Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / ucas-haoranwei/vary-toy issues and pull requests
#41 - Vary-tiny 是否支持中文?
Issue -
State: open - Opened by Davidwhw 2 months ago
#40 - 请问下,相对于诸如Florence2这类的0.3/0.7B的模型,Vary-tony的性能如何呢?
Issue -
State: open - Opened by gjd2017 3 months ago
#40 - 请问下,相对于诸如Florence2这类的0.3/0.7B的模型,Vary-tony的性能如何呢?
Issue -
State: open - Opened by gjd2017 3 months ago
#39 - How do I download flash-attn? I have followed the downloading steps completely.
Issue -
State: open - Opened by ranck626 4 months ago
#39 - How do I download flash-attn? I have followed the downloading steps completely.
Issue -
State: open - Opened by ranck626 4 months ago
#38 - where the requirements
Issue -
State: closed - Opened by Moneorker 4 months ago
#38 - where the requirements
Issue -
State: closed - Opened by Moneorker 4 months ago
#37 - ValueError: Trying to set a tensor of shape torch.Size([257, 1024]) in "weight" (which has shape torch.Size([577, 1024])), this look incorrect.
Issue -
State: open - Opened by willpat1213 7 months ago
#37 - ValueError: Trying to set a tensor of shape torch.Size([257, 1024]) in "weight" (which has shape torch.Size([577, 1024])), this look incorrect.
Issue -
State: open - Opened by willpat1213 7 months ago
#36 - 难以控制生成语言种类
Issue -
State: open - Opened by TekhneC 7 months ago
- 1 comment
#36 - 难以控制生成语言种类
Issue -
State: open - Opened by TekhneC 7 months ago
- 1 comment
#35 - 路径很奇怪
Issue -
State: closed - Opened by qin-yuhao 8 months ago
- 3 comments
#35 - 路径很奇怪
Issue -
State: closed - Opened by qin-yuhao 8 months ago
- 3 comments
#34 - 一张卡train不起来
Issue -
State: open - Opened by fanshuaiyao 8 months ago
- 1 comment
#34 - 一张卡train不起来
Issue -
State: open - Opened by fanshuaiyao 8 months ago
- 1 comment
#33 - 训练数据中的<lb>
Issue -
State: open - Opened by fanshuaiyao 8 months ago
- 2 comments
#33 - 训练数据中的<lb>
Issue -
State: open - Opened by fanshuaiyao 8 months ago
- 2 comments
#32 - 训练loss降为0
Issue -
State: open - Opened by afreestudy 9 months ago
- 1 comment
#32 - 训练loss降为0
Issue -
State: open - Opened by afreestudy 9 months ago
- 1 comment
#31 - 训练json的格式
Issue -
State: open - Opened by afreestudy 10 months ago
#31 - 训练json的格式
Issue -
State: open - Opened by afreestudy 10 months ago
#30 - 咨询训练SAM
Issue -
State: closed - Opened by zhyj3038 10 months ago
- 20 comments
#30 - 咨询训练SAM
Issue -
State: closed - Opened by zhyj3038 10 months ago
- 20 comments
#29 - 请问修改哪里能在训练模型时,接入opt模型
Issue -
State: open - Opened by LimbCC 11 months ago
#29 - 请问修改哪里能在训练模型时,接入opt模型
Issue -
State: open - Opened by LimbCC 11 months ago
#28 - How to handle detected coordinates, how is it normalized?
Issue -
State: closed - Opened by LinJM 11 months ago
- 2 comments
#28 - How to handle detected coordinates, how is it normalized?
Issue -
State: closed - Opened by LinJM 11 months ago
- 2 comments
#27 - 关于demo运行
Issue -
State: open - Opened by Tiehr2000 11 months ago
- 1 comment
#27 - 关于demo运行
Issue -
State: open - Opened by Tiehr2000 11 months ago
- 1 comment
#26 - 我在进行第一阶段的训练(视觉词汇表)后,测试的时候opt输出错误的坐标位置,无法检测对象
Issue -
State: open - Opened by black1948 11 months ago
- 1 comment
#26 - 我在进行第一阶段的训练(视觉词汇表)后,测试的时候opt输出错误的坐标位置,无法检测对象
Issue -
State: open - Opened by black1948 11 months ago
- 1 comment
#25 - 有什么办法把llm部分切换到hf上的qwen2吗?
Issue -
State: open - Opened by shifan3 11 months ago
- 1 comment
#25 - 有什么办法把llm部分切换到hf上的qwen2吗?
