Update README.md
Browse files
README.md
CHANGED
|
@@ -10,17 +10,32 @@ language:
|
|
| 10 |
- ja
|
| 11 |
---
|
| 12 |
# karakuri-lm-upscaled-103b-v0.1
|
|
|
|
| 13 |
|
| 14 |
-
|
| 15 |
|
| 16 |
-
[
|
| 17 |
|
| 18 |
-
[
|
| 19 |
|
| 20 |
This is a 103b frankenmerge of [karakuri-ai/karakuri-lm-70b-chat-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-70b-chat-v0.1) created by interleaving layers of [karakuri-ai/karakuri-lm-70b-chat-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-70b-chat-v0.1) with itself using [mergekit](https://github.com/cg123/mergekit). Please refer to the original model regarding the license.
|
| 21 |
|
| 22 |
Inspired by [wolfram/miqu-1-103b](https://huggingface.co/wolfram/miqu-1-103b).
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## ベンチマーク/Benchmark
|
| 25 |
ベースとしたkarakuri-ai/karakuri-lm-70b-chat-v0.1と本モデルの[japanese-mt-bench](https://github.com/Stability-AI/FastChat/tree/jp-stable/fastchat/llm_judge)の結果は以下の通りです。
|
| 26 |
（シングルターン, 4ビット量子化）
|
|
|
|
| 10 |
- ja
|
| 11 |
---
|
| 12 |
# karakuri-lm-upscaled-103b-v0.1
|
| 13 |
+
[GGUF版はこちら/Click here for the GGUF version](https://huggingface.co/Aratako/karakuri-lm-chat-upscaled-103b-v0.1-GGUF)
|
| 14 |
|
| 15 |
+
## 概要/Description
|
| 16 |
|
| 17 |
+
[karakuri-ai/karakuri-lm-70b-chat-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-70b-chat-v0.1)を自身でフランケンマージし、103bまで拡張したモデルです。ライセンスに関しては元モデルと同一です。
|
| 18 |
|
| 19 |
+
[wolfram/miqu-1-103b](https://huggingface.co/wolfram/miqu-1-103b)と同じマージ手法を用いています。
|
| 20 |
|
| 21 |
This is a 103b frankenmerge of [karakuri-ai/karakuri-lm-70b-chat-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-70b-chat-v0.1) created by interleaving layers of [karakuri-ai/karakuri-lm-70b-chat-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-70b-chat-v0.1) with itself using [mergekit](https://github.com/cg123/mergekit). Please refer to the original model regarding the license.
|
| 22 |
|
| 23 |
Inspired by [wolfram/miqu-1-103b](https://huggingface.co/wolfram/miqu-1-103b).
|
| 24 |
|
| 25 |
+
## ライセンス/License
|
| 26 |
+
元モデルのライセンスを継承します。元モデルのライセンスを引用します。
|
| 27 |
+
|
| 28 |
+
This model inherits the license of the original model. I will quote the license of the original model.
|
| 29 |
+
|
| 30 |
+
>Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
|
| 31 |
+
>
|
| 32 |
+
>Subject to the license above, and except for commercial purposes, you are free to share and adapt KARAKURI LM, provided that you must, in a recognizable and appropriate manner, (i) state that you are using KARAKURI LM developed by KARAKURI Inc., when you publish or make available to third parties KARAKURI LM, its derivative works or modification, or any output or results of KARAKURI LM or its derivative works or modification, and (ii) indicate your contributions, if you modified any material of KARAKURI LM.
|
| 33 |
+
>
|
| 34 |
+
>
|
| 35 |
+
>If you plan to use KARAKURI LM for commercial purposes, please contact us beforehand. You are not authorized to use KARAKURI LM for commercial purposes unless we expressly grant you such rights.
|
| 36 |
+
>
|
| 37 |
+
>If you have any questions regarding the interpretation of above terms, please also feel free to contact us.
|
| 38 |
+
|
| 39 |
## ベンチマーク/Benchmark
|
| 40 |
ベースとしたkarakuri-ai/karakuri-lm-70b-chat-v0.1と本モデルの[japanese-mt-bench](https://github.com/Stability-AI/FastChat/tree/jp-stable/fastchat/llm_judge)の結果は以下の通りです。
|
| 41 |
（シングルターン, 4ビット量子化）
|