Skip to content

Issues: TinyLLaVA/TinyLLaVA_Factory

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

87 Open 67 Closed
87 Open 67 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

For the 'share' training recipe, the adapter_config.json file is missing when LoRA is used in both the pretraining and fine-tuning processes.
#170 opened Jan 17, 2025 by fortuneate3
The size of tensor a (1290) must match the size of tensor b (778) at non-singleton dimension 3
#169 opened Jan 16, 2025 by mrpeerat
2
Support TinyLLaVA-3.1B with vLLM inference
#168 opened Jan 15, 2025 by TheBobbyliu
1
release of the pre-trained models
#166 opened Jan 4, 2025 by FightingFighting
prepare_inputs_for_generation in TinyLlavaForConditionalGeneration
#165 opened Dec 23, 2024 by SakuraTroyChen
可以提供一下您的Zhang199/TinyLLaVA-Qwen2-0.5B-SigLIP的每层的参数量吗
#164 opened Dec 23, 2024 by MichealZhangxa
为什么使用huggingface上面的代码，老是说识别不了这个model type tinyllava
#162 opened Dec 23, 2024 by MichealZhangxa
8
更改loss function
#160 opened Dec 20, 2024 by chocho0130
4
recombine vision and language model
#159 opened Dec 19, 2024 by sailfish009
想问一下作者的论文中的雷达图是怎么画的
#157 opened Dec 18, 2024 by MichealZhangxa
请问pope上面的这个指标代表的是什么分数
#154 opened Dec 10, 2024 by MichealZhangxa
4
gqa的指标评估的文件怎么没找到
#153 opened Dec 10, 2024 by MichealZhangxa
6
训练到一半变得很慢怎么解决，是因为数据问题吗
#152 opened Dec 9, 2024 by MichealZhangxa
5
基于base的方法具体是怎么做的
#151 opened Dec 8, 2024 by MichealZhangxa
1
how to enable the 'share' training recipe in the paper
#150 opened Dec 6, 2024 by Danield21
7
max_length和你们的训练脚本的不一致影响大吗
#149 opened Dec 5, 2024 by MichealZhangxa
7
老是会因为各种各样的原因停止训练，有什么办法能够训练中断后重启训练吗
#148 opened Dec 5, 2024 by MichealZhangxa
1
[Feature Request] llava mini
#147 opened Dec 4, 2024 by sailfish009
4
如果想要全量微调qwen2_0.5B需要多大显存的显卡
#146 opened Dec 4, 2024 by MichealZhangxa
1
基于base方法训练的模型仅仅使用的是llava_dataset吗
#145 opened Dec 4, 2024 by MichealZhangxa
1
'TinyLlavaForConditionalGeneration' object has no attribute 'peft_config'
#142 opened Dec 4, 2024 by pspdada
1
1
flash_attn_2 undefined symbol
#141 opened Dec 3, 2024 by pspdada
2
Support DPO training?
#140 opened Dec 3, 2024 by pspdada
3
为什么训练时候有时候速度会变得很慢，GPU利用率不高，显存也没爆
#139 opened Dec 2, 2024 by MichealZhangxa
7
请问训练模型，显存有限的情况下，lora方法会很影响模型性能吗
#138 opened Nov 30, 2024 by MichealZhangxa
6
ProTip! What’s not been updated in a month: updated:<2025-01-09.