-
Dear @xiaoachen98,
Thank you very much for releasing the code. I am running your fine-tuning script to replicate your LLaMA 3 results. However, I am getting zero loss after the first iteration. Hav…
-
Thank you for releasing this model. I tried finetuning this model with my custom dataset using this [script](https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/finetune_task_lora.sh) from LLa…
-
Using the latest versions of mlx and mlx_vlm, on
```python
import mlx.core as mx
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils impor…
-
### What happened?
With ccache installed in Windows, trying to build with SYCL by following instructions in https://github.com/ggerganov/llama.cpp/blob/master/docs/backend/SYCL.md#windows.
I found t…
-
During the process of testing the demo, I encountered several version conflicts. I have tried the following two setups:
1. pytorchvideo==0.1.5, torch==2.2.1, torchvision==0.17.1, with nvcc version…
-
Hey, I just tried the Alpaca Flatpak, it works perfectly fine with small Models.
But whenever I try to download Models bigger than 6GB, the Progression Bar always stops.
Llama 3.1 models, as well as…
-
Hello!
I am evaluating the llava-next-llama-3-8b model using lmms-eval, meeting this bug:
```
File "lmms-eval/lmms_eval/models/llava.py", line 358, in generate_until
conv = copy.deepcopy(con…
-
- [x] MiniCPM-Llama3-V-2_5
- [x] Florence 2
- [x] Phi-3-vision
- [x] Bunny
- [x] Dolphi-vision-72b
- [x] Llava Next
- [x] Qwen2-VL
- [x] Pixtral
- [x] Llama-3.2
- [x] Llava Interleave
- [x] …
-
### System Info
The regression happens after transformers==4.45.2.
```
- `transformers` version: 4.47.0.dev0
- Platform: Linux-6.6.0-gnr.bkc.6.6.9.3.15.x86_64-x86_64-with-glibc2.34
- Python v…
-
According to readme, this is the code for training:
```
(llama3-ft) python train.py --dataset_path path/to/dataset.json --output_dir path/to/output_dir --text_model_id="meta-llama/Meta-Llama-3-8B-I…