Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / THUDM/CogVLM issues and pull requests
#98 - May I finetune CogVLM using chinese dataset?请问目前可以支持中文数据微调吗?
Issue -
State: closed - Opened by LianghuiGuo 10 months ago
- 1 comment
#97 - How to add Chain of Thought prompt?
Issue -
State: closed - Opened by superaha 10 months ago
- 3 comments
#96 - nan in logits
Issue -
State: closed - Opened by haoboluo 10 months ago
- 4 comments
#95 - Web demo Timeout
Issue -
State: closed - Opened by JiaweiMorris 10 months ago
- 1 comment
#94 - Newbranch
Pull Request -
State: closed - Opened by luiswenus 10 months ago
#93 - Can CogVLM accept interleaved images and texts (multiple images) as input?
Issue -
State: closed - Opened by McCarrtney 10 months ago
- 5 comments
#92 - multi gpu CLI 推理错误
Issue -
State: closed - Opened by liuzhx2016 10 months ago
- 2 comments
#91 - [Request] Code for batch inference
Issue -
State: closed - Opened by g-h-chen 10 months ago
- 1 comment
#90 - How could I fixed this error? Thanks!
Issue -
State: closed - Opened by zetaodu 10 months ago
- 4 comments
#89 - Fine Tuning Issue with scripts/finetune_224_lora.sh
Issue -
State: closed - Opened by signalprime 11 months ago
- 2 comments
#88 - Specific task
Issue -
State: closed - Opened by Haonote 11 months ago
- 2 comments
#87 - 有没有方案提升infer的速度
Issue -
State: closed - Opened by pf67 11 months ago
- 3 comments
#86 - Any plan to train CogVLM based on a larger text model?
Issue -
State: closed - Opened by rfan-debug 11 months ago
- 3 comments
#85 - Request for CPU option inference
Issue -
State: closed - Opened by rusuanjun007 11 months ago
- 4 comments
#84 - Create a demo on Hugging Face Hub
Issue -
State: closed - Opened by adeenayakup 11 months ago
- 15 comments
#83 - Update web_demo.py
Pull Request -
State: closed - Opened by eltociear 11 months ago
#82 - Error running web_demo.py AttributeError: 'Chatbot' object has no attribute 'style'. Did you mean: 'scale'?
Issue -
State: closed - Opened by lxe 11 months ago
- 1 comment
#81 - Eva CLIP model: trained or freezed?
Issue -
State: closed - Opened by shkarupa-alex 11 months ago
- 3 comments
#80 - Did you do experiment on Flickr30k entities? what should I do if I need model ground all noun phrase of visible entities existing in certain sentence rather than just ground one.
Issue -
State: closed - Opened by zetaodu 11 months ago
- 1 comment
#79 - High Resolution
Issue -
State: closed - Opened by excellent-ai 11 months ago
- 2 comments
#78 - interrupt when download the sat model
Issue -
State: closed - Opened by CarolXh 11 months ago
- 1 comment
#77 - 有类似visualglm-6b那样提供api调用的代码吗
Issue -
State: closed - Opened by cdqncn 11 months ago
- 2 comments
#76 - Do you have a plan to open source your scripts which evaluate on several image-text benchmarks?
Issue -
State: closed - Opened by miznchimaki 11 months ago
- 1 comment
#75 - Fast captioning
Issue -
State: closed - Opened by rahimentezari 11 months ago
- 5 comments
#74 - Similarity between Image and Text
Issue -
State: closed - Opened by mxllc 11 months ago
- 2 comments
#73 - 请问中文版有计划开源吗?谢谢~
Issue -
State: closed - Opened by LianghuiGuo 11 months ago
- 1 comment
#72 - The process stops without any further prompt
Issue -
State: closed - Opened by eric4note 11 months ago
- 7 comments
#71 - Please make the code backward compatible with lower versions of PyTorch==2.0.1
Issue -
State: closed - Opened by ZetangForward 11 months ago
- 3 comments
#70 - 运行官方demo报错。提示AttributeError: module 'flash_attn' has no attribute '__version__'
Issue -
State: closed - Opened by shikimoon 11 months ago
- 1 comment
#69 - CLI模式报错
Issue -
State: closed - Opened by jyC23333 11 months ago
- 8 comments
#68 - how to set 'MP_SIZE' ?
