Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / deepseek-ai/DeepSeek-VL issues and pull requests
#60 - ValueError: The checkpoint you are trying to load has model type `multi_modality` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
Issue -
State: open - Opened by Y-PanC about 1 month ago
#59 - training cost of deepseek-vl-1.3B
Issue -
State: open - Opened by shufangxun 3 months ago
#58 - TypeError: Object of type AlignerConfig is not JSON serializable
Issue -
State: open - Opened by JingyuanHan 4 months ago
- 1 comment
#57 - 拉了一个多模态大模型技术交流群,大家可以加入进来进行技术交流
Issue -
State: closed - Opened by feihuamantian 4 months ago
- 1 comment
#56 - dataset format of pretraining stage
Issue -
State: open - Opened by annopackage 4 months ago
#55 - How to get feature representation vector of input image?
Issue -
State: open - Opened by lukywangwang 5 months ago
#54 - 多图的数量上限
Issue -
State: open - Opened by JUNJIE99 6 months ago
- 1 comment
#53 - How can I get a GenerateOutput after language_model.generate() ?
Issue -
State: open - Opened by ApolloRay 6 months ago
#52 - RuntimeError: "triu_tril_cuda_template" not implemented for 'BFloat16'
Issue -
State: open - Opened by sulaiman1988 6 months ago
- 1 comment
#51 - Add base64 images support
Pull Request -
State: closed - Opened by Youho99 7 months ago
#50 - 支持ollama部署吗
Issue -
State: open - Opened by yuanjie-ai 7 months ago
#49 - If I want to run and use in ollama, I can import the GGUF version into ollama if it is available
Issue -
State: open - Opened by alex13by 7 months ago
- 1 comment
#48 - Batching
Issue -
State: open - Opened by SinanAkkoyun 7 months ago
- 7 comments
#47 - feat: add multiple images (or in-context learning) conversation example
Pull Request -
State: closed - Opened by StevenLiuWen 7 months ago
#46 - An error is reported for multi-GPU inference
Issue -
State: open - Opened by Athicbliss 7 months ago
#45 - grdio加载模型卡住
Issue -
State: open - Opened by LianghuiGuo 7 months ago
#44 - question: help needed for arch clarification
Issue -
State: open - Opened by SinanAkkoyun 7 months ago
#43 - What's the difference of base and chat model?
Issue -
State: closed - Opened by BlueBlueFF 7 months ago
- 1 comment
#42 - tips for running the model in FP16 on 24GB GPU
Issue -
State: closed - Opened by adamo1139 8 months ago
#41 - What tasks in training for image-text interleaved data?
Issue -
State: closed - Opened by BlueBlueFF 8 months ago
- 1 comment
#40 - 模型重复输出最后一句话,是什么原因呢,有办法能解决吗
Issue -
State: closed - Opened by Yangfan-96 8 months ago
- 1 comment
#39 - LMDeploy support accelerating DeepSeek VL models now!!! :rocket:
Issue -
State: open - Opened by AllentDan 8 months ago
- 2 comments
#38 - How to convert it to GGUF/GGML for general use?
Issue -
State: open - Opened by YuanfengZhang 8 months ago
#37 - error when i run inference.py
Issue -
State: closed - Opened by Yangfan-96 8 months ago
- 6 comments
#36 - pretrain 模型通过什么prompt 能激发OCR能力,能否输出坐标信息
Issue -
State: open - Opened by paulpaul91 8 months ago
#35 - Finetuning
Issue -
State: open - Opened by univa-JASON 8 months ago
- 2 comments
#34 - Adding support for quantization and fast inference server
Issue -
State: open - Opened by rostandk 8 months ago
#33 - LLaVA1.6-GPT4V是什么数据集呢?
