Activity Feed

AI & ML interests

None defined yet.

Recent Activity

ehristoforuΒ 
posted an update 1 day ago
view post
Post
45
πŸš€ REV LLM: Open Models, Reworked with Intent

REV LLM is an independent project focused on improving open-weight language and multimodal models through fine-tuning, LoRA training, distillation, and model merging.

Rev-Qwen3.5-2B

Rev-Qwen3.5-2B is the first release, based on Qwen/Qwen3.5-2B.

The model focuses on communication, translation, mathematics, science, medicine, coding, and agent functions.

- Model: ehristoforu/rev-qwen3.5-2b
- Collection: https://huggingface.co/collections/ehristoforu/rev-llm-models
- License: Apache-2.0, inherited from the base model

The release combines fine-tuned model merging with a LoRA trained through distillation from open-weight flagship models.
victorΒ 
posted an update 2 days ago
view post
Post
147
In case you haven’t seen (or tried) it yet: Ava is an AI character you can talk to face to face, right in your browser πŸ™‚

townbox/ava

- No login, nothing to install
- Runs 100% in the browser via WebGPU
- Powered by LiquidAI/LFM3-Omni-2B-GGUF, running locally on your device via WebGPU
- Your conversations stay on your machine

Really bullish on 100% local experiences lately. No backend inference bill, no account to create, and you keep your data.
fffiloniΒ 
posted an update 17 days ago
view post
Post
506
I’ve been building IDOL Commons πŸ—Ώ

A place to create, share and explore 3D Gaussian splats, powered by IDOL from Sperid Labs.

Start with an image, or generate one from a prompt. Inspect the result in 3D, choose its thumbnail, add a description and credits, then decide whether to publish it to the community collection.

Browse what others have shared and download the original PLY files, with attribution and per-object licensing.

I’d love to see what you contribute β€” and hear what would make this useful in your workflow.

Try it:
fffiloni/idol-commons

Community dataset:
fffiloni/idol-community-assets
  • 1 reply
Β·
TonicΒ 
posted an update 18 days ago
view post
Post
434
πŸ‘‹Hey there folks ,

I wanted to use a Jev model in a practical way , and I came up with this OCR pipeline using decision-models to evaluate OCR quality .

Check it out :

Tonic/OCR-with-JEV
  • 4 replies
Β·
fffiloniΒ 
posted an update 26 days ago
view post
Post
2,810
Carbon-X brings DNA and language together: it reads sequences and answers questions about them 🧬

To accompany the release article, I put together Carbon-X Playground: five experiments exploring sequence completion, single-letter changes, regulatory roles, DNA origins and motif finding.

Try curated samples or your own sequences, ask questions and compare answers with references when available.

Built with Gradio, running on ZeroGPU.

πŸ“– HuggingFaceBio/Carbon-X-Release
🧬 fffiloni/Carbon-X-Playground
fffiloniΒ 
posted an update about 1 month ago
view post
Post
467
πŸ“– A gamebook you can play in your own words, powered by local Decision Models.

Traditional gamebooks offer explicit branches: β€œTo enter the forest, turn to page 42.” In Choose your own adventure, you can describe an action, question a character, or ask what you already know before deciding. Clickable choices remain available.

The story’s branches and consequences are authored. Natural language adds a flexible way to interact with them, with conversations between actions.

I built this project to explore a concrete role for Decision Models in an interactive application:

β€’ Kev-4B makes structured decisions: matching intentions to available actions and distinguishing acting from discussing.
β€’ Ink manages story progression, discoveries, inventory and endings.
β€’ Qwen3-8B selects dialogue responses from authored content available in the current state.

Both models run locally inside the Space through llama.cpp, using quantized GGUFs. You can inspect the model calls, scores and routing decisions directly in the interface.

The current release includes three adventures in French and English, with a pack format for adding new stories without changing the engine.

It’s still experimental, and interpretations can go wrong. I’d love feedback on how it feels to playβ€”and on this use of Decision Models to connect natural language with explicit game logic.

Try and play here: fffiloni/choose-your-own-adventure-dm πŸ€—
  • 1 reply
Β·
AtAndDevΒ 
posted an update about 1 month ago
view post
Post
5,321
@Banaxi-Tech stop hiding my comments. AND STOP STEALING PAPERS AND SPREADING MISINFORMATION.
your BGA blog is a copy of NSA (deepseek, 2025) branded under your name. literally the same top16 selected blocks, 512 local window, router over block summaries, all you did was change block size from 64 to 128.
you didnt cite NSA once but you put a β€œplease cite BGA” bibtex at the bottom.
i commented under your post and said that there is no way that you can support claims like: β€œThe Accuracy Should BE WAy better than DSA but untested yet.” you didnt run a single experiment. and the 256x isnt from BGA, its just n/2k with k=2048 so the exact same k DSA uses. if opus wrote this for you, at least read it before posting.
i commented again after you hid my comment despite it having constructive and correct feedback and you hid that too. and again.
you can hide the truth and just try to get hf post likes..... but is it really the thing that needs to be done? do you really want to take papers and make them yours while barely even changing the params?

