Text Generation
Transformers
Safetensors
English
Chinese
llama
Taiwan
R.O.C
zhtw
SLM
Llama-32
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use twinkle-ai/Llama-3.2-3B-F1-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use twinkle-ai/Llama-3.2-3B-F1-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="twinkle-ai/Llama-3.2-3B-F1-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("twinkle-ai/Llama-3.2-3B-F1-Instruct") model = AutoModelForCausalLM.from_pretrained("twinkle-ai/Llama-3.2-3B-F1-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use twinkle-ai/Llama-3.2-3B-F1-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "twinkle-ai/Llama-3.2-3B-F1-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "twinkle-ai/Llama-3.2-3B-F1-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/twinkle-ai/Llama-3.2-3B-F1-Instruct
- SGLang
How to use twinkle-ai/Llama-3.2-3B-F1-Instruct with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "twinkle-ai/Llama-3.2-3B-F1-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "twinkle-ai/Llama-3.2-3B-F1-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "twinkle-ai/Llama-3.2-3B-F1-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "twinkle-ai/Llama-3.2-3B-F1-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use twinkle-ai/Llama-3.2-3B-F1-Instruct with Docker Model Runner:
docker model run hf.co/twinkle-ai/Llama-3.2-3B-F1-Instruct
Model Card for Llama-3.2-3B-F1-Instruct (a.k.a Formosa-1 or F1)
Llama-3.2-3B-F1-Instruct(a.k.a Formosa-1 or F1) 是由 Twinkle AI 與 APMIC 合作開發,並在國家高速網路與計算中心技術指導之下,針對中華民國台灣語境與任務需求所微調之繁體中文語言模型,涵蓋法律、教育、生活應用等多元場景,並以高指令跟隨能力為目標進行強化。
Model Details
Model Description
- Developed by: Liang Hsun Huang、Min Yi Chen、Wen Bin Lin、Chao Chun Chuang & Dave Sung (All authors have contributed equally to this work.)
- Funded by: APMIC
- Model type: LlamaForCausalLM
- Language(s) (NLP): Tranditional Chinese & English
- License: llama3.2
Model Sources
- Repository: twinkle-ai/Llama-3.2-3B-F1-Instruct
- Paper: (TBA)
Evaluation
Results
下表採用 🌟 Twinkle Eval 評測框架
| 模型 | 評測模式 | TMMLU+(%) | 台灣法律(%) | MMLU(%) | 測試次數 | 選項排序 |
|---|---|---|---|---|---|---|
| mistralai/Mistral-Small-24B-Instruct-2501 | box | 56.15 (±0.0172) | 37.48 (±0.0098) | 74.61 (±0.0154) | 3 | 隨機 |
| meta-llama/Llama-3.2-3B-Instruct | box | 15.49 (±0.0104) | 25.68 (±0.0200) | 6.90 (±0.0096) | 3 | 隨機 |
| meta-llama/Llama-3.2-3B-Instruct | pattern | 35.85 (±0.0174) | 32.22 (±0.0023) | 59.33 (±0.0168) | 3 | 隨機 |
| MediaTek-Research/Llama-Breeze2-3B-Instruct | pattern | 40.32 (±0.0181) | 38.92 (±0.0193) | 55.37 (±0.0180) | 3 | 隨機 |
| 🌟twinkle-ai/Llama-3.2-3B-F1-Instruct (ours) | box | 44.11 (±0.0179) | 35.24 (±0.0119) | 50.64 (±0.0189) | 3 | 隨機 |
Function Calling Benchmark
我們採用了 BFCL (Berkeley Function Calling Leaderboard) 來評估模型在 Function Calling(函式呼叫)任務中的表現。
測試使用的指標如下:
- AST Accuracy(AST 正確率):
比較模型生成的函式呼叫與目標答案在抽象語法樹(AST)上的結構相似度。涵蓋四種題型:- 單一函式(Simple Function)
- 多函式(Multiple Function)
- 平行函式(Parallel Function)
- 平行多函式(Parallel Multiple Function)
| Model | Overall Accuracy | AST Accuracy (S.) | AST Accuracy (M.) | AST Accuracy (P.) | AST Accuracy (P.M.) |
|---|---|---|---|---|---|
| meta-llama/Llama-3.2-3B-Instruct | 84 | 92 | 92 | 80 | 74 |
| MediaTek-Research/Llama-Breeze2-3B-Instruct | 85 | 92 | 92 | 84 | 81 |
| meta-llama/Llama-3.1-8B-Instruct | 57 | 56 | 54 | 49 | 35 |
| MediaTek-Research/Llama-Breeze2-8B-Instruct | 87 | 91 | 93 | 86 | 81 |
| GPT-4o-mini(2024-07-18) | 87 | 91 | 93 | 90 | 84 |
| 🌟twinkle-ai/Llama-3.2-3B-F1-Instruct (ours) | 91 | 93 | 95 | 91 | 87 |
Note: 部分數據取自 Breeze 的論文。
🔧 Tool Calling
本模型使用 Hermes 格式訓練,並支援平行呼叫(Parallel calling),以下為完整範例流程。 Tool call 模板已經為大家寫好放進 chat-template 了,Enjoy it!
