appvoid's picture

appvoid

appvoid

AI & ML interests

training small language models aiming to high-quality text | fine-tuning + merging expert

Recent Activity

updated a model 1 day ago
appvoid/arco-2
updated a collection 5 days ago
favorite models
liked a model 5 days ago
Datou1111/shou_xin
View all activity

Organizations

ZeroGPU Explorers's profile picture Social Post Explorers's profile picture

appvoid's activity

reacted to KnutJaegersberg's post with ๐Ÿ‘ 5 days ago
reacted to alielfilali01's post with ๐Ÿค— 11 days ago
view post
Post
3295
Unpopular opinion: Open Source takes courage to do !

Not everyone is brave enough to release what they have done (the way they've done it) to the wild to be judged !
It really requires a high level of "knowing wth are you doing" ! It's kind of a super power !

Cheers to the heroes here who see this!
ยท
reacted to merve's post with ๐Ÿ”ฅ about 1 month ago
view post
Post
4994
OmniVision-968M: a new local VLM for edge devices, fast & small but performant
๐Ÿ’จ a new vision language model with 9x less image tokens, super efficient
๐Ÿ“– aligned with DPO for reducing hallucinations
โšก๏ธ Apache 2.0 license ๐Ÿ”ฅ

Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model https://huggingface.co./NexaAIDev/omnivision-968M
  • 4 replies
ยท
reacted to m-ric's post with ๐Ÿš€ about 2 months ago
view post
Post
1630
๐—”๐—ป๐—ฑ๐—ฟ๐—ผ๐—ถ๐—ฑ๐—Ÿ๐—ฎ๐—ฏ: ๐—™๐—ถ๐—ฟ๐˜€๐˜ ๐—ฒ๐˜ƒ๐—ฒ๐—ฟ ๐˜€๐˜†๐˜€๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ ๐—ฏ๐—ฒ๐—ป๐—ฐ๐—ต๐—บ๐—ฎ๐—ฟ๐—ธ ๐—ณ๐—ผ๐—ฟ ๐—”๐—ป๐—ฑ๐—ฟ๐—ผ๐—ถ๐—ฑ ๐—บ๐—ผ๐—ฏ๐—ถ๐—น๐—ฒ ๐—ฎ๐—ด๐—ฒ๐—ป๐˜๐˜€ ๐˜€๐—ต๐—ผ๐˜„๐˜€ ๐˜๐—ต๐—ฎ๐˜ ๐˜€๐—บ๐—ฎ๐—น๐—น, ๐—ณ๐—ถ๐—ป๐—ฒ-๐˜๐˜‚๐—ป๐—ฒ๐—ฑ ๐—ผ๐—ฝ๐—ฒ๐—ป ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€ ๐—ฐ๐—ฎ๐—ป ๐—ฝ๐—ผ๐˜„๐—ฒ๐—ฟ ๐—ฎ ๐—๐—”๐—ฅ๐—ฉ๐—œ๐—ฆ ๐˜€๐˜†๐˜€๐˜๐—ฒ๐—บ ๐—ผ๐—ป ๐˜†๐—ผ๐˜‚๐—ฟ ๐˜€๐—บ๐—ฎ๐—ฟ๐˜๐—ฝ๐—ต๐—ผ๐—ป๐—ฒ ๐Ÿ“ฑ๐Ÿ”ฅ

A team from Tsinghua University just released AndroidLab, the first systematic framework to evaluate and train Android mobile agents that works with both text-only and multimodal models.

They show that fine-tuning small open-source models can significantly boost performance, matching that of much bigger closed models like GPT-4o.

The team built:

๐Ÿ“Šย A reproducible benchmark with 138 tasks across 9 apps to evaluate mobile agents systematically

๐Ÿ“๐Ÿ“ฑย A framework supporting both text-only (via XML) and visual (via marked screenshots) interfaces

โœ…ย An instruction dataset of 10.5k operation traces for training mobile agents

Key insights:

- ๐Ÿ“ˆ Fine-tuning improves performance BY A LOT: Open-source model Llama-3.1-8B improves from 2% to 24% success rate after training, nearly reaching GPT-4o performance although itโ€™s much smaller
- โš™๏ธ Text-only agents match multimodal ones: XML-based agents achieve similar performance to screenshot-based multimodal agents.