admitting your mistakes and doing something about them needs humbleness, intelligence, humanness.
i encourage you to admit your mistakes and try to do better next time (at least read what blog your ai wrote or do proper experiments to back your stuff up).
  • 49 replies
Β·
SeverianΒ 
posted an update about 1 month ago
view post
Post
175
SlopSoup TV. A live, never-ending 24/7 pixel-art TV network inspired by old-school late night Adult Swim. No human makes any of it.

Tune in anytime: https://severian-slopsoup.hf.space or https://www.youtube.com/live/Bikb9JGy6vg?si=YPpIqLjW6y9yML6m

20+ shows in the spirit of late-night Adult Swim:

- an hourly news desk with exhausted overnight anchors
- a game show with a reigning champion
- small-claims court and a cursed cooking show
- a talk show hosted by a houseplant or a microwave
- a 1 a.m. call-in hotline
- an ’80s sitcom on a decaying VHS tape
- 4 a.m. infomercials that slide into existential dread
- wordless generative music videos
- many more shows and content added daily...

Fully AI-run: AI writes the scripts, invents new characters every episode, designs each one a unique voice, directs the camera, cuts the edit, schedules the day and runs the broadcast.

Nothing ever airs twice: a memory of everything that’s aired blocks repeated premises, jokes and characters, so every minute is new.

Real facts, delivered weird: the news, trivia and explainers are sourced and cited; the comedy is the chaos around them.

Its own engine: a custom pixel renderer with a virtual camera, lip-synced close-ups and 50+ animated sets, all running in a browser on one cloud box.

It’s weird, it’s for adults, and it never stops. Happy to answer questions about how it works.
  • 2 replies
Β·
alielfilali01Β 
posted an update about 2 months ago
view post
Post
641
multi-agents orchestration is old news by now. Try multi-teams of agents ! that is a whole different nightmare ... This is the real signal about the sparks of AGI.
mrfakenameΒ 
posted an update 2 months ago
view post
Post
3,330
We’ve been working with LAION on a voice acting arena. You listen to two models doing the same scene and compare how well they pull it off.

It’s ready to try now - would love to hear what you think πŸ™‚

https://huggingface.co/spaces/TTS-AGI/voice-acting-arena
fffiloniΒ 
posted an update 2 months ago
view post
Post
691
Been pushing Viggle Animate a bit further πŸ‘€

Viggle Mine is my take on longer, harder character replacement shots β€” crowds, distance changes, characters turning their back and reappearing.

Still experimental, but it’s getting surprisingly robust.

Try it : fffiloni/Viggle-Mine πŸ€—
AtAndDevΒ 
posted an update 3 months ago
view post
Post
2,970
SPECK 2 IS ALREADY OUT: specklabs/Speck2-140M

Pretrained on 4x more tokens than the previous releases (20b vs 5b).
Instruct tuned versions are coming soon.
Very interesting models are coming soon too (hint: super long context).

Thanks for everyone supporting!
  • 3 replies
Β·
AtAndDevΒ 
posted an update 3 months ago
view post
Post
222
SPECK1.5 IS COMING SOON!
Same 5B token budget but much better corpus quality.

Also getting a ton of downloads, thanks for everyone downloading and liking <3

specklabs
AtAndDevΒ 
posted an update 3 months ago
view post
Post
169
NEW SPECK UPDATES:

Just hit #14 and #15 with out FIRST models on Open SLM Leaderboard. The models were trained on 5B tokens, while competing with similarly sized models trained on more than 6-20x the data.

A new base model Speck1.5-140M being trained right now on a higher quality corpus and will be released soon.
SpeckChat3 is coming very soon with 1 million samples, specifically designed to post train small base models.

Also, just to clarify stuff, we will NOT release anything that is NOT MIT licensed EVER. Openness is needed in small language research.

Thanks to everyone supporting the project, and stay tuned for new releases!
AtAndDevΒ 
posted an update 3 months ago
view post
Post
1,900
SPECK UPDATES:
1 New instruct model tuned on top of Speck1-140M: specklabs/Speck1-140M-Instruct
2 Instruction tuning datasets
2 GGUFs

Much more coming soon:
Speck1.1-140M-Instruct that is post trained on SpeckChat2 will be coming very soon
New base model Speck1.5-140M is coming with a much higher quality corpus

Thanks to everyone who is already supporting the project, and stay tuned for new releases!
  • 3 replies
Β·