1️⃣ 啟動 vLLM 後端
vllm serve twinkle-ai/Llama-3.2-3B-F1-Instruct \
--port 8001 \
--enable-auto-tool-choice \
--tool-call-parser hermes
2️⃣ 定義工具(Functions)
def get_weather(location: str, unit: str):
return f"{location}的氣溫是{unit}26度,晴朗無風"
def search(query: str):
return "川普終於宣布對等關稅政策,針對 18 個經濟體課徵一半的對等關稅,並從 4/5 起對所有進口產品徵收10%的基準關稅!美國將針對被認定為不當貿易行為(不公平貿易) 的國家,於 4/9 起課徵報復型對等關稅 (Discounted Reciprocal Tariff),例如:日本將被課徵 24% 的關稅,歐盟則為 20%,以取代普遍性的 10% 關稅。\n針對中國則開啟新一波 34% 關稅,並疊加於先前已實施的關稅上,這將使中國進口商品的基本關稅稅率達到 54%,而且這尚未包含拜登總統任內或川普第一任期所施加的額外關稅。加拿大與墨西哥則不適用這套對等關稅制度,但川普認為這些國家在芬太尼危機與非法移民問題尚未完全解決,因此計畫對這兩國的大多數進口商品施加 25% 關稅。另外原本針對汽車與多數其他商品的關稅豁免將於 4/2 到期。\n台灣的部分,美國擬向台灣課徵32%的對等關稅,雖然並未針對晶片特別課徵關稅,但仍在記者會中提到台灣搶奪所有的電腦與半導體晶片,最終促成台積電對美國投資計劃額外加碼 1,000 億美元的歷史性投資;歐盟則課徵20%的對等關稅。最後是汽車關稅將於 4/2 起,對所有外國製造的汽車課徵25% 關稅。"
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "國家或城市名, e.g., 'Taipei'、'Jaipei'"},
"unit": {"type": "string", "description": "氣溫單位,亞洲城市使用攝氏;歐美城市使用華氏", "enum": ["celsius", "fahrenheit"]}
},
"required": ["location", "unit"]
}
}
},
{
"type": "function",
"function": {
"name": "search",
"description": "這是一個類似 Google 的搜尋引擎,關於知識、天氣、股票、電影、小說、百科等等問題,如果你不確定答案就搜尋一下。",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string", "description": "should be a search query, e.g., '2024 南韓 戒嚴'"}
},
"required": ["query"]
}
}
}
]
3️⃣ 執行工具調用(Tool Calls)
⚠️ 注意:system_prompt 可以不用帶,除非是需要時間基準的工具。
response = client.chat.completions.create(
model=client.models.list().data[0].id,
messages=[
{"role": "system", "content": "記住你的知識截止於 2024/12,今天是 2025/4/7"},
{"role": "user", "content": "台北氣溫如何? 另外,告訴我川普最新關稅政策"},
],
max_tokens=1500,
temperature=0.6,
top_p=0.95,
tools=tools,
tool_choice="auto",
extra_body={"skip_special_tokens": False}
)
print(response.choices[0].message.tool_calls)
⚙️ Tool Calls List:
[ChatCompletionMessageToolCall(id='chatcmpl-tool-35e74420119349999913a10133b84bd3', function=Function(arguments='{"location": "Taipei", "unit": "celsius"}', name='get_weather'), type='function'), ChatCompletionMessageToolCall(id='chatcmpl-tool-7ffdcb98e59f4134a6171defe7f2e31b', function=Function(arguments='{"query": "Donald Trump latest tariffs policy"}', name='search'), type='function')]
4️⃣ 產生最終回答
response = client.chat.completions.create(
model=client.models.list().data[0].id,
messages=[
{"role": "system", "content": "記住你的知識截止於 2024/12,今天是 2025/4/7"},
{"role": "user", "content": "台北氣溫如何? 另外,告訴我川普最新關稅政策"},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": response.choices[0].message.tool_calls[0].id,
"type": "function",
"function": {
"name": response.choices[0].message.tool_calls[0].function.name,
