モデル概要
モデル特徴
モデル能力
使用事例
🚀 Mistral-Small-3.2-24B-Instruct-2506
Mistral-Small-3.2-24B-Instruct-2506は、画像テキストからテキストへのモデルです。モデルの量子化において優れた性能を発揮し、命令の遵守、繰り返しエラーの削減、関数呼び出しなどの面で著しい向上が見られます。
🚀 クイックスタート
実行環境
英語、フランス語、ドイツ語、スペイン語など、複数の言語をサポートしています。
ライセンス
Apache - 2.0ライセンスを採用しています。
実行コード
llama.cppでの実行
./llama.cpp/llama-cli -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:UD-Q4_K_XL --jinja --temp 0.15 --top-k -1 --top-p 1.00 -ngl 99
Ollamaでの実行
ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:UD-Q4_K_XL
注意事項
⚠️ 重要な注意事項
このモデルには GGUFチャットテンプレートの修正 が含まれています!ツール呼び出しも正常に機能します!
llama.cpp
を使用する場合は、--jinja
を使用してシステムプロンプトを有効にしてください。
💡 使用上のヒント
比較的低い温度(例:
temperature = 0.15
)を使用することをおすすめします。また、特定のニーズに合わせるために、モデルにシステムプロンプトを追加することを確認してください。モデルを汎用アシスタントとして使用する場合は、SYSTEM_PROMPT.txtファイルに記載されているプロンプトを使用することをおすすめします。
Unsloth Dynamic 2.0 は、モデルの量子化においてSOTA性能を達成しています。
✨ 主な機能
- Mistral-Small-3.1-24B-Instruct-2503 と同じ核心機能を備えています。
- 命令の遵守:Small - 3.2は、正確な命令を遵守する能力がより高いです。
- 繰り返しエラー:Small - 3.2は、無限生成や繰り返しの答えを減らしています。
- 関数呼び出し:Small - 3.2の関数呼び出しテンプレートはより堅牢です。
📦 インストール
vLLM(推奨)
vLLM >= 0.9.1
をインストールしてください:
pip install vllm --upgrade
インストールが完了すると、自動的にmistral_common >= 1.6.2
がインストールされます。以下のコマンドで確認できます:
python -c "import mistral_common; print(mistral_common.__version__)"
dockerイメージ を使用するか、docker hub で実行することもできます。
💻 使用例
基本的な使用法
サーバーの起動
vllm serve mistralai/Mistral-Small-3.2-24B-Instruct-2506 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --limit_mm_per_prompt 'image=10' --tensor-parallel-size 2
注意:GPU上でMistral - Small - 3.2 - 24B - Instruct - 2506を実行するには、約55GBのGPU RAM(bf16またはfp16)が必要です。
高度な使用法
視覚的な推論
from datetime import datetime, timedelta
from openai import OpenAI
from huggingface_hub import hf_hub_download
# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
TEMP = 0.15
MAX_TOK = 131072
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
models = client.models.list()
model = models.data[0].id
def load_system_prompt(repo_id: str, filename: str) -> str:
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
today = datetime.today().strftime("%Y-%m-%d")
yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
model_name = repo_id.split("/")[-1]
return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
},
{"type": "image_url", "image_url": {"url": image_url}},
],
},
]
response = client.chat.completions.create(
model=model,
messages=messages,
temperature=TEMP,
max_tokens=MAX_TOK,
)
print(response.choices[0].message.content)
# In this situation, you are playing a Pokémon game where your Pikachu (Level 42) is facing a wild Pidgey (Level 17). Here are the possible actions you can take and an analysis of each:
# 1. **FIGHT**:
# - **Pros**: Pikachu is significantly higher level than the wild Pidgey, which suggests that it should be able to defeat Pidgey easily. This could be a good opportunity to gain experience points and possibly items or money.
# - **Cons**: There is always a small risk of Pikachu fainting, especially if Pidgey has a powerful move or a status effect that could hinder Pikachu. However, given the large level difference, this risk is minimal.
# 2. **BAG**:
# - **Pros**: You might have items in your bag that could help in this battle, such as Potions, Poké Balls, or Berries. Using an item could help you capture the Pidgey or heal your Pikachu if needed.
# - **Cons**: Using items might not be necessary given the level difference. It could be more efficient to just fight and defeat the Pidgey quickly.
# 3. **POKÉMON**:
# - **Pros**: You might have another Pokémon in your party that is better suited for this battle or that you want to gain experience. Switching Pokémon could also be a strategic move if you want to train a lower-level Pokémon.
# - **Cons**: Switching Pokémon might not be necessary since Pikachu is at a significant advantage. It could also waste time and potentially give Pidgey a turn to attack.
# 4. **RUN**:
# - **Pros**: Running away could save time and conserve your Pokémon's health and resources. If you are in a hurry or do not need the experience or items, running away is a safe option.
# - **Cons**: Running away means you miss out on the experience points and potential items or money that you could gain from defeating the Pidgey. It also means you do not get the chance to capture the Pidgey if you wanted to.
# ### Recommendation:
# Given the significant level advantage, the best action is likely to **FIGHT**. This will allow you to quickly defeat the Pidgey, gain experience points, and potentially earn items or money. If you are concerned about Pikachu's health, you could use an item from your **BAG** to heal it before or during the battle. Running away or switching Pokémon does not seem necessary in this situation.
