Files

ModelHub XC fc73bec338 初始化项目，由ModelHub XC社区提供模型

Model: okwinds/Qwen3-14B-Int4-W4A16
Source: Original Platform

2026-10-20 01:04:16 +08:00

19 KiB

Raw Permalink Blame History

frameworks, library_name, license, license_link, pipeline_tag, base_model, language, tags, tools, tasks, base_model_relation

frameworks

library_name

license

license_link

pipeline_tag

base_model

language

重要：友情提醒，推理本模型时，请按照如下官方指引：

对于思考模式（enable_thinking=True，默认为 True）

请使用 Temperature=0.6 、 TopP=0.95 、 TopK=20 和 MinP=0 （ generation_config.json 中的默认设置）。请勿使用贪婪解码（greedy decoding），因为它可能导致性能下降和无限循环。如需更详细的指导，请参阅最佳实践部分。

对于非思考模式（enable_thinking=False）

建议使用 Temperature=0.7 、 TopP=0.8 、 TopK=20 和 MinP=0 。如需更详细的指导，请参阅最佳实践部分。

📖 关于量化损失方面的研究，可阅读公众号“觉察流”文章👇

《Reason Model 的“瘦身计划”：量化技术的得与失》

通义千问 Qwen3-14B-Int4-W4A16 量化高精校准

原模型 qwen/Qwen3-14B

作者在此 👇🏻 扫一扫

下载

SDK下载

#安装ModelScope
pip install modelscope

#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('okwinds/Qwen3-14B-Int4-W4A16')

Git下载

#Git模型下载
git clone https://www.modelscope.cn/okwinds/Qwen3-14B-Int4-W4A16.git

模型概述

Qwen3-14B-Int4-W4A16 是一个基于通义千问 Qwen3-14B 的 INT4 量化并校准的模型。

模型名称: Qwen3-14B-Int4-W4A16
模型架构: Qwen3
权重量化: INT4

该模型通过将 qwen/Qwen3-14B 的权重量化为 INT4 数据类型而实现。

量化过程将每个参数从 16bit 减少到 4bit，将模型占用磁盘空间大小，以及推理时加载模型需要的GPU显存空间，减少到了大约为原模型的1/4。只有 transformer 中的 Linear 层权重是量化的，其他层均保持为原模型数据类型，采用了混合精度的计算方式，尽可能减少模型量化后所带来的精度损失。

量化本模型，使用了AutoGPTQ，采用 Symmetric group-wise 方式量化（group size : 128）。并在量化过程中，进行了数据校准，以提升模型生成精度。

注意：本模型需要 compute capability > 8.0（Ampere、Ada Lovelace、Hopper 架构）的 Nvidia GPU 来支持 INT4 混合精度计算。

部署推理

附录 Qwen3-14B 介绍

Qwen3 Highlights

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:

Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.

Model Overview

Qwen3-14B has the following features:

Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 14.8B
Number of Paramaters (Non-Embedding): 13.2B
Number of Layers: 40
Number of Attention Heads (GQA): 40 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.

Quickstart

The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers.

With transformers<4.51.0, you will encounter the following error:

KeyError: 'qwen3'

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen3-14B"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

For deployment, you can use sglang>=0.4.6.post1 or vllm>=0.8.4 or to create an OpenAI-compatible API endpoint:

SGLang:

python -m sglang.launch_server --model-path Qwen/Qwen3-14B --reasoning-parser qwen3

vLLM:

vllm serve Qwen/Qwen3-14B --enable-reasoning --reasoning-parser deepseek_r1

For local use, applications such as llama.cpp, Ollama, LMStudio, and MLX-LM have also supported Qwen3.

Switching Between Thinking and Non-Thinking Mode

Tip

The enable_thinking switch is also available in APIs created by SGLang and vLLM. Please refer to our documentation for SGLang and vLLM users.

`enable_thinking=True`

By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting enable_thinking=True or leaving it as the default value in tokenizer.apply_chat_template, the model will engage its thinking mode.

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True  # True is the default value for enable_thinking
)

In this mode, the model will generate think content wrapped in a <think>...</think> block, followed by the final response.

Note

For thinking mode, use Temperature=0.6, TopP=0.95, TopK=20, and MinP=0 (the default setting in generation_config.json). DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the Best Practices section.

`enable_thinking=False`

We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False  # Setting enable_thinking=False disables thinking mode
)

In this mode, the model will not generate any think content and will not include a <think>...</think> block.

Note

For non-thinking mode, we suggest using Temperature=0.7, TopP=0.8, TopK=20, and MinP=0. For more detailed guidance, please refer to the Best Practices section.

Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input

We provide a soft switch mechanism that allows users to dynamically control the model's behavior when enable_thinking=True. Specifically, you can add /think and /no_think to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.

