MiniGPT-4 · Issues· 376 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #561
Significant discrepancy in CHAIR metrics when reproducing results with MiniGPT-4 (Vicuna-7B)
Updated Feb 23, 2026 - #542
Training Data Annotation File Link is Inaccessible
Updated Jan 26, 2026 - #516
Where is the region_descriptions.json?
Updated Jan 26, 2026 - #560
https://<اسم‑المستخدم‑عند‑GitHub>.github.io/<اسم‑المستودع>/
Updated Nov 24, 2025 - #331
Is there any scripts for inference ? Not gradio demo
Updated Nov 18, 2025 - #237
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
Updated Oct 29, 2025 - #558
LLama output embeddings shape keeps increasing with multiple image inputs unless model is reloaded
Updated Jul 23, 2025 - #555
Request assistance for the situation where the dataset and checkpoint links cannot be opened during the fine-tuning of MiniGPT-4
Updated May 9, 2025 - #530
AssertionError: Model 'mini_gpt4' has not been registered.
Updated May 7, 2025 - #159
How to finetune with my own dataset?
Updated May 7, 2025 - #554
minigptV2 does not achieve the expected effect
Updated Apr 21, 2025 - #553
Why minigpt4-13b sometimes answer in Chinese/Janpanese/Korea while the prompt is English?
Updated Apr 7, 2025 - #487
The same input but different output from the online demo.
Updated Mar 31, 2025 - #552
Error running MiniGPT-v2 demo code
Updated Mar 25, 2025 - #334
Error when running the demo in Colab with Llama 2 Chat 7B
Updated Mar 25, 2025