関数呼び出し
from openai import OpenAI
from huggingface_hub import hf_hub_download
# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
TEMP = 0.15
MAX_TOK = 131072
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
models = client.models.list()
model = models.data[0].id
def load_system_prompt(repo_id: str, filename: str) -> str:
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
return system_prompt
model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
image_url = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/europe.png"
tools = [
{
"type": "function",
"function": {
"name": "get_current_population",
"description": "Get the up-to-date population of a given country.",
"parameters": {
"type": "object",
"properties": {
"country": {
"type": "string",
"description": "The country to find the population of.",
},
"unit": {
"type": "string",
"description": "The unit for the population.",
"enum": ["millions", "thousands"],
},
},
"required": ["country", "unit"],
},
},
},
{
"type": "function",
"function": {
"name": "rewrite",
"description": "Rewrite a given text for improved clarity",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The input text to rewrite",
}
},
},
},
},
]
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": "Could you please make the below article more concise?\n\nOpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership.",
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "bbc5b7ede",
"type": "function",
"function": {
"name": "rewrite",
"arguments": '{"text": "OpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership."}',
},
}
],
},
{
"role": "tool",
"content": '{"action":"rewrite","outcome":"OpenAI is a FOR-profit company."}',
"tool_call_id": "bbc5b7ede",
"name": "rewrite",
},
{
"role": "assistant",
"content": "---\n\nOpenAI is a FOR-profit company.",
},
{
"role": "user",
"content": [
{
"type": "text",
"text": "Can you tell me what is the biggest country depicted on the map?",
},
{
"type": "image_url",
"image_url": {
"url": image_url,
},
},
],
}
]
response = client.chat.completions.create(
model=model,
messages=messages,
temperature=TEMP,
max_tokens=MAX_TOK,
tools=tools,
tool_choice="auto",
)
assistant_message = response.choices[0].message.content
print(assistant_message)
# The biggest country depicted on the map is Russia.
messages.extend([
{"role": "assistant", "content": assistant_message},
{"role": "user", "content": "What is the population of that country in millions?"},
])
response = client.chat.completions.create(
model=model,
messages=messages,
temperature=TEMP,
max_tokens=MAX_TOK,
tools=tools,
tool_choice="auto",
)
print(response.choices[0].message.tool_calls)
# [ChatCompletionMessageToolCall(id='3e92V6Vfo', function=Function(arguments='{"country": "Russia", "unit": "millions"}', name='get_current_population'), type='function')]
📚 ドキュメント
ベンチマーク結果
Mistral - Small - 3.2 - 24BをMistral - Small - 3.1 - 24B - Instruct - 2503 と比較しました。他の同規模のモデルとのより多くの比較を行うには、Mistral - Small - 3.1のベンチマーク を参照してください。
テキストテスト
モデル | Wildbench v2 | Arena Hard v2 | IF(内部;正解率) |
---|---|---|---|
Small 3.1 24B Instruct | 55.6% | 19.56% | 82.75% |
Small 3.2 24B Instruct | 65.33% | 43.1% | 84.78% |
無限生成テスト
Small 3.2は、挑戦的で長く繰り返しのあるプロンプトで、無限生成の発生率を2倍に減らしました。
モデル | 無限生成(内部;低いほど良い) |
---|---|
Small 3.1 24B Instruct | 2.11% |
Small 3.2 24B Instruct | 1.29% |
STEMテスト
モデル | MMLU | MMLU Pro(5-shot CoT) | MATH | GPQA Main(5-shot CoT) | GPQA Diamond(5-shot CoT) | MBPP Plus - Pass@5 | HumanEval Plus - Pass@5 | SimpleQA(総正解率) |
---|---|---|---|---|---|---|---|---|
Small 3.1 24B Instruct | 80.62% | 66.76% | 69.30% | 44.42% | 45.96% | 74.63% | 88.99% | 10.43% |
Small 3.2 24B Instruct | 80.50% | 69.06% | 69.42% | 44.22% | 46.13% | 78.33% | 92.90% | 12.10% |
視覚テスト
モデル | MMMU | Mathvista | ChartQA | DocVQA | AI2D |
---|---|---|---|---|---|
Small 3.1 24B Instruct | 64.00% | 68.91% | 86.24% | 94.08% | 93.72% |
Small 3.2 24B Instruct | 62.50% | 67.09% | 87.4% | 94.86% | 92.91% |
🔧 技術詳細
ベースモデル
- mistralai/Mistral - Small - 3.2 - 24B - Instruct - 2506
サポート言語
- 英語、フランス語、ドイツ語、スペイン語、ポルトガル語、イタリア語、日本語、韓国語、ロシア語、中国語、アラビア語、ペルシャ語、インドネシア語、マレー語、ネパール語、ポーランド語、ルーマニア語、セルビア語、スウェーデン語、トルコ語、ウクライナ語、ベトナム語、ヒンディー語、ベンガル語
推論設定
推論機能は有効になっていません。
パイプラインラベル
image - text - to - text
📄 ライセンス
このプロジェクトはApache - 2.0ライセンスの下で提供されています。








