README.md

---
license: apache-2.0
extra_gated_prompt: "We will release in the nearly future."
extra_gated_fields:
  Name: text
  Company: text
  Title: text
---

# Model Card for MediaTek Research Breeze-7B-FC-v1_0

MediaTek Research Breeze-7B-FC (hereinafter referred to as Breeze-7B-FC) is an advanced language model developed by MediaTek Research, building on [Breeze-7B-Base](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v1_0). Breeze-7B-FC extends its predecessor by incorporating a key feature: function calling. These enhancements make Breeze-7B-FC more versatile and capable of handling a wider range of tasks efficiently.


## 🏆 Performance

| Models                                                                                     | #Parameters | Organization | License    | 🧰 Function Calling? | 💬 Instrustion Following? |
|--------------------------------------------------------------------------------------------|-------------|------------|------------|-------------------|----------|
| [Breeze-7B-Instruct-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0)| 7B          | MediaTek Research | Apache 2.0 | ❌  | ✅       |
| [**Breeze-7B-FC-v1_0**](https://huggingface.co/MediaTek-Research/Breeze-7B-FC-v1_0)        | 7B          | MediaTek Research | Apache 2.0 | ✅ | ✅      |
| [Gorilla-OpenFunctions-v2](https://huggingface.co/MediaTek-Research/Breeze-7B-FC-v1_0)     | 7B          | Gorilla LLM       | Apache 2.0 | ✅ | ❌       |
| [GPT-3.5-Turbo-0125](https://openai.com)                                                   |             | OpenAI            | Proprietary| ✅ | ✅      |

**Evaluate function calling on EN benchmark**

We evaluate the performance of function calling on English with benchmark [Berkeley function-calling leaderboard](https://gorilla.cs.berkeley.edu/blogs/8_berkeley_function_calling_leaderboard.html).

| Models                            | ↑ Overall | Irrelevance<br/>Detection | AST/<br/>Simple | AST/<br/>Multiple | AST/<br/>Parallel | AST/<br/>Parallel-Multiple  | Exec/<br/>Simple | Exec/<br/>Multiple | Exec/<br/>Parallel | Exec/<br/>Parallel-Multiple  | 
|-----------------------------------|----------|---------------------|------------|--------------|--------------|------------------------|--------------|---------------------|---------------------|-------------------------------|
| **Breeze-7B-FC-v1_0 (FC)**        | 86.89 |  76.25 | 90.00 | 93.00 | 84.00 | 84.00 | 100.00 | 92.00 | 88.00 | 77.50 |
| Gorilla-OpenFunctions-v2 (FC)     | 85.95 |  60.00 | 94.25 | 95.50 | 86.50 | 86.00 | 97.00 | 96.00 | 80.00 | 75.00 |
| GPT-3.5-Turbo-0125 (FC)           | 72.77 |  4.58  | 87.75 | 90.50 | 88.50 | 82.50 | 91.00 | 82.00 | 78.00 | 52.50 |



![](misc/radar_chart_en.png)

**Evaluate function calling on ZHTW benchmark**

We evaluate the performance of function calling on Traditional Chinese with benchmark [function-calling-leaderboard-for-zhtw](https://github.com/mtkresearch/function-calling-leaderboard-for-zhtw).

| Models                            | ↑ Overall | Irrelevance<br/>Detection | AST/<br/>Simple | AST/<br/>Multiple | AST/<br/>Parallel | AST/<br/>Parallel-Multiple  | Exec/<br/>Simple | Exec/<br/>Multiple | Exec/<br/>Parallel | Exec/<br/>Parallel-Multiple  | 
|-----------------------------------|----------|---------------------|------------|--------------|--------------|------------------------|--------------|---------------------|---------------------|-------------------------------|
| **Breeze-7B-FC-v1_0 (FC)**        | 78.18 |  72.50 | 82.00 |	86.00 | 76.50|67.00|88.00|88.00|80.00|60.00|
| Gorilla-OpenFunctions-v2 (FC)     | 75.68 |  53.75 | 84.75 |	86.50 |	72.50 |	68.00 |	92.00 |	92.00 |	62.00 |	72.50 |
| GPT-3.5-Turbo-0125 (FC)           | 66.15 |  7.50  | 83.75 |	83.50 |	73.00 |	65.50 |	88.00 |	84.00 |	72.00 |	40.00 |



![](misc/radar_chart_zhtw.png)


 **Evaluate instrustion following on EN benchmark**

We evaluate the performance of instruction following on English with benchmark [MT-Bench](https://github.com/lm-sys/FastChat/blob/main/fastchat/llm_judge/README.md).