Issue -
State: closed - Opened by microhu 11 months ago
- 3 comments
#67 - CUDA error: the launch timed out and was terminated
Issue -
State: closed - Opened by hxgqh 11 months ago
- 2 comments
#66 - How to reproduce Textvqa(val) score- 68.1
Issue -
State: closed - Opened by Cuiunbo 11 months ago
- 7 comments
#65 - generate multiple captions
Issue -
State: closed - Opened by rahimentezari 11 months ago
- 2 comments
#64 - is all the models of cogvlm are commercial license ?
Issue -
State: closed - Opened by papasanimohansrinivas 11 months ago
- 3 comments
#63 - cogvlm-chat模型的微调怎么实现呢?
Issue -
State: closed - Opened by xuxuxuchen 11 months ago
- 30 comments
Labels: good first issue
#62 - how to run web_domo.py in muti-GPUs?
Issue -
State: closed - Opened by makangzhe 11 months ago
#61 - How to run web_demo.py in muti-gpu?
Issue -
State: closed - Opened by makangzhe 11 months ago
- 5 comments
#60 - fine-tuning失败
Issue -
State: closed - Opened by jukylin 11 months ago
- 2 comments
#59 - CogVLM中英双语版有计划开源吗
Issue -
State: closed - Opened by jukylin 11 months ago
- 1 comment
#58 - When will the bilingual version of weight be available?
Issue -
State: closed - Opened by shengyuwoo 11 months ago
- 5 comments
#57 - 请问为什么对Visual feature用的也是causal mask而不是类似prefix的mask?
Issue -
State: closed - Opened by 4IK1d 11 months ago
- 3 comments
#56 - ncclUnhandledCudaError: Call to CUDA function failed.
Issue -
State: closed - Opened by zslittlehelper 11 months ago
- 5 comments
#55 - A40的48G显存能finetune吗?
Issue -
State: closed - Opened by chenjingcheng 11 months ago
- 2 comments
#54 - 关于模型版本的问题
Issue -
State: closed - Opened by pf67 11 months ago
- 3 comments
#53 - Is there a plan to release the quantized version of the model? Or to provide some guides on how to quantize?
Issue -
State: closed - Opened by jxl4650152 11 months ago
- 1 comment
#52 - using PIL images instead of path
Issue -
State: closed - Opened by rahimentezari 11 months ago
- 1 comment
#51 - Grounding 同一张图多次推理结果不一致
Issue -
State: closed - Opened by Pro-flynn 11 months ago
- 7 comments
#50 - What is the meaning of different 'image_xxx_mask' ?
Issue -
State: closed - Opened by microhu 11 months ago
- 9 comments
#49 - can anyone tell me how to run web_demo.py with multi-gpus?
Issue -
State: closed - Opened by wonder-hy 11 months ago
- 7 comments
#48 - 这个可以拿来做PI CI图片信息抽取吗?
Issue -
State: closed - Opened by zhangquanwei962 11 months ago
- 3 comments
#47 - web demo does not work
Issue -
State: closed - Opened by wangkunyu241 11 months ago
- 2 comments
#46 - The grounding detection frame coordinates are inconsistent with the image resolution.
Issue -
State: closed - Opened by JoaquinChou 11 months ago
- 3 comments
#45 - “list index out of range”when running Multi-GPU inference demo
Issue -
State: closed - Opened by tcexeexe 11 months ago
- 1 comment
#44 - which model does the web demo use?
Issue -
State: closed - Opened by uestcMeng 11 months ago
- 6 comments
#43 - AMD Support
Issue -
State: closed - Opened by userbox020 11 months ago
- 4 comments
#42 - Multiple images analysis
Issue -
State: closed - Opened by sskorol 11 months ago
- 1 comment
#41 - 关于使用cli进行推理的问题
Issue -
State: closed - Opened by Rui-Hu01 11 months ago
- 7 comments
#40 - 请问预训练阶段训练了哪些参数?
Issue -
State: closed - Opened by xyfZzz 11 months ago
- 4 comments
#39 - instructions for multitask training stage
Issue -
State: closed - Opened by Cuiunbo 11 months ago
- 1 comment
#38 - Will it support video input?
Issue -
State: closed - Opened by KooSung 11 months ago
- 4 comments
#37 - download 224 when --from_pretrained cogvlm-base-490
Issue -
State: closed - Opened by YukunZEX 11 months ago
- 10 comments
#36 - What format of image-text pairs should be used for fine-tuning?
