Search results

qwenvl中的past_key_values如何用来跑自回归。

Status: Open.

#503 In QwenLM/Qwen-VL;

· 12liurunze opened on Mar 13, 2025

【求助】qwen2.5-vl模型基于目标检测的lora微调,数据集格式以这种形式可行吗

Status: Open.

#502 In QwenLM/Qwen-VL;

· cllz56442 opened on Mar 11, 2025

运行web_demo_mm.py出现Loading checkpoint shards进度0%后退出

Status: Open.

#501 In QwenLM/Qwen-VL;

· zzccctv opened on Feb 17, 2025

Extending OCR Model Support for Additional Languages: Fine-tuning or Alternative Solutions?"

Status: Open.

#499 In QwenLM/Qwen-VL;

· parth1313 opened on Jan 31, 2025

[BUG] <title>在使用Qwen-VL，在同一个prompt提出两个问题，只能回答第一个

Status: Open.

#498 In QwenLM/Qwen-VL;

· stillbetter opened on Jan 27, 2025

[BUG] <title>

Status: Open.

#497 In QwenLM/Qwen-VL;

· charlie2728 opened on Jan 27, 2025

[BUG] transformers的版本无法用于finetune

Status: Open.

#495 In QwenLM/Qwen-VL;

· estuday opened on Dec 17, 2024

We detect you are probably using the pretrained model (rather than chat model) for chatting, since the chat_format in generation_config is not "chatml". If you are directly using the model downloaded from Huggingface, please make sure you are using our "Qwen/Qwen-7B-Chat" Huggingface model (rather than "Qwen/Qwen-7B") when you call model.chat()

Status: Open.

#493 In QwenLM/Qwen-VL;

· snowattitude opened on Dec 3, 2024

【求助】finetune支持对qwen2-vl的微调吗？

Status: Open.

#492 In QwenLM/Qwen-VL;

· Rxma1805 opened on Nov 25, 2024

[BUG] {'use_reentrant': True} results in "Gradients will be None"

Status: Open.

#490 In QwenLM/Qwen-VL;

· RonanKMcGovern opened on Nov 20, 2024

[求助] <title> qwen-vl-chat-int4量化后的模型并不能参与合并，但是lora后的模型却要怎么拿来推理呢？

Status: Open.

#489 In QwenLM/Qwen-VL;

· AuTingU opened on Nov 15, 2024

[BUG] <Response from Qwen-VL very short>

Status: Open.

#488 In QwenLM/Qwen-VL;

· zifuwan opened on Nov 14, 2024