| | Win | Tie | Lose |
|---|---|---|---|
| **Breeze-7B-FC-v1_0** *v.s.* Breeze-7B-Instruct-v1_0 | 29 (18.1%) | 55 (34.3%) | 76 (47.5%) |


**Evaluate instrustion following on ZHTW benchmark**

We evaluate the performance of instruction following on Traditional Chinese with benchmark [MT-Bench-TC](https://github.com/mtkresearch/TCEval).

| | Win | Tie | Lose |
|---|---|---|---|
| **Breeze-7B-FC-v1_0** *v.s.* Breeze-7B-Instruct-v1_0 | 35 (21.9%) | 73 (45.6%) | 52 (32.5%) |


## 👩‍💻 How to use

**Dependiency**

Install `mtkresearch` package

```
git clone https://github.com/mtkresearch/mtkresearch.git
cd mtkresearch
pip install -e .
```

**Hosting by VLLM**

```python
from vllm import LLM, SamplingParams

llm = LLM(
    model='MediaTek-Research/Breeze-7B-FC-v1_0',
    tensor_parallel_size=num_gpu, # number of gpus
    gpu_memory_utilization=0.7
)

instance_end_token_id = llm.get_tokenizer().convert_token_to_ids('<|im_end|>')
params = SamplingParams(
    temperature=0.01,
    top_p=0.01,
    max_tokens=4096,
    repetition_penalty=1.1,
    stop_token_ids=[instance_end_token_id]
)

def _inference(prompt, llm, params):
    return llm.generate(prompt, params)[0].outputs[0].text

```

**Instruction following**

```python
from mtkresearch.llm.prompt import MRPromptV2

sys_prompt = ('You are a helpful AI assistant built by MediaTek Research. '
  'The user you are helping speaks Traditional Chinese and comes from Taiwan.')

prompt_engine = MRPromptV2()

conversations = [
    {"role": "system", "content": sys_prompt},
    {"role": "user", "content": "請問什麼是深度學習？"},
]

prompt = prompt_engine.get_prompt(conversations)


output_str = _inference(prompt, llm, params)
result = prompt_engine.parse_generated_str(output_str)

print(result)
# {'role': 'assistant',
#  'content': '深度學習（Deep Learning）是一種機器學習方法，它模仿人類大腦的神經網路結構來
#              處理複雜的數據和任務。在深度學習中，模型由多層人工神經元組成，每個神經元之間有
#              權重連接，並通過非線性轉換進行計算。這些層與層之間的相互作用使模型能夠學習複雜
#              的函數關係或模式，從而解決各種問題，如圖像識別、自然語言理解、語音辨識等。深度
#              學習通常需要大量的數據和強大的計算能力，因此經常使用圖形處理器（GPU）或特殊的
#              加速器來執行。'}
```

**Function Calling**

```python
import json

from mtkresearch.llm.prompt import MRPromptV2

functions = [
    {
      "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",
            "enum": ["celsius", "fahrenheit"]
          }
        },
        "required": ["location"]
      }
    }
]

def faked_get_current_weather(location, unit=None):
    return {'temperature': 30}

mapping = {
    'get_current_weather': faked_get_current_weather
}

prompt_engine = MRPromptV2()

# stage 1: query
conversations = [
    {"role": "user", "content": "請問台北目前溫度是攝氏幾度？"},
]

prompt = prompt_engine.get_prompt(conversations, functions=functions)

output_str = _inference(prompt, llm, params)
result = prompt_engine.parse_generated_str(output_str)

print(result) 
# {'role': 'assistant', 
#  'tool_calls': [
#    {'id': 'call_U9bYCBRAbF639uUqfwehwSbw', 'type': 'function', 
#     'function': {'name': 'get_current_weather', 'arguments': '{"location": "台北, 台灣", "unit": "celsius"}'}}]}

# stage 2: execute called functions
conversations.append(result)

tool_call = result['tool_calls'][0]
func_name = tool_call['function']['name']
func = mapping[func_name]
arguments = json.loads(tool_call['function']['arguments'])
called_result = func(**arguments)

# stage 3: put executed results
conversations.append(
    {
        'role': 'tool',
        'tool_call_id': tool_call['id'],
        'name': func_name,
        'content': json.dumps(called_result)
    }
)

prompt = prompt_engine.get_prompt(conversations, functions=functions)

output_str2 = _inference(prompt, llm, params)
result2 = prompt_engine.parse_generated_str(output_str2)
print(result2)
# {'role': 'assistant', 'content': '台北目前的溫度是攝氏30度。'}
```