theluyuan/rwkv-runner
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

allow setting quantizedLayers of WebGPU mode; chore

Browse Source
This commit is contained in:
josc146
2024-03-01 14:23:05 +08:00
parent c9513822c9
commit 887ba06bd6
8 changed files with 46 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
frontend/src/_locales/ja/main.json
View File

@@ -341,5 +341,7 @@
"Load Conversation": "会話を読み込む",
"The latest X messages will be sent to the server. If you are using the RWKV-Runner server, please use the default value because RWKV-Runner has built-in state cache management which only calculates increments. Sending all messages will have lower cost. If you are using ChatGPT, adjust this value according to your needs to reduce ChatGPT expenses.": "最新のX件のメッセージがサーバーに送信されます。RWKV-Runnerサーバーを使用している場合は、デフォルト値を使用してください。RWKV-Runnerには組み込みの状態キャッシュ管理があり、増分のみを計算します。すべてのメッセージを送信すると、コストが低くなります。ChatGPTを使用している場合は、ChatGPTの費用を削減するために必要に応じてこの値を調整してください。",
"History Message Number": "履歴メッセージ数",
"Send All Message": "すべてのメッセージを送信"
"Send All Message": "すべてのメッセージを送信",
"Quantized Layers": "量子化されたレイヤー",
"Number of the neural network layers quantized with current precision, the more you quantize, the lower the VRAM usage, but the quality correspondingly decreases.": "現在の精度で量子化されたニューラルネットワークのレイヤーの数、量子化するほどVRAMの使用量が低くなりますが、品質も相応に低下します。"
}

4
frontend/src/_locales/zh-hans/main.json
View File

@@ -341,5 +341,7 @@
"Load Conversation": "读取对话",
"The latest X messages will be sent to the server. If you are using the RWKV-Runner server, please use the default value because RWKV-Runner has built-in state cache management which only calculates increments. Sending all messages will have lower cost. If you are using ChatGPT, adjust this value according to your needs to reduce ChatGPT expenses.": "最近的X条消息会发送至服务器. 如果你正在使用RWKV-Runner服务器, 请使用默认值, 因为RWKV-Runner内置了state缓存管理, 只计算增量, 发送所有消息将具有更低的成本. 如果你正在使用ChatGPT, 则根据你的需要调整此值, 这可以降低ChatGPT的费用",
"History Message Number": "历史消息数量",
"Send All Message": "发送所有消息"
"Send All Message": "发送所有消息",
"Quantized Layers": "量化层数",
"Number of the neural network layers quantized with current precision, the more you quantize, the lower the VRAM usage, but the quality correspondingly decreases.": "神经网络以当前精度量化的层数, 量化越多, 占用显存越低, 但质量相应下降"
}