🚀 Llama3.1-Typhoon2-8B

Llama3.1-Typhoon2-8B是一个泰语大语言模型（指令型），基于Transformer架构，能够处理多种语言任务，为用户提供高效准确的语言交互服务。

🚀 快速开始

本模型的使用需要transformers 4.45.0或更新的版本。以下是使用该模型的示例代码：

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "scb10x/llama3.1-typhoon2-8b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a male AI assistant named Typhoon created by SCB 10X to be helpful, harmless, and honest. Typhoon is happy to help with analysis, question answering, math, coding, creative writing, teaching, role-play, general discussion, and all sorts of other tasks. Typhoon responds directly to all human messages without unnecessary affirmations or filler phrases like “Certainly!”, “Of course!”, “Absolutely!”, “Great!”, “Sure!”, etc. Specifically, Typhoon avoids starting responses with the word “Certainly” in any way. Typhoon follows this information in all languages, and always responds to the user in the language they use or request. Typhoon is now being connected with a human. Write in fluid, conversational prose, Show genuine interest in understanding requests, Express appropriate emotions and empathy. Also showing information in term that is easy to understand and visualized."},
    {"role": "user", "content": "ขอสูตรไก่ย่าง"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

✨ 主要特性

性能表现出色

• 指令遵循和函数调用性能：通过可视化图表展示了在相关任务上的优秀表现。
• 特定领域性能（数学和编码）：在数学和编码等特定领域有良好的表现。
• 长上下文性能：能够处理较长的上下文输入。
• 详细性能指标：通过表格对比了不同模型在多个指标上的表现。 | 模型 | IFEval - TH | IFEval - EN | MT - Bench TH | MT - Bench EN | 泰语代码切换(t = 0.7) | 泰语代码切换(t = 1.0) | 函数调用 - TH | 函数调用 - EN | GSM8K - TH | GSM8K - EN | MATH - TH | MATH - EN | HumanEval - TH | HumanEval - EN | MBPP - TH | MBPP - EN | |-------------------------------|-------------|-------------|---------------|---------------|------------------------|------------------------|---------------|---------------|-------------|-------------|-------------|-------------|---------------|---------------|-------------|-------------| | Llama3.1 8B Instruct | 58.04% | 77.64% | 5.109 | 8.118 | 93% | 11.2% | 36.92% | 66.06% | 45.18% | 62.4% | 24.42% | 48% | 51.8% | 67.7% | 64.6% | 66.9% | | Typhoon2 Llama3 8B Instruct| 72.60% | 76.43% | 5.7417 | 7.584 | 98.8% | 98% | 75.12% | 79.08% | 71.72% | 81.0% | 38.48% | 49.04% | 58.5% | 68.9% | 60.8% | 63.0% |

模型特性丰富

• 模型类型：基于Llama架构的80亿参数指令型仅解码器模型。
• 环境要求：需要transformers 4.45.0或更新版本。
• 上下文长度：支持90k的上下文长度。
• 主要语言：泰语和英语。
• 许可证：[Llama 3.1社区许可证](https://github.com/meta - llama/llama - models/blob/main/models/llama3_1/LICENSE)

📦 安装指南

如果你想使用推理服务器托管该模型，可以按照以下步骤进行安装：

pip install vllm
vllm serve scb10x/llama3.1-typhoon2-8b-instruct
# 更多信息请参考 https://docs.vllm.ai/

💻 使用示例

基础用法

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "scb10x/llama3.1-typhoon2-8b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a male AI assistant named Typhoon created by SCB 10X to be helpful, harmless, and honest. Typhoon is happy to help with analysis, question answering, math, coding, creative writing, teaching, role-play, general discussion, and all sorts of other tasks. Typhoon responds directly to all human messages without unnecessary affirmations or filler phrases like “Certainly!”, “Of course!”, “Absolutely!”, “Great!”, “Sure!”, etc. Specifically, Typhoon avoids starting responses with the word “Certainly” in any way. Typhoon follows this information in all languages, and always responds to the user in the language they use or request. Typhoon is now being connected with a human. Write in fluid, conversational prose, Show genuine interest in understanding requests, Express appropriate emotions and empathy. Also showing information in term that is easy to understand and visualized."},
    {"role": "user", "content": "ขอสูตรไก่ย่าง"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

高级用法（函数调用示例）

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
import ast
model_name = "scb10x/llama3.1-typhoon2-8b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, torch_dtype=torch.bfloat16, device_map='auto'
)

get_weather_api = {
    "name": "get_weather",
    "description": "Get the current weather for a location",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, New York",
            },
            "unit": {
                "type": "string",
                "enum": ["celsius", "fahrenheit"],
                "description": "The unit of temperature to return",
            },
        },
        "required": ["location"],
    },
}


search_api = {
    "name": "search",
    "description": "Search for information on the internet",
    "parameters": {
        "type": "object",
        "properties": {
            "query": {
                "type": "string",
                "description": "The search query, e.g. 'latest news on AI'",
            }
        },
        "required": ["query"],
    },
}

get_stock = {
    "name": "get_stock_price",
    "description": "Get the stock price",
    "parameters": {
        "type": "object",
        "properties": {
            "symbol": {
                "type": "string",
                "description": "The stock symbol, e.g. AAPL, GOOG",
            }
        },
        "required": ["symbol"],
    },
}
# Tool input are same format with OpenAI tools
openai_format_tools = [get_weather_api, search_api, get_stock]

messages = [
    {"role": "system", "content": "You are an expert in composing functions."},
    {"role": "user", "content": "ขอราคาหุ้น Tasla (TLS) และ Amazon (AMZ) ?"},
]

inputs = tokenizer.apply_chat_template(
    messages, tools=openai_format_tools, add_generation_prompt=True, return_tensors="pt"
).to(model.device)

outputs = model.generate(
    inputs,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    num_return_sequences=1,
    eos_token_id=[tokenizer.eos_token_id, 128009],
)
response = outputs[0][inputs.shape[-1]:]

print("Here Output:", tokenizer.decode(response, skip_special_tokens=True))