Here is an example of a multi-turn conversation:

from transformers import AutoModelForCausalLM, AutoTokenizer

class QwenChatbot:
    def __init__(self, model_name="Qwen/Qwen3-14B"):
        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
        self.model = AutoModelForCausalLM.from_pretrained(model_name)
        self.history = []

    def generate_response(self, user_input):
        messages = self.history + [{"role": "user", "content": user_input}]

        text = self.tokenizer.apply_chat_template(
            messages,
            tokenize=False,
            add_generation_prompt=True
        )

        inputs = self.tokenizer(text, return_tensors="pt")
        response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
        response = self.tokenizer.decode(response_ids, skip_special_tokens=True)

        # Update history
        self.history.append({"role": "user", "content": user_input})
        self.history.append({"role": "assistant", "content": response})

        return response

# Example Usage
if __name__ == "__main__":
    chatbot = QwenChatbot()

    # First input (without /think or /no_think tags, thinking mode is enabled by default)
    user_input_1 = "How many r's in strawberries?"
    print(f"User: {user_input_1}")
    response_1 = chatbot.generate_response(user_input_1)
    print(f"Bot: {response_1}")
    print("----------------------")

    # Second input with /no_think
    user_input_2 = "Then, how many r's in blueberries? /no_think"
    print(f"User: {user_input_2}")
    response_2 = chatbot.generate_response(user_input_2)
    print(f"Bot: {response_2}") 
    print("----------------------")

    # Third input with /think
    user_input_3 = "Really? /think"
    print(f"User: {user_input_3}")
    response_3 = chatbot.generate_response(user_input_3)
    print(f"Bot: {response_3}")

Note

For API compatibility, when enable_thinking=True, regardless of whether the user uses /think or /no_think, the model will always output a block wrapped in <think>...</think>. However, the content inside this block may be empty if thinking is disabled. When enable_thinking=False, the soft switches are not valid. Regardless of any /think or /no_think tags input by the user, the model will not generate think content and will not include a <think>...</think> block.

Agentic Use

Qwen3 excels in tool calling capabilities. We recommend using Qwen-Agent to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.

To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.

from qwen_agent.agents import Assistant

# Define LLM
llm_cfg = {
    'model': 'Qwen3-14B',

    # Use the endpoint provided by Alibaba Model Studio:
    # 'model_type': 'qwen_dashscope',
    # 'api_key': os.getenv('DASHSCOPE_API_KEY'),

    # Use a custom endpoint compatible with OpenAI API:
    'model_server': 'http://localhost:8000/v1',  # api_base
    'api_key': 'EMPTY',

    # Other parameters:
    # 'generate_cfg': {
    #         # Add: When the response content is `<think>this is the thought</think>this is the answer;
    #         # Do not add: When the response has been separated by reasoning_content and content.
    #         'thought_in_content': True,
    #     },
}

# Define Tools
tools = [
    {'mcpServers': {  # You can specify the MCP configuration file
            'time': {
                'command': 'uvx',
                'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
            },
            "fetch": {
                "command": "uvx",
                "args": ["mcp-server-fetch"]
            }
        }
    },
  'code_interpreter',  # Built-in tools
]

# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)

# Streaming generation
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
for responses in bot.run(messages=messages):
    pass
print(responses)

Processing Long Texts

Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the YaRN method.

YaRN is currently supported by several inference frameworks, e.g., transformers and llama.cpp for local use, vllm and sglang for deployment. In general, there are two approaches to enabling YaRN for supported frameworks:

Modifying the model files: In the config.json file, add the rope_scaling fields:

{
    ...,
    "rope_scaling": {
        "type": "yarn",
        "factor": 4.0,
        "original_max_position_embeddings": 32768
    }
}

For llama.cpp, you need to regenerate the GGUF file after the modification.

Passing command line arguments:

For vllm, you can use

vllm serve ... --rope-scaling '{"type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072

For sglang, you can use

python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"type":"yarn","factor":4.0,"original_max_position_embeddings":32768}}'

For llama-server from llama.cpp, you can use

llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768

Important

If you encounter the following warning
Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'original_max_position_embeddings'}
please upgrade transformers>=4.51.0.

Note

All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts. We advise adding the rope_scaling configuration only when processing long contexts is required. It is also recommended to modify the factor as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set factor as 2.0.

Note

The default max_position_embeddings in config.json is set to 40,960. This allocation includes reserving 32,768 tokens for outputs and 8,192 tokens for typical prompts, which is sufficient for most scenarios involving short text processing. If the average context length does not exceed 32,768 tokens, we do not recommend enabling YaRN in this scenario, as it may potentially degrade model performance.

Tip

The endpoint provided by Alibaba Model Studio supports dynamic YaRN by default and no extra configuration is needed.

Best Practices

To achieve optimal performance, we recommend the following settings:

Sampling Parameters:
- For thinking mode (enable_thinking=True), use Temperature=0.6, TopP=0.95, TopK=20, and MinP=0. DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions.
- For non-thinking mode (enable_thinking=False), we suggest using Temperature=0.7, TopP=0.8, TopK=20, and MinP=0.
- For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
Adequate Output Length: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking.
- Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
- Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the answer field with only the choice letter, e.g., "answer": "C"."
No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3,
    title  = {Qwen3},
    url    = {https://qwenlm.github.io/blog/qwen3/},
    author = {Qwen Team},
    month  = {April},
    year   = {2025}
}

19 KiB Raw Permalink Blame History Unescape Escape