891
InfiniteYou-FLUX
πΈ
Flexible Photo Recrafting While Preserving Your Identity
sandik
limaku
Β·
AI & ML interests
None yet
Recent Activity
liked
a Space
27 days ago
ByteDance/InfiniteYou-FLUX
liked
a Space
27 days ago
Roblox/cube3d-interactive
reacted
to
luigi12345's
post
with π₯
27 days ago
π₯ ULTRA VIDEO COMPRESSION (300MB β 3MB!)
```
ffmpeg -i input.mp4 -vcodec libx264 -crf 28 -vf "pad=ceil(iw/2)*2:ceil(ih/2)*2" -y output.mp4
```
-i β Input β‘οΈ -vcodec libx264 β H.264 codec β‘οΈ -crf 28 β Compression (lower = better quality) β‘οΈ-vf pad=... β Even dimensions β‘οΈ -y β Overwrite
Organizations
None yet
limaku's activity
liked
2
Spaces
27 days ago
reacted to
luigi12345's
post with π₯
27 days ago
Post
2439
π₯ ULTRA VIDEO COMPRESSION (300MB β 3MB!)
-i β Input β‘οΈ -vcodec libx264 β H.264 codec β‘οΈ -crf 28 β Compression (lower = better quality) β‘οΈ-vf pad=... β Even dimensions β‘οΈ -y β Overwrite
ffmpeg -i input.mp4 -vcodec libx264 -crf 28 -vf "pad=ceil(iw/2)*2:ceil(ih/2)*2" -y output.mp4-i β Input β‘οΈ -vcodec libx264 β H.264 codec β‘οΈ -crf 28 β Compression (lower = better quality) β‘οΈ-vf pad=... β Even dimensions β‘οΈ -y β Overwrite
- 4 replies
reacted to
ZennyKenny's
post with β€οΈ
27 days ago
Post
1934
Besides being the coolest named benchmark in the game, HellaSwag is an important measurement of Π·Π΄ΡΠ°Π²ΡΠΉ ΡΠΌΡΡΠ»Ρ (or common sense) in LLMs.
- More on HellaSwag: https://github.com/rowanz/hellaswag
I spent the afternoon benchmarking YandexGPT Pro 4th Gen, one of the Russian tech giant's premier models.
- Yandex HF Org:
yandex
- More on Yandex models: https://yandex.cloud/ru/docs/foundation-models/concepts/yandexgpt/models
The eval notebook is available on GitHub and the resulting dataset is already on the HF Hub!
- Eval Notebook: https://github.com/kghamilton89/ai-explorer/blob/main/yandex-hellaswag/hellaswag-assess.ipynb
- Eval Dataset: ZennyKenny/yandexgptpro_4th_gen-hellaswag
And of course, everyone wants to see the results so have a look at the results in the context of other zero-shot experiments that I was able to find!
- More on HellaSwag: https://github.com/rowanz/hellaswag
I spent the afternoon benchmarking YandexGPT Pro 4th Gen, one of the Russian tech giant's premier models.
- Yandex HF Org:
yandex
- More on Yandex models: https://yandex.cloud/ru/docs/foundation-models/concepts/yandexgpt/models
The eval notebook is available on GitHub and the resulting dataset is already on the HF Hub!
- Eval Notebook: https://github.com/kghamilton89/ai-explorer/blob/main/yandex-hellaswag/hellaswag-assess.ipynb
- Eval Dataset: ZennyKenny/yandexgptpro_4th_gen-hellaswag
And of course, everyone wants to see the results so have a look at the results in the context of other zero-shot experiments that I was able to find!
-
- 2 replies
reacted to
giux78's
post with β€οΈ
27 days ago
Post
3181
This is truly an inspirational story please help us spread the word,
@clem
,
@thomwolf
and everyone who supports open source AI.
A few weeks ago, @mmuffo94 and @cittiberto from indigo_ai launched the Chatbot Arena for the Italian language: https://indigo.ai/it/chatbot-arena-italia/.
To our surprise, among the top-ranked models is mii-llm/maestrale-chat-v0.4-beta a carefully fine-tuned version of mistralai/Mistral-7B-v0.1, developed by @efederici and @mferraretto from
mii-llm
, and released nearly a year ago.
At this very moment, as shown in the screenshot, mii-llm/maestrale-chat-v0.4-beta is ranked 8th right between ChatGPT-4.5 and ChatGPT-4o.
It's likely that for several months, the best Italian speaking LLM has been an open source 7B model created by open source contributors and hardly anyone knew it.
A few weeks ago, @mmuffo94 and @cittiberto from indigo_ai launched the Chatbot Arena for the Italian language: https://indigo.ai/it/chatbot-arena-italia/.
To our surprise, among the top-ranked models is mii-llm/maestrale-chat-v0.4-beta a carefully fine-tuned version of mistralai/Mistral-7B-v0.1, developed by @efederici and @mferraretto from
mii-llm
, and released nearly a year ago.At this very moment, as shown in the screenshot, mii-llm/maestrale-chat-v0.4-beta is ranked 8th right between ChatGPT-4.5 and ChatGPT-4o.
It's likely that for several months, the best Italian speaking LLM has been an open source 7B model created by open source contributors and hardly anyone knew it.
-
- 2 replies
reacted to
nroggendorff's
post with π€
27 days ago
Post
2376
I'm not really doing much on HuggingFace right now due to their new Docker space policies, so if you want to keep up with most of what I'm up to, follow my [instagram](https://sly.sh/ig)
- 11 replies