Katehuuh

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction 5e6f808 format DPO Dataset `name_dpo.json`: ```json [ { "instruction": "Last Question", "input": "", "output":...

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction Error seems to show on any (dpo) dataset, not just `dpo_mix_en`. Full Log. Clean...

llava - RuntimeError: Index put requires the source and destination dtypes match, got Half for the destination and Float for the source.

1

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction Broke after update to 2bec28e ``` set CUDA_VISIBLE_DEVICES=0 && llamafactory-cli train --stage sft --do_train...

https://github.com/Leeroo-AI/mergoo

Instead of bulky wheels, is it possible in a straightforward way to replace locomotion using a strong robot arm at the base, eg. for walking steps? This also would give...

Add dataset % sample num equally distribute

2

# What does this PR do? Update https://github.com/hiyouga/LLaMA-Factory/pull/3829 to `num_samples` include % of dataset and equally distribute the selection. Useful when the max number of `num_samples` is unknown. ## Before...

Error processing frame: %s generator already executing

2

```python import os from fastrtc import ( Stream, ReplyOnPause, get_stt_model, get_tts_model, KokoroTTSOptions ) import numpy as np import requests import json # Initialize local STT and TTS models stt_model =...

TORCH_USE_CUDA_DSA on policy act

1

### System Info ```Shell Windows, CUDA 12.8, torch Nightly 2.8.0, using 1*So100 dataset include 3 ep/example of simple "pick and place". ``` Here for additional information of my full installation....

[Feature request]: fast-whisper+streaming

2

**Description** [whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) and [distil-large-v2](https://huggingface.co/distil-whisper/distil-large-v2) with integration of https://github.com/Vaibhavs10/insanely-fast-whisper could be interesting for real-time dialogue. Also **streaming** option to not have to click on microphone where for example [current](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/whisper_stt) [extensions](https://github.com/oobabooga/text-generation-webui/wiki/07-%E2%80%90-Extensions#a-full-example) could...

Image Attachment Fails with 403 Error

2

I was unable to send PNG image through the API, return 403 error: ```cmd [403] Unable to prepare file attachment -> Image.png Reason: ��5��.. ``` Code Example `unofficial-claude-api version`: `0.3.3`...