Issue -
State: closed - Opened by mzfive 8 months ago
- 1 comment
#32 - docs: update README.md
Pull Request -
State: closed - Opened by RERV 8 months ago
#31 - docs: update README.md
Pull Request -
State: closed - Opened by RERV 8 months ago
#30 - RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
Issue -
State: closed - Opened by linny2002 8 months ago
#29 - Does not start
Issue -
State: open - Opened by Troceleng 8 months ago
#28 - 4-bit quant?
Issue -
State: open - Opened by nmandic78 8 months ago
- 5 comments
#27 - docs: update readme about chat demo url
Pull Request -
State: closed - Opened by Benjamin-eecs 8 months ago
#26 - docs: update readme
Pull Request -
State: closed - Opened by Benjamin-eecs 8 months ago
#25 - Gradio issue on colab notebook T4 gpu
Issue -
State: open - Opened by clarencerat 8 months ago
#24 - ERROR: Package 'deepseek-vl' requires a different Python: 3.11.8 not in '<3.10,>=3.8'
Issue -
State: closed - Opened by kakaxixx 8 months ago
- 1 comment
#23 - 是否评估过有作为web或者windows的agent的潜力?
Issue -
State: open - Opened by DirtyKnightForVi 8 months ago
#22 - feat: add mps support
Pull Request -
State: open - Opened by Fodark 8 months ago
- 2 comments
#21 - feat: automatically patch `collections` for >python 3.10 support
Pull Request -
State: closed - Opened by Fodark 8 months ago
#20 - Multi-image mixed input
Issue -
State: closed - Opened by TechxGenus 8 months ago
- 4 comments
#19 - Can you address the work you have referenced?
Issue -
State: closed - Opened by lucasjinreal 8 months ago
- 5 comments
#18 - 请问是否后期会实现目标检测功能
Issue -
State: open - Opened by whysirier 8 months ago
#17 - About the preprocessor way in high and low input?
Issue -
State: closed - Opened by lucasjinreal 8 months ago
#16 - feat: gradio demo integration
Pull Request -
State: closed - Opened by haoy945 8 months ago
#15 - 'FieldInfo' object has no attribute 'required'
Issue -
State: open - Opened by White-Friday 8 months ago
- 1 comment
Labels: environment
#14 - ROCm Support
Issue -
State: open - Opened by hchasens 8 months ago
- 1 comment
Labels: enhancement
#13 - feat: replicate demo integration
Pull Request -
State: open - Opened by lucataco 8 months ago
#12 - CLI: enables image drop-in from file explorer
Pull Request -
State: closed - Opened by SinanAkkoyun 8 months ago
#11 - Support for M1 Mac, or non-cuda devices
Issue -
State: open - Opened by mattkanwisher 8 months ago
- 3 comments
Labels: enhancement
#10 - deepseek-vl系列的微调支持 (finetune)
Issue -
State: closed - Opened by Jintao-Huang 8 months ago
- 6 comments
#9 - 请问什么时候可以开源微调代码
Issue -
State: closed - Opened by cdxzyc 8 months ago
- 1 comment
#8 - 是否又评估过OCR能力?
Issue -
State: open - Opened by lucasjinreal 8 months ago
- 5 comments
#7 - text-generation-webui是否支持
Issue -
State: open - Opened by newstargo 8 months ago
#6 - Fine-tuning Script
Issue -
State: open - Opened by TechxGenus 8 months ago
- 7 comments
#5 - feat: add replicate demo and api
Pull Request -
State: closed - Opened by lucataco 8 months ago
- 1 comment
#4 - ImportError: cannot import name 'Mapping' from 'collections'
Issue -
State: closed - Opened by NickLucche 8 months ago
- 3 comments
Labels: environment
#3 - Does the sam-branch use the Vary initialization for dense OCR?
Issue -
State: closed - Opened by Ucas-HaoranWei 8 months ago
#2 - How to finetune and serve the finetuned model using VLLM like tools
Issue -
State: open - Opened by monksgoyal 8 months ago
- 3 comments
#1 - feat: change setup.py to pyproject.toml
Pull Request -
State: closed - Opened by Benjamin-eecs 8 months ago