-
This issue aims at keeping track of the models that would be interesting to get added to candle. Feel free to make a comment to mention a new model, or vote for a model already in the list.
- [musicg…
-
我尝试在自己的数据集上进行了微调，但是当我微调后不论是lora还是全量，在尝试输入图片的时候都出现了报错：
***
RuntimeError: mat1 and mat2 shapes cannot be multiplied (729x1152 and 3456x4096)
***
根据调用堆栈，可能是我的projector维度异常发生了改变
这是我的微调配置文件：
#!/bin/…
htesd updated
4 months ago
-
你好，我在使用你们代码进行训练时发现，使用S2增加图像的输入分辨率的方式的训练速度比不使用S2慢4倍，这种现象正常吗？
-
Information:
OS: Ubuntu 22.04
Conda Environment: python=3.10
024-10-08 06:17:12,277 - …
-
作者好，非常感谢你的开源。我有两个疑问想咨询下
**1. convnext 的 drop path 问题**
convnext 的 drop path 是 0.1，虽然你在训练时候设置的是不训练，但是这个路径还是会执行的。原则上在训练时候，convnext 要设置为 eval 模式吧？ 我没有找到相关代码，有点奇怪，想了解下
**2. 代码鲁棒性问题**
如果是 clip+…
-
### Describe the issue
Issue:
In pretraining or finetuning, the training always stuck after the log "Formatting inputs...Skip in lazy mode". Everytime I need to force shutting down my GPU server b…
-
Very good work!
I encountered the following error while running the function
```
all_generated_str = generate_w_clip(model, tokenizer, vis_processor, text, image, device=device, verbose=False, fi…
-
Hi,
Bunny-Llama-3-8B-V is very impressive and is able to pick up far more details than anything that uses clip-vit-large-patch14-336!
As most of the community uses [LLAMA.CPP](https://github.com…
GJSea updated
5 months ago
-
I have tried converting the Bunny model to GGUF using the script - https://github.com/ggerganov/llama.cpp/tree/master/examples/llava (Right now the script is only available for Llava1.5 and 1.6, Moond…
-
Hello,
It's a great work! And there are several questions:
1. In the technical report you mentioned
> We find that LoRA empirically leads to better performance than fully tuning across all c…