Issue -
State: open - Opened by shifan3 11 months ago
- 1 comment
#24 - RuntimeError: Input type (c10::Half) and bias type (float) should be the same
Issue -
State: open - Opened by Gary-code 11 months ago
#24 - RuntimeError: Input type (c10::Half) and bias type (float) should be the same
Issue -
State: open - Opened by Gary-code 11 months ago
#23 - add dockerfile and docker-compose.yml
Pull Request -
State: open - Opened by hotwa 11 months ago
- 1 comment
#23 - add dockerfile and docker-compose.yml
Pull Request -
State: open - Opened by hotwa 11 months ago
- 1 comment
#22 - 请问new vision vocabulary weights是否指的是sam部分的权重?
Issue -
State: closed - Opened by whalefa1I 12 months ago
- 3 comments
#22 - 请问new vision vocabulary weights是否指的是sam部分的权重?
Issue -
State: closed - Opened by whalefa1I 12 months ago
- 3 comments
#21 - train errorKeyError: 'data_name1'
Issue -
State: open - Opened by bsbrother 12 months ago
- 1 comment
#21 - train errorKeyError: 'data_name1'
Issue -
State: open - Opened by bsbrother 12 months ago
- 1 comment
#20 - Error: Downloading models from huggingface
Issue -
State: open - Opened by chenweilong915 12 months ago
- 1 comment
#20 - Error: Downloading models from huggingface
Issue -
State: open - Opened by chenweilong915 12 months ago
- 1 comment
#19 - 麻烦问一下,qwen 1.8B用的是chat版本的还是非chat版本的?
Issue -
State: open - Opened by duchenzhuang 12 months ago
- 2 comments
#19 - 麻烦问一下,qwen 1.8B用的是chat版本的还是非chat版本的?
Issue -
State: open - Opened by duchenzhuang 12 months ago
- 2 comments
#18 - About deployment?
Issue -
State: open - Opened by CVHub520 12 months ago
- 1 comment
#18 - About deployment?
Issue -
State: open - Opened by CVHub520 12 months ago
- 1 comment
#17 - 训练参数 --model_name_or_path
Issue -
State: closed - Opened by sixgod-666 about 1 year ago
- 1 comment
#17 - 训练参数 --model_name_or_path
Issue -
State: closed - Opened by sixgod-666 about 1 year ago
- 1 comment
#16 - exits with return code = -9 after I delete 'device_map="cuda"', OOM will occur if I keep 'device_map="cuda"'
Issue -
State: open - Opened by zodiac50 about 1 year ago
#16 - exits with return code = -9 after I delete 'device_map="cuda"', OOM will occur if I keep 'device_map="cuda"'
Issue -
State: open - Opened by zodiac50 about 1 year ago
#15 - 生成的内容出现问题
Issue -
State: open - Opened by Nikol-coder about 1 year ago
- 3 comments
#15 - 生成的内容出现问题
Issue -
State: open - Opened by Nikol-coder about 1 year ago
- 3 comments
#14 - 路径如何修改
Issue -
State: open - Opened by lht1605766283 about 1 year ago
- 3 comments
#13 - 训练的问题
Issue -
State: open - Opened by duchenzhuang about 1 year ago
- 1 comment
#12 - RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:5 and cuda:6!
Issue -
State: open - Opened by readyFly about 1 year ago
- 1 comment
#11 - ValueError: Trying to set a tensor of shape torch.Size([1024, 1024]) in "weight" (which has shape torch.Size([2048, 1024])), this look incorrect.
Issue -
State: open - Opened by zodiac50 about 1 year ago
- 1 comment
#10 - Update qwen_generation_utils.py
Pull Request -
State: open - Opened by eltociear about 1 year ago
#9 - 请问训练大概需要什么性能的GPU
Issue -
State: open - Opened by xaswq about 1 year ago
- 9 comments
#8 - Enhancement Request: Improve Table Recognition and Markdown Conversion
Issue -
State: open - Opened by hotwa about 1 year ago
- 6 comments
#7 - 修改加载 CLIP-VIT-L 模型路径的问题
Issue -
State: open - Opened by hotwa about 1 year ago
- 9 comments
#6 - 有没有开源文档渲染数据代码的计划?
Issue -
State: open - Opened by yazheng0307 about 1 year ago
- 1 comment
#5 - CUDA out of memory
Issue -
State: open - Opened by sixgod-666 about 1 year ago
- 8 comments
#4 - Trying to set a tensor of shape torch.Size([1024]) in "class_embedding"
Issue -
State: closed - Opened by zhangxyzte about 1 year ago
- 12 comments
#3 - 支持 4/8 bit 量化运行
Issue -
State: open - Opened by yazheng0307 about 1 year ago
- 1 comment
#2 - How to fine-tune Vary-tiny with LoRA or SFT?
Issue -
State: closed - Opened by parap1uie-s about 1 year ago
- 3 comments
#1 - 可以更一下 requirements.txt 么
Issue -
State: open - Opened by tpoisonooo about 1 year ago
- 7 comments