"arguments": response.choices[0].message.tool_calls[0].function.arguments
}
},
{
"id": response.choices[0].message.tool_calls[1].id,
"type": "function",
"function": {
"name": response.choices[0].message.tool_calls[1].function.name,
"arguments": response.choices[0].message.tool_calls[1].function.arguments
}
}
]
},
{
"role": "tool",
"content": search(**json.loads(response.choices[0].message.tool_calls[0].function.arguments)),
"tool_call_id": response.choices[0].message.tool_calls[0].id # tool_call_id 必須要帶,才能正確配對 工具 及 tool_call
},
{
"role": "tool",
"content": get_weather(**json.loads(response.choices[0].message.tool_calls[1].function.arguments)),
"tool_call_id": response.choices[0].message.tool_calls[1].id # tool_call_id 必須要帶,才能正確配對 工具 及 tool_call
}
],
max_tokens=1500,
temperature=0.6,
top_p=0.95,
tools=tools,
tool_choice="auto",
extra_body={"skip_special_tokens": False}
)
print(response.choices[0].message.content)
📋 最終輸出內容:
以下是您請求的資訊:
**臺北市氣溫**
- 目前的氣溫為 **26°C**(攝氏)
- 天候狀況:晴朗無風
**川普最新關稅政策概述**
1. **對等關稅政策**
- 對 18 個經濟體課徵 50% 的對等關稅
- 自 4 月 5 日起,所有進口產品全面徵收 10% 基本關稅
2. **報復型對等關稅**
- 日本 24%、歐盟 20%
3. **對中國的高額關稅**
- 增加至 54%(原有關稅 + 新增 34%)
4. **特殊案例**
- 加拿大與墨西哥不適用,但其他商品課徵 25%
- 汽車與部分商品的免稅即將到期
5. **對台灣的影響**
- 美國計畫對台灣課徵 32% 關稅,但晶片暫無額外課稅
6. **全球視角**
- 歐盟與日本關稅比例相對較高
Citation
@misc{twinkleai2025llama3.2f1,
title = {Llama-3.2-3B-F1-Instruct: A Traditional Chinese Instruction-Tuned Language Model for Taiwan},
author = {Huang, Liang Hsun and Chen, Min Yi and Lin, Wen Bin and Chuang, Chao Chun and Sung, Dave},
year = {2025},
howpublished = {\url{https://huggingface.co/twinkle-ai/Llama-3.2-3B-F1-Instruct}},
note = {Twinkle AI and APMIC. All authors contributed equally.}
}
Acknowledge
- 特此感謝國家高速網路與計算中心的指導與 APMIC 的算力支援,才得以讓本專案訓利完成。
- 特此致謝黃啟聖老師、許武龍(哈爸)、臺北市立第一女子高級中學物理科陳姿燁老師、奈視科技 CTO Howard、AIPLUX Technology、郭家嘉老師以及所有在資料集製作過程中提供寶貴協助的夥伴。
Model Card Authors
Model Card Contact
- Downloads last month
- 10
Model tree for twinkle-ai/Llama-3.2-3B-F1-Instruct
Base model
meta-llama/Llama-3.2-3BDatasets used to train twinkle-ai/Llama-3.2-3B-F1-Instruct
Viewer • Updated • 116k • 34 • 2
minyichen/tw_mm_R1
Viewer • Updated • 297 • 19 • 2
minyichen/tw-instruct-R1-200k
Updated • 18
Space using twinkle-ai/Llama-3.2-3B-F1-Instruct 1
Collection including twinkle-ai/Llama-3.2-3B-F1-Instruct
Paper for twinkle-ai/Llama-3.2-3B-F1-Instruct
Evaluation results
- single choice on tmmlu+test set self-reported44.110
- single choice on mmlutest set self-reported50.640
- single choice on tw-legal-benchmark-v1test set self-reported35.240
