-
Hello and thank you for the great work here!
We are trying to save a Phi 3 vision mode, but are running into some issues saving it as safetensors.
Due to a shared weight, saving unfortunately fa…
-
That model is insane for its size ....
https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
-
I use GPT-4o is running ok.
But when I changed to the local model, I used some error message.
EXCEPTION: 'function' object has no attribute 'name'
![image](https://github.com/onuratakan/gpt-compute…
-
When running the `finetune.sh` script with my own dataset, I encountered the following error during checkpoint / saving the model:
```
RuntimeError: The weights trying to be saved contained shared t…
-
我正在对internvl2使用视频数据进行full finetune,显卡为单张32G V100,报错torch.cuda.OutOfMemoryError: CUDA out of memory.
torchrun /cache/InternVL/internvl_chat/internvl/train/internvl_chat_finetune.py \
--model_name…
-
Phi3 Vision weights are opensourced in hugging face
https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
Hoping to see it in ollama models.
-
Can it be developed for local use? ollamam
-
### Describe the issue as clearly as possible:
`Should work with Phi3-vision, but running into errors`
### Steps/code to reproduce the bug:
```python
from outlines import models
from outlines impo…
-
https://huggingface.co/microsoft/Phi-3.5-vision-instruct
-
while merging the lora weights with the **merge_lora_weights.py**, I got this error
Here's the parameters for merge_lora_weights.py
`python src/merge_lora_weights.py \
--model-path /kaggle/wo…