Read their paper here ๐Ÿ‘‰ AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2410.24024)
reacted to KnutJaegersberg's post with ๐Ÿค— 2 months ago
posted an update 2 months ago
view post
Post
1349
If someone would like to keep pushing the limits of what's possible on cpu while being efficient/fast, here's my un-trained arco model scaled-up to 770m parameters. Consider it a modern gpt-2-large to experiment with
appvoid/arco-plus
replied to their post 3 months ago
view reply

How long did it take to reply and what are your context window limits? Model type?

it takes 3-5 seconds to reply when the prompt is longer than 30-50 words on average but it increases linearly with number of tokens in the prompt, the one on the picture is llama 3 1b but the one i'm using right now is arco 2 which is a llama model, cannot keep any kind of general knowledge, i noticed with qwen 2 (and later confirmed with meta's model) that you don't need a lot of parameters to get general knowledge, you just need tons of data

posted an update 3 months ago
view post
Post
3375
700m parameters are the sweet spot for cpu usage, please let's make more of those!
  • 2 replies
ยท
posted an update 3 months ago
view post
Post
1824
meta just released 1b parameters model and to honor it i released arco 2 just in time for the fine-tuners to tweak around, enjoy these small powerful language models!!!

meta-llama/Llama-3.2-1B
appvoid/arco-2
  • 1 reply
ยท
posted an update 3 months ago
view post
Post
759
WHY ARE THERE NOT TEXT FEWSHOT DATASETS @ HUGGINGFACE? ๐Ÿ˜ฒ
reacted to zolicsaki's post with ๐Ÿ”ฅ 3 months ago
view post
Post
1293
Fast inference is no longer a nice-to-have demo; it will be the driving force behind future frontier models. Time to switch over to custom AI hardware and short Nvidia.

Try out SambaNova's lightning fast API for free at https://sambanova.ai/fast-api?api_ref=444868
reacted to KnutJaegersberg's post with โค๏ธ 3 months ago
view post
Post
1175
appvoid/arco

arco consistently outperforms every sota model below 600m parameters on average

appvoid/arco
posted an update 4 months ago
view post
Post
1282
i just made the best 0.5b model to date (again)

its name is arco and is ready to fight any 0.5b model at arc challenge

appvoid/arco
replied to clem's post 4 months ago
view reply

as a model-tweaker is such a huge relief to know we have hf for years to come

reacted to clem's post with โค๏ธ 4 months ago
view post
Post
3678
This isnโ€™t a goal of ours because we have plenty of money in the bank but quite excited to see that @huggingfaceis profitable these days, with 220 team members and most of our platform being free (like model hosting) and open-source for the community!

Especially noteworthy at a time when most AI startups wouldnโ€™t survive a year or two without VC money. Yay!
ยท
reacted to severo's post with ๐Ÿš€ 5 months ago
view post
Post
3483
[New tool] Follow interesting ML persons ๐Ÿ‘ฉโ€๐ŸŽจ ๐Ÿ‘จโ€๐ŸŽค ๐Ÿ‘ฉโ€๐Ÿซ with Followgraph

severo/followgraph

Please try it and tell me if it helped you discover high-quality content ๐Ÿ‘ ๐Ÿ‘Ž

I repurposed "Followgraph for Mastodon" (https://followgraph.vercel.app/).

My new follows: @TheBloke @mlabonne @teknium @KnutJaegersberg @SkalskiP @AmelieSchreiber @lbourdois @ceyda @andrewyng @Pclanglais @karpathy

And you?
ยท
replied to severo's post 5 months ago
posted an update 5 months ago
view post
Post
1499
palmer-004 becomes ๐Ÿ”ฅturbo๐Ÿ”ฅ now is half the size, twice the speed and the best overall 0.5b language model in huggingface.

appvoid/palmer-004-turbo
  • 1 reply
ยท
reacted to qnguyen3's post with ๐Ÿ”ฅ 6 months ago
replied to qnguyen3's post 6 months ago