Open-OSS/privacy-filter
Token Classification ā¢ 1B ā¢ Updated ā¢ 244k ā¢ 10
Cahlen Humphreys PRO
cahlen
AI & ML interests
ā ļøš»
Recent Activity
liked a model about 14 hours ago
Open-OSS/privacy-filterOrganizations
liked a
model about 14 hours ago
reacted to BlueNipples's post with š 1 day ago
Post
2276
Good news, llama.cpp seems to be close to supporting MTP on qwen models. Bad news, every single gguf will have to be redone when it is.
- 1 reply
reacted to yuriyvnv's post with š„ 1 day ago
Post
2538
š The WAVe paper is officially out in the Information Sciences Journal.
You saw the PT and NL model releases earlier this year. This is the peer-reviewed paper behind them, with the full method, ablations, and downstream ASR evaluation.
Quick recap: WAVe is a 1B multimodal embedding model that filters synthetic speech at the word level, not the sentence level. On Portuguese ASR it cuts training steps by 34%, improves cross-domain generalization by 50%, and matches WER with 30% less synthetic data.
š¦ Resources
- Paper: https://www.sciencedirect.com/science/article/pii/S0020025526005220
- PT model: yuriyvnv/WAVe-1B-Multimodal-PT
- NL model: yuriyvnv/WAVe-1B-Multimodal-NL
- Collection: https://huggingface.co/collections/yuriyvnv/multi-modal-embeddings-for-synthetic-transcript-filtering
- Code: https://github.com/yuriyvnv/WAVe
If you train ASR on synthetic or back-translated data, would like to see WAVe benchmarked on other languages.
@reach-vb @ylacombe @hf-audio @BramVanroy
#speech #asr #multimodal #syntheticdata #lowresource
You saw the PT and NL model releases earlier this year. This is the peer-reviewed paper behind them, with the full method, ablations, and downstream ASR evaluation.
Quick recap: WAVe is a 1B multimodal embedding model that filters synthetic speech at the word level, not the sentence level. On Portuguese ASR it cuts training steps by 34%, improves cross-domain generalization by 50%, and matches WER with 30% less synthetic data.
š¦ Resources
- Paper: https://www.sciencedirect.com/science/article/pii/S0020025526005220
- PT model: yuriyvnv/WAVe-1B-Multimodal-PT
- NL model: yuriyvnv/WAVe-1B-Multimodal-NL
- Collection: https://huggingface.co/collections/yuriyvnv/multi-modal-embeddings-for-synthetic-transcript-filtering
- Code: https://github.com/yuriyvnv/WAVe
If you train ASR on synthetic or back-translated data, would like to see WAVe benchmarked on other languages.
@reach-vb @ylacombe @hf-audio @BramVanroy
#speech #asr #multimodal #syntheticdata #lowresource
reacted to unmodeled-tyler's post with š 1 day ago
Post
2129
Hey Hugging Face!
Repo: https://github.com/unmodeled-tyler/vessel-browser
I wanted to share a cool feature from my open source AI native web browser, Vessel: Persistent highlights!
You can highlight anything on the page and the context is provided to the agent. It's kind of a fun way to learn about new stuff, synthesize info, or just deepen your comprehension/understanding.
Since highlights are persistent, you can close the page, come back later - and your highlights will be exactly where you left them. I've found this particularly useful when reviewing technical blogs, model cards, etc.
Check it out!
Repo: https://github.com/unmodeled-tyler/vessel-browser
I wanted to share a cool feature from my open source AI native web browser, Vessel: Persistent highlights!
You can highlight anything on the page and the context is provided to the agent. It's kind of a fun way to learn about new stuff, synthesize info, or just deepen your comprehension/understanding.
Since highlights are persistent, you can close the page, come back later - and your highlights will be exactly where you left them. I've found this particularly useful when reviewing technical blogs, model cards, etc.
Check it out!
- 1 reply
posted an update 1 day ago
Post
103
So I built a multimodal video annotation pipeline in my spare time, as you do.
corpus-mill turns any long-form video with people on camera into a time-aligned event corpus across audio, vision, OCR, faces, brand observations, music, and clip-worthy moments. Runs entirely on local GPU because ā and I cannot stress this enough ā your footage has no business being on someone else's servers.
The honest origin: I needed real multimodal supervision data, the public corpora are weirdly thin once you need per-frame / per-speaker / per-second labels with provenance, so I built one. Then it grew. Then I looked up and it was 30K LOC and ~30 stages and I thought, ok, maybe other people would want this.
Stack is the usual suspects: Whisper-large-v3 (faster-whisper), pyannote-3.1 (which secretly drags in 433 NeMo modules ā surprise!), Qwen2.5-VL-7B for vision/OCR/shoppable detection, dlib + YuNet for faces, qwen2.5:7b / qwen3:14b via local Ollama for the LLM passes, chromaprint + PDQ for fingerprinting. Outputs as Parquet + SQLite. Apache 2.0.
There's a Docker compose that works, after I spent a day discovering that faster-whisper wants CUDA 12 cuBLAS while pyannote 4 wants CUDA 13, and the answer is "install both, point LD_LIBRARY_PATH at the cu12 wheels, ship it." That's now baked in. You're welcome.
