )
|
19 |
+
[mmnga/llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-gguf ](https://huggingface.co/mmnga/llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-gguf )
|
20 |
+
|
21 |
+
|
22 |
+
GGUF V1.0系
|
23 |
+
[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)
|
24 |
+
[mmnga/llm-jp-13b-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-13b-v1.0-gguf)
|
25 |
+
[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)
|
26 |
+
[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)
|
27 |
+
[mmnga/llm-jp-1.3b-v1.0-gguf](https://huggingface.co/mmnga/llm-jp-1.3b-v1.0-gguf)
|
28 |
+
|
29 |
+
|
30 |
+
## Convert Script
|
31 |
+
[convert-hf-to-gguf_llmjp_v2-py](https://gist.github.com/mmnga/8b8f6ca14f94326ffdac96a3c3605751#file-convert-hf-to-gguf_llmjp_v2-py)
|
32 |
+
|
33 |
+
## Usage
|
34 |
+
|
35 |
+
```
|
36 |
+
git clone https://github.com/ggerganov/llama.cpp.git
|
37 |
+
cd llama.cpp
|
38 |
+
make -j
|
39 |
+
./main -m 'llm-jp-13b-v2.0-q4_0.gguf' -n 128 -p '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。\n\n### 指示:\n自然言語処理とは何か\n\n### 応答:\n' --top_p 0.95 --temp 0.7 --repeat-penalty 1.1
|
40 |
+
```
|