Issue -
State: closed - Opened by summerbuild 11 months ago
- 4 comments
#35 - GPU usage stuck on 100% percent when using 2* RTX 3090
Issue -
State: closed - Opened by HSPK 11 months ago
- 12 comments
#34 - Baselines - comparison to IDEFICS
Issue -
State: closed - Opened by VictorSanh 11 months ago
- 1 comment
#33 - run cli_demo error
Issue -
State: closed - Opened by rainsoulsrx 11 months ago
- 17 comments
#32 - 部署时报错
Issue -
State: closed - Opened by Yj1027520 11 months ago
- 2 comments
#31 - The paper cannot be downloaded.
Issue -
State: closed - Opened by kaiwangntu 11 months ago
- 3 comments
#30 - Update README.md
Pull Request -
State: closed - Opened by eltociear 11 months ago
- 1 comment
#29 - "Sorry, I can't analyze the content of the current image for you. "
Issue -
State: closed - Opened by wizardlancet 11 months ago
- 3 comments
#28 - where can i find the alignment data?
Issue -
State: closed - Opened by MingsYang 11 months ago
- 1 comment
#27 - Expecting LLaVA-Instruct dataset via mannual annotation
Issue -
State: closed - Opened by Yuqifan1117 11 months ago
- 4 comments
#26 - xformers attention to onnx?
Issue -
State: closed - Opened by hardlipay 11 months ago
- 6 comments
#25 - the format of coordinate
Issue -
State: closed - Opened by peiliu0408 12 months ago
- 6 comments
#24 - How to use CogVLM in image caption tasks.
Issue -
State: closed - Opened by sanbuphy 12 months ago
- 7 comments
#23 - 4 bit quantization version available?
Issue -
State: closed - Opened by hugh-min 12 months ago
- 3 comments
#22 - Cloud you please provide hardware requirement with different model?
Issue -
State: closed - Opened by vergil-ong 12 months ago
- 4 comments
#21 - update web_demo
Pull Request -
State: closed - Opened by lykeven 12 months ago
#20 - gradio api result is inconsistent with web demo
Issue -
State: closed - Opened by XZLancer 12 months ago
- 12 comments
#19 - remove quantization related part for not supported right now
Pull Request -
State: closed - Opened by aisensiy 12 months ago
#18 - Fix web_demo.py
Issue -
State: closed - Opened by miandai 12 months ago
- 2 comments
#17 - Commercially available?
Issue -
State: closed - Opened by lj163ucas 12 months ago
- 3 comments
#16 - what is difference between this weights?
Issue -
State: closed - Opened by WeiXuanLi-1024 12 months ago
- 4 comments
#15 - Do you have a plan to release the evaluation code?
Issue -
State: closed - Opened by HenryHZY 12 months ago
- 1 comment
#14 - Could you please provide a simple script to use your multimodel like huggingface or other multimodels?
Issue -
State: closed - Opened by xinsir6 12 months ago
- 13 comments
Labels: good first issue
#13 - add more info about the default model location using SAT
Pull Request -
State: closed - Opened by aisensiy 12 months ago
- 1 comment
#12 - Recognition Error
Issue -
State: closed - Opened by jony4 12 months ago
- 1 comment
#11 - how to change from 224x224 to 490*490
Issue -
State: closed - Opened by microhu 12 months ago
- 1 comment
#10 - What the diffference between CogVLM and VisualGLM?/
Issue -
State: closed - Opened by najingligong1111 12 months ago
- 1 comment
#9 - How to do Model Quantization?
Issue -
State: closed - Opened by miandai 12 months ago
- 20 comments
#8 - When will Chinese version release?
Issue -
State: closed - Opened by lucasjinreal 12 months ago
- 1 comment
#7 - Missing dependency "jmespath" when downloading models
Issue -
State: closed - Opened by aisensiy 12 months ago
- 1 comment
#6 - remove fixed port
Pull Request -
State: closed - Opened by aisensiy 12 months ago
#5 - Please make a replicate demo
Issue -
State: closed - Opened by kenhuang1964 12 months ago
- 3 comments
#4 - add missing bitsandbytes dependency
Pull Request -
State: closed - Opened by aisensiy 12 months ago
- 1 comment
#3 - So... the pretrained model it not available now?
Issue -
State: closed - Opened by aisensiy 12 months ago
- 6 comments
#2 - add web demo
Pull Request -
State: closed - Opened by lykeven 12 months ago
#1 - Dev ywm
Pull Request -
State: closed - Opened by 1049451037 12 months ago