Lyte (Yassine Ennaour)

liked 3 models 1 day ago

upvoted an article 4 days ago

Article

TerjamaBench: A Cultural Benchmark for English-Darija Machine Translation

By

•

5 days ago

• 20

reacted to hexgrad's post with 🚀🔥 6 days ago

Post

12061

📣 Looking for labeled, high-quality synthetic audio/TTS data 📣 Have you been or are you currently calling API endpoints from OpenAI, ElevenLabs, etc? Do you have labeled audio data sitting around gathering dust? Let's talk! Join https://discord.gg/QuGxSWBfQy or comment down below.

If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.

What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. ❤️

More details at hexgrad/Kokoro-82M#21

18 replies

·

upvoted a paper 6 days ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published 7 days ago • 218

liked a model 7 days ago

ICTNLP/llava-mini-llama-3.1-8b

Image-Text-to-Text • Updated 2 days ago • 3.04k • 32

reacted to alielfilali01's post with 👍 7 days ago

Post

1757

3C3H AraGen Leaderboard welcomes today deepseek-ai/DeepSeek-V3 and 12 other models (including the late gpt-3.5 💀) to the ranking of best LLMs in Arabic !

Observations:
- DeepSeek-v3 ranked 3rd and only Open model among the top 5 !

- A 14B open model ( Qwen/Qwen2.5-14B-Instruct) outperforms gpt-3.5-turbo-0125 (from last year). This shows how much we came in advancing and supporting Arabic presence within the LLM ecosystem !

- Contrary to what observed in likelihood-acc leaderboards (like OALL/Open-Arabic-LLM-Leaderboard) further finetuned models like maldv/Qwentile2.5-32B-Instruct actually decreased the performance compared to the original model Qwen/Qwen2.5-32B-Instruct.
It's worth to note that the decrease is statiscally insignificant which imply that at best, the out-domain finetuning do not really hurts the model original capabilities acquired during pretraining.
Previous work addressed this (finetuning VS pretraining) but more investigation in this regard is required (any PhDs here ? This could be your question ...)

Check out the latest rankings: inceptionai/AraGen-Leaderboard

liked a model 7 days ago

Lightricks/LTX-Video

Image-to-Video • Updated 27 days ago • 88.4k • 860

upvoted a paper 7 days ago

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

Paper • 2501.03895 • Published 8 days ago • 48

liked a model 8 days ago

city96/HunyuanVideo-gguf

Text-to-Video • Updated 29 days ago • 63.2k • 92

reacted to bartowski's post with 👍 8 days ago

Post

5950

Switching to author_model-name

I posted a poll on twitter, and others have mentioned the interest in me using the convention of including the author name in the model path when I upload.

It has a couple advantages, first and foremost of course is ensuring clarity of who uploaded the original model (did Qwen upload Qwen2.6? Or did someone fine tune Qwen2.5 and named it 2.6 for fun?)

The second thing is that it avoids collisions, so if multiple people upload the same model and I try to quant them both, I would normally end up colliding and being unable to upload both

I'll be implementing the change next week, there are just two final details I'm unsure about:

First, should the files also inherit the author's name?

Second, what to do in the case that the author name + model name pushes us past the character limit?

Haven't yet decided how to handle either case, so feedback is welcome, but also just providing this as a "heads up"