-
There are two existing (closed) issues related to this, but neither offers a solution. I've tweaked the n_ctx value, but the error persists: 2048 tokens aren't enough. So, is this parameter ineffectiv…
-
### Problem
Wondering if basic support already exists.
Llama vision 3.2 is unlike https://github.com/turboderp/exllamav2/issues/399, and in some ways may be very easy for basic Exllama integration…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
- `llamafactory` version: 0.8.4.dev0
- Platform: Linux-5.15.153.1-microsoft-standard-WSL2-x86_64-w…
-
### System Info
In current implementation of VLMs, the "_supports_sdpa" attribute checks and activates SDPA attention only for the language model. For example in [Llava](https://github.com/huggingf…
-
Awesome work!
I had some issues when trying to test it with custom data via gradio interface. Could you provide some insights on how the apis are called? Or perhaps any insights on implementing wi…
-
### System Info
-GPU A100
NVIDIA-SMI 535.183.01 Driver Version: 535.183.01 CUDA Version: 12.2
NVIDIA A100-SXM4-80GB
### Who can help?
@byshiue @kaiyux
### Information
- [X] …
-
### 🐛 Describe the bug
The LLAVA model loaded successfully. Please check the screenshot. After an image is given as a prompt, the app crashes. Please check the logs as well. I am attaching the logs f…
-
I'm trying to instruction tune llava-next models following the llava_vsft.py examples shared for llava-1.5.
```
python vsft.py \
--dataset_name="HuggingFaceH4/llava-instruct-mix-vsft" \
--…
-
Hi @hadley, thanks for sharing this, really exciting.
Very nice to see support for open models via ollama. I wonder if you would consider adding support for VLLM-hosted models as well, e.g. see ht…
-
Hello. Thanks for your excellent work!
Earlier, I reproduced LLaVA-NeXT-Image training and got the desired performance, and I am now trying to reproduce LLaVA-NeXT-Interleave training. I would like…