File size: 1,280 Bytes
8bb4028
 
 
 
5bf95ca
 
 
8bb4028
 
5bf95ca
 
8bb4028
 
 
 
 
 
5bf95ca
 
 
8bb4028
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
---
license: cc-by-nc-4.0
---
# What is this?
CohereForAI(C4AI)のオープンウェイト言語モデル[Command R+](https://huggingface.co/CohereForAI/c4ai-command-r-plus)をGGUFフォーマットに変換したものです。<br>
商用利用は不可となっているため注意してください。<br>
**llama.cppのpre-tokenization対応アップデート([#6920](https://github.com/ggerganov/llama.cpp/pull/6920))を反映しています。**

# imatrix dataset
日本語能力を重視し、日本語が多量に含まれる[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)データセットを使用しました。<br>
なお、計算リソースの関係上imatrixの算出においてはQ6_K量子化モデルを使用しました。

# Chat template
```
<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>ここにSystem Promptを書きます<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>ここにMessageを書きます<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
```

# Environment
Windows版llama.cpp-b3181およびllama.cpp-b3171同時リリースのconvert-hf-to-gguf.pyを使用して量子化作業を実施しました。

# License
CC-BY-NC-4.0

# Developer
CohereForAI(C4AI)