Pinned issues
Issues
- 0
【您好,请求帮助】魔搭下载的qwen1_5-14b-chat-q2_k.gguf 使用llama.cpp中的./server部署运行后,对话或者postman接口访问服务偶尔不返回生成结果。
#432 opened by hanshishang - 0
MOD训练的模型能否用vllm推理
#431 opened by LiuChen19960902 - 2
有没有function_call的功能实现啊?
#428 opened by ucasiggcas - 1
qwen1.5 fail load lora
#417 opened by kynow2 - 0
【求助】关于算法备案的问题
#430 opened by bh4ffu - 1
我无法按照常规文本格式提供超过2048字符的详细回复
#429 opened by wwjCMP - 0
Qwen1.5 应用 langchain agent 问题
#426 opened by bzr1 - 2
多轮对话训练数据格式问题
#427 opened by yangxin60-tal - 3
请问作者有尝试过neftune实验吗?
#418 opened by fanbooo - 1
- 2
32B-AWQ预测慢而且输出乱码
#421 opened by wingjson - 1
💡 [REQUEST] - qwen1.5 110b能提供一个8bit量化的版本么
#383 opened by starsliao - 5
swift微调qwen1.5-32b,然后用autoawq量化,用vllm部署有时会出现感叹号
#381 opened by CNXDZS - 1
[BUG] <ModuleNotFoundError: No module named 'transformers_modules.Qwen1'>
#384 opened by sugarandgugu - 1
多机多卡训练配置问题
#386 opened by summerrain321 - 2
💡 [REQUEST] - <有没有vLLM 部署Qwen1.5-110b-chat版本的?>
#392 opened by ucas010 - 1
AWQ 模型的精度和使用
#401 opened by chenchunhui97 - 1
关于device_map
#402 opened by Tvrco - 2
为什么同样的脚本(Qwen1.5/examples/web_demo.py)去执行Qwen1.5-32B-Chat-GPTQ-Int4的推理时,4090 24G 比 V100 32G 回答速度快了5倍,这是什么原因,是显卡性能的问题,还是代码还有哪个配置没有打开,导致V100的计算能力没有发挥出来?
#405 opened by lbl1120 - 4
Qwen1.5-7B-Chat推理,结果不一致
#409 opened by yecphaha - 1
Readme inconsistent with small model licences
#411 opened by ozppupbg - 3
RuntimeError: Failed to import transformers.models.qwen2.modeling_qwen2 because of the following error (look up to see its traceback): Failed to import transformers.integrations.peft because of the following error (look up to see its traceback): No module named 'torch.distributed.checkpoint.format_utils'
#413 opened by imrankh46 - 1
why the base model can chat?
#419 opened by smallflyingpig - 1
Qwen-7B量化4bit的预测结果问题
#420 opened by yecphaha - 1
💡 [REQUEST] - <title> finetuning data format question
#424 opened by lzl-mt - 3
是否可提供与model.py类似的模型原代码
#422 opened by WzjCoder - 0
- 1
求问Dify模型配置参数
#415 opened by wencan - 0
4B的alpacaeval leaderboard分数
#414 opened by LiuChen19960902 - 1
why padding_side right?
#416 opened by smallflyingpig - 1
unlimited output,vllm 0.4.0 post ,0.5b-chat
#410 opened by Jun-Howie - 1
14b模型为啥总偷懒?
#412 opened by bwb0101 - 1
- 2
- 2
how to reproduce QWEN1.5-7B-CHAT results
#382 opened by chunniunai220ml - 1
Ollama库中,不同的标签后缀含义是什么?
#403 opened by RuikangSun - 1
- 5
- 1
- 1
qwen1 和 qwen1.5 finetune脚本为什么数据预处理会不一样?
#391 opened by spider-man-jiaye - 1
qwen1.5的sft数据处理部分使用了预训练的数据处理方式
#396 opened by bjr-yql - 0
A question about the structure of the model
#397 opened by WzjCoder - 5
用2080TI 22G单张显卡跑 qwen 1.5 32B-INT4模型没有成功
#389 opened by zhuyang2356 - 0
LlamaIndex能否直接使用modelscode下载的千问模型进行RAG检索?
#395 opened by BigFishDreamWater - 4
Qwen的代码开源了吗?
#393 opened by WzjCoder - 4
ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length. Perhaps your features (`labels` in this case) have excessive nesting (inputs type `list` where type `int` is expected).
#388 opened by sjlmg - 1
Not able to setup Qwen1.5-72B-Chat with Taskweaver
#390 opened by Haxeebraja - 6
Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4 demo encount: RuntimeError: CUDA error: invalid configuration argument
#385 opened by MasterYi1024 - 1
How to batch inference for lora
#380 opened by may012345 - 1
vllm本地部署Qwen1.5-72B-chat,在一次性生成长文本的任务中,出现超出字数限制的提示
#387 opened by JSLW