--- license: apache-2.0 base_model: - Qwen/Qwen3-235B-A22B-Thinking-2507 --- ## Model Details This model is a mixed guff q2km model of [Qwen/Qwen3-235B-A22B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507) generated by [intel/auto-round](https://github.com/intel/auto-round). Embedding layer and lm-head layer are fallback to 8 bits and non expert layers are fallback to 4 bits. Please refer to Section `Generate the model` for more details. Please follow the license of the original model. ## How To Use ### LLamacpp Inference ~~~bash ./llama-cli -hf Intel/Qwen3-235B-A22B-Thinking-2507-gguf-q2ks-mixed-AutoRound:q2_k_s --conversation ~~~ ~~~bash > 9.8大还是9.11大 首先,用户的问题是:“9.8大还是9.11大”,这看起来是在比较两个数字:9.8 和 9.11。 我需要理解这些数字的含义。9.8 可能指的是 9.8,而 9.11 可能指的是 9.11。在十进制中,9.8 表示 9 + 8/10 = 9.8,而 9.11 表示 9 + 11/100 = 9.11。 现在,比较 9.8 和 9.11: - 9.8 = 9.80(为了便于比较,可以写成 9.80) - 9.11 = 9.11 所以,9.80 与 9.11 比较。 9.80 是 9.8,相当于 98/10 = 9.8 9.11 是 9.11,相当于 911/100 = 9.11 为了比较,可以将它们转换为相同的小数位数。 9.8 = 9.80 9.11 = 9.11 现在,9.80 大于 9.11,因为 80/100 > 11/100。 9.8 - 9.11 = 0.69,所以 9.8 大于 9.11。 用户可能是在问日期,比如 9月8日 vs 9月11日,但问题中写的是“9.8”和“9.11”,在中文中,点通常表示小数点,而不是日期分隔符。日期通常用斜杠或连字符,如 9/8 或 9-8。 在中文上下文中,“9.8” 可能被误解为日期,但标准表示法中,日期通常不会用点分隔。例如,9月8日常写成“9/8”或“9月8日”。 问题中是“9.8”和“9.11”,点更像是小数点。 此外,用户说“大还是”,意思是“哪个大”,所以很可能是在比较数值大小。 另一个可能性:9.8 可能指代某个事件,如 9.8地震,但9.8地震通常指2008年5月12日汶川地震,震级为8.0,但这里写的是9.8,可能不准确。9.11 可能指9/11事件。 但问题直接说“9.8大还是9.11大”,没有上下文,所以可能只是简单的数值比较。 在数值上,9.8 > 9.11。 确认: 9.8 = 9.8 9.11 = 9.11 9.8 - 9.11 = 0.69 > 0, 所以 9.8 > 9.11. 如果用户意指日期,9月8日 vs 9月11日,那么9月11日在9月8日之后,所以9月11日更大,但日期比较通常不是“大”的意思,而是时间顺序。 但问题说“大”,在中文中“大”可以指尺寸、大小或数值大小。 在数值上下文中,9.8 更大。 或许是版本号,如软件版本9.8 vs 9.11,但9.11版本可能不存在,通常版本号是9.10、9.11等,但9.8和9.11,9.11可能比9.8新,但版本号比较不是简单的数值,因为9.11可能表示9.1.1,但这里写的是9.11,可能直接比较。 但问题没有指定上下文,所以最直接的解释是数值比较。 另一个想法:9.8 可能指9.8%,但同样,数值上9.8% vs 9.11%,9.8 > 9.11。 9.8% = 0.098, 9.11% = 0.0911, 0.098 > 0.0911, 所以9.8% > 9.11%。 但问题中没有百分号,所以可能只是数字。 我认为最合理的解释是用户想比较数字9.8和9.11的大小。 因此,9.8 大于 9.11。 所以,回答应该是9.8大。 为了完整,可以说:9.8 大于 9.11。 在中文中:"9.8大"。 用户的问题是“9.8大还是9.11大”,所以回答可以是“9.8大”。 或者解释一下。 既然用户可能混淆,可以澄清。 但作为AI,应该给出正确答案。 最终答案:9.8 大。 在数值比较中,**9.8 大于 9.11**。以下是详细解释: ### 为什么 9.8 更大? - **9.8** 表示 9.8(即 9 + 8/10 = 9.8)。 - **9.11** 表示 9.11(即 9 + 11/100 = 9.11)。 - 将两者转换为相同小数位数以便比较: - 9.8 = 9.80 - 9.11 = 9.11 - 比较小数部分:80/100(0.80) > 11/100(0.11),因此 9.80 > 9.11。 - 计算差值:9.8 - 9.11 = 0.69 > 0,这进一步证明 9.8 更大。 ### 其他可能的误解 - **如果是日期比较(如 9月8日 vs 9月11日)**: 在日期上下文中,“9.8”通常指 9月8日,“9.11”指 9月11日。9月11日比9月8日晚(即时间顺序上更大),但问题中的“大”一般指**数值大小**而非时间先后。数值比较仍是 9.8 > 9.11。 - **如果是事件代号(如 9.8地震 vs 9.11事件)**: - “9.8”可能指2008年5月12日汶川地震(实际震级为8.0,但有时被误称为9.8)。 - “9.11”通常指2001年9月11日美国恐怖袭击事件。 但事件本身无法直接比较“大小”,问题更可能是在问**数值**。如果指事件影响力,9.11事件全球影响更大,但问题表述更倾向于数值比较。 ### 结论 **9.8 大**。 如果您的问题有特定背景(如日期、事件或版本号),请提供更多细节,我可以进一步解释! ~~~ ### Generate the model auto-round>0.5.1 ~~~python import torch from transformers import AutoModelForCausalLM, AutoTokenizer from auto_round import AutoRound model_name = "Qwen/Qwen3-235B-A22B-Thinking-2507" model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cpu", torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(model_name) layer_config = {} for n, m in model.named_modules(): if n == "lm_head" or isinstance(m, torch.nn.Embedding): layer_config[n] = {"bits": 8} elif isinstance(m, torch.nn.Linear) and (not "expert" in n or "shared_experts" in n) and n != "lm_head": layer_config[n] = {"bits": 4} autoround = AutoRound(model, tokenizer, iters=0, nsamples=512,layer_config=layer_config) autoround.quantize_and_save("./Qwen3-235B-A22B-Thinking-2507-q2ks", format="gguf:q2_k_s") ~~~ ## Ethical Considerations and Limitations The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs. Therefore, before deploying any applications of the model, developers should perform safety testing. ## Caveats and Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Here are a couple of useful links to learn more about Intel's AI software: - Intel Neural Compressor [link](https://github.com/intel/neural-compressor) ## Disclaimer The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes. ## Cite @article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} } [arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)