# Decoding function utility
def resolve_ast_by_type(value):
    if isinstance(value, ast.Constant):
        if value.value is Ellipsis:
            output = "..."
        else:
            output = value.value
    elif isinstance(value, ast.UnaryOp):
        output = -value.operand.value
    elif isinstance(value, ast.List):
        output = [resolve_ast_by_type(v) for v in value.elts]
    elif isinstance(value, ast.Dict):
        output = {
            resolve_ast_by_type(k): resolve_ast_by_type(v)
            for k, v in zip(value.keys, value.values)
        }
    elif isinstance(
        value, ast.NameConstant
    ):  # Added this condition to handle boolean values
        output = value.value
    elif isinstance(
        value, ast.BinOp
    ):  # Added this condition to handle function calls as arguments
        output = eval(ast.unparse(value))
    elif isinstance(value, ast.Name):
        output = value.id
    elif isinstance(value, ast.Call):
        if len(value.keywords) == 0:
            output = ast.unparse(value)
        else:
            output = resolve_ast_call(value)
    elif isinstance(value, ast.Tuple):
        output = tuple(resolve_ast_by_type(v) for v in value.elts)
    elif isinstance(value, ast.Lambda):
        output = eval(ast.unparse(value.body[0].value))
    elif isinstance(value, ast.Ellipsis):
        output = "..."
    elif isinstance(value, ast.Subscript):
        try:
            output = ast.unparse(value.body[0].value)
        except:
            output = ast.unparse(value.value) + "[" + ast.unparse(value.slice) + "]"
    else:
        raise Exception(f"Unsupported AST type: {type(value)}")
    return output


def resolve_ast_call(elem):
    func_parts = []
    func_part = elem.func
    while isinstance(func_part, ast.Attribute):
        func_parts.append(func_part.attr)
        func_part = func_part.value
    if isinstance(func_part, ast.Name):
        func_parts.append(func_part.id)
    func_name = ".".join(reversed(func_parts))
    args_dict = {}
    for arg in elem.keywords:
        output = resolve_ast_by_type(arg.value)
        args_dict[arg.arg] = output
    return {func_name: args_dict}


def ast_parse(input_str, language="Python"):
    if language == "Python":
        cleaned_input = input_str.strip("[]'")
        parsed = ast.parse(cleaned_input, mode="eval")
        extracted = []
        if isinstance(parsed.body, ast.Call):
            extracted.append(resolve_ast_call(parsed.body))
        else:
            for elem in parsed.body.elts:
                assert isinstance(elem, ast.Call)
                extracted.append(resolve_ast_call(elem))
        return extracted
    else:
        raise NotImplementedError(f"Unsupported language: {language}")


def parse_nested_value(value):
    """
    Parse a potentially nested value from the AST output.

    Args:
        value: The value to parse, which could be a nested dictionary, which includes another function call, or a simple value.

    Returns:
        str: A string representation of the value, handling nested function calls and nested dictionary function arguments.
    """
    if isinstance(value, dict):
        # Check if the dictionary represents a function call (i.e., the value is another dictionary or complex structure)
        if all(isinstance(v, dict) for v in value.values()):
            func_name = list(value.keys())[0]
            args = value[func_name]
            args_str = ", ".join(
                f"{k}={parse_nested_value(v)}" for k, v in args.items()
            )
            return f"{func_name}({args_str})"
        else:
            # If it's a simple dictionary, treat it as key-value pairs
            return (
                "{"
                + ", ".join(f"'{k}': {parse_nested_value(v)}" for k, v in value.items())
                + "}"
            )
    return repr(value)

def default_decode_ast_prompting(result, language="Python"):
    result = result.strip("`\n ")
    if not result.startswith("["):
        result = "[" + result
    if not result.endswith("]"):
        result = result + "]"
    decoded_output = ast_parse(result, language)
    return decoded_output


fc_result = default_decode_ast_prompting(tokenizer.decode(response, skip_special_tokens=True))
print(fc_result) # [{'Function': {'arguments': '{"symbol": "TLS"}', 'name': 'get_stock_price'}}, {'Function': {'arguments': '{"symbol": "AMZ"}', 'name': 'get_stock_price'}}]

📚 详细文档

预期用途和限制

本模型是一个指令型模型，但仍在开发中。它包含了一定程度的防护机制，但在响应用户提示时，仍可能产生不准确、有偏见或其他令人反感的答案。我们建议开发者在其使用场景中评估这些风险。

关注我们

• Twitter：https://twitter.com/opentyphoon

支持社区

• Discord：https://discord.gg/us5gAYmrxw

引用方式

如果你发现Typhoon2对你的工作有帮助，请使用以下方式引用：

@misc{typhoon2,
      title={Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models}, 
      author={Kunat Pipatanakul and Potsawee Manakul and Natapong Nitarach and Warit Sirichotedumrong and Surapon Nonesung and Teetouch Jaknamon and Parinthapat Pengpun and Pittawat Taveekitworachai and Adisai Na-Thalang and Sittipong Sripaisarnmongkol and Krisanapong Jirayoot and Kasima Tharnpipitchai},
      year={2024},
      eprint={2412.13702},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.13702}, 
}

📄 许可证

本模型遵循[Llama 3.1社区许可证](https://github.com/meta - llama/llama - models/blob/main/models/llama3_1/LICENSE)。