モデル概要
モデル特徴
モデル能力
使用事例
🚀 Llama-4-Scout-17B-16E-Instruct-GGUF
このプロジェクトは、Llama-4-Scout-17B-16E-Instructモデルの量子化バージョンを提供しています。多言語に対応しており、LlamaEdgeを通じて実行できます。
🚀 クイックスタート
実行環境
現在はLlama-4のテキストモードのみサポートしています!
オリジナルモデル
unsloth/Llama-4-Scout-17B-16E-Instruct
LlamaEdgeを使用した実行
バージョン要件
LlamaEdgeのバージョンは v0.16.16 以上が必要です。
プロンプトテンプレート
- プロンプトタイプ:
llama-4-chat
- プロンプト文字列
<|begin_of_text|><|header_start|>system<|header_end|>
{system_prompt}<|eot|><|header_start|>user<|header_end|>
{user_message_1}<|eot|><|header_start|>assistant<|header_end|>
{assistant_message_1}<|eot|><|header_start|>user<|header_end|>
{user_message_2}<|eot|>
<|header_start|>assistant<|header_end|>
- 例:ツールの使用
-
ユーザーの質問とツール情報を含むプロンプト
例を表示するにはクリック
```text <|begin_of_text|><|header_start|>system<|header_end|>You are a helpful assistant.<|eot|> <|header_start|>user<|header_end|>
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
[ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "description": "The temperature unit to use. Infer this from the users location.", "enum": [ "celsius", "fahrenheit" ] } }, "required": [ "location", "unit" ] } } }, { "type": "function", "function": { "name": "predict_weather", "description": "Predict the weather in 24 hours", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "description": "The temperature unit to use. Infer this from the users location.", "enum": [ "celsius", "fahrenheit" ] } }, "required": [ "location", "unit" ] } } }, { "type": "function", "function": { "name": "sum", "description": "Calculate the sum of two numbers", "parameters": { "type": "object", "properties": { "a": { "type": "integer", "description": "the left hand side number" }, "b": { "type": "integer", "description": "the right hand side number" } }, "required": [ "a", "b" ] } } } ]
Question: How is the weather of Beijing, China in celsius?<|eot|><|header_start|>assistant<|header_end|>
</details>
-
ツールの結果を含むプロンプト
例を表示するにはクリック
```text <|begin_of_text|><|header_start|>system<|header_end|>You are a helpful assistant.<|eot|> <|header_start|>user<|header_end|>
How is the weather of Beijing, China in celsius?<|eot|> <|header_start|>assistant<|header_end|>
{"name":"get_current_weather","arguments":"{"location":"Beijing, China","unit":"celsius"}"}<|eot|> <|header_start|>ipython<|header_end|>
{"temperature":"30","unit":"celsius"}<|eot|><|header_start|>assistant<|header_end|>
</details>
-
コンテキストサイズ
10M
LlamaEdgeサービスとして実行
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-4-Scout-17B-16E-Instruct-Q5_K_M.gguf \
llama-api-server.wasm \
--prompt-template llama-4-chat \
--ctx-size 1000000 \
--model-name Llama-4-Scout
LlamaEdgeコマンドアプリケーションとして実行
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-4-Scout-17B-16E-Instruct-Q5_K_M.gguf \
llama-chat.wasm \
--prompt-template llama-4-chat \
--ctx-size 1000000
📦 量子化されたGGUFモデル
llama.cpp b5074を使用して量子化されています。
📄 ライセンス
ライセンスタイプ:other ライセンス名:llama4
📚 ドキュメント
属性 | 詳細 |
---|---|
モデル名 | Llama-4-Scout-17B-16E-Instruct |
ベースモデル | unsloth/Llama-4-Scout-17B-16E-Instruct |
モデル作成者 | Meta |
量子化者 | Second State Inc. |
ライブラリ名 | transformers |
サポート言語 | アラビア語、ドイツ語、英語、スペイン語、フランス語、ヒンディー語、インドネシア語、イタリア語、ポルトガル語、タイ語、タガログ語、ベトナム語 |
タグ | facebook、meta、llama、llama-4 |