Spare-time project, bugs are real, fixing them for your specific footage is on you. If you're training multimodal models and want a corpus pipeline you fully control on-prem, this might save you months. If not, the README is at least mildly entertaining.
https://github.com/cahlen/corpus-mill
corpus-mill turns any long-form video with people on camera into a time-aligned event corpus across audio, vision, OCR, faces, brand observations, music, and clip-worthy moments. Runs entirely on local GPU because ā and I cannot stress this enough ā your footage has no business being on someone else's servers.
The honest origin: I needed real multimodal supervision data, the public corpora are weirdly thin once you need per-frame / per-speaker / per-second labels with provenance, so I built one. Then it grew. Then I looked up and it was 30K LOC and ~30 stages and I thought, ok, maybe other people would want this.
Stack is the usual suspects: Whisper-large-v3 (faster-whisper), pyannote-3.1 (which secretly drags in 433 NeMo modules ā surprise!), Qwen2.5-VL-7B for vision/OCR/shoppable detection, dlib + YuNet for faces, qwen2.5:7b / qwen3:14b via local Ollama for the LLM passes, chromaprint + PDQ for fingerprinting. Outputs as Parquet + SQLite. Apache 2.0.
There's a Docker compose that works, after I spent a day discovering that faster-whisper wants CUDA 12 cuBLAS while pyannote 4 wants CUDA 13, and the answer is "install both, point LD_LIBRARY_PATH at the cu12 wheels, ship it." That's now baked in. You're welcome.
Spare-time project, bugs are real, fixing them for your specific footage is on you. If you're training multimodal models and want a corpus pipeline you fully control on-prem, this might save you months. If not, the README is at least mildly entertaining.
https://github.com/cahlen/corpus-mill
- 1 reply
liked 2
datasets 3 days ago
liked 3
models 3 days ago
reacted to prithivMLmods's post with š„ 6 days ago
Post
3907
Multimodal-Edge Demo, a node-based inference canvas demo, is now live on Spaces. It features node-based Transformers for fast inference across 10+ edge-device multimodal models on the Hub, all within a single space. The series includes models from Qwen3.5, Qwen3-VL, Gemma 4, and the LFM 2.5 VL model series, with support for reasoning and grounding tasks.
š¤ Demo: prithivMLmods/Multimodal-Edge-Node
š GitHub: https://github.com/PRITHIVSAKTHIUR/Multimodal-Edge-Node
ā Multimodal Apps Collections: https://huggingface.co/collections/prithivMLmods/hall-of-multimodal-apps
š¤ > To learn more, visit the app page or the respective model pages.
š¤ Demo: prithivMLmods/Multimodal-Edge-Node
š GitHub: https://github.com/PRITHIVSAKTHIUR/Multimodal-Edge-Node
ā Multimodal Apps Collections: https://huggingface.co/collections/prithivMLmods/hall-of-multimodal-apps
š¤ > To learn more, visit the app page or the respective model pages.
liked a
model 7 days ago
reacted to SeaWolf-AI's post with š 8 days ago
Post
5032
š Introducing Model Galaxy ā a Living, Multimodal Fork of the HF Model Atlas
š Try it: FINAL-Bench/model-galaxy
This Space is a fork of the brilliant Eliahu/Model-Atlas, the official demo of "Charting and Navigating Hugging Face's Model Atlas" (Horwitz et al., arXiv 2503.10633). Their pre-computed HF model graph is the foundation of every node and edge you see, and we are deeply grateful for its open release.
The original atlas is a static snapshot of early 2025. Model Galaxy turns it into a living, multimodal map. We injected the 2026 trending originals that did not exist when the atlas was frozen ā DeepSeek-V4, Hy3-preview, GLM-5.1, Kimi-K2, gpt-oss, Nemotron-3 Super / Nano / Omni, Hermes-4.3, Qwen3-Coder-Next, Llama-3.3, Granite-4.1, plus the latest multimodal releases (FLUX.2, ERNIE-Image, HunyuanImage / Video, LTX-2.3, Wan2.2, Kokoro-82M, VoxCPM2, Voxtral-TTS, whisper-v3-turbo, Gemma-4, Qwen3-Omni, Phi-4-mm) ā each with proper base_model lineage edges.
We also added the complete VIDRAFT Darwin family ontology: 120 nodes covering Darwin Core, AETHER, every brand variant (Rogue, AWAXIS, TenOS, Warecube), NOESIS-Darwin multimodal extensions, and 40+ community quantizations ā the most complete Darwin lineage view anywhere.
The name "Galaxy" is now literal: our three injected clusters are re-laid out as logarithmic spiral galaxies, with bigger models near the bright cores and quantizations scattering to the outer arms ā just like real star mass distribution. A top-right toggle switches between Galaxy mode (deep-space gradient with 220 animated stars) and Atlas mode (clean white panels for reports). A 15-second progress bar narrates the render, and per-modality / per-company colors make every cluster legible at a glance.
Final scale: 22,480 nodes in the default Modalities atlas, 137,324 in the Large NLP atlas, and a 277-node compact Darwin + Trending view for instant exploration. Feedback and PRs welcome.
š Try it: FINAL-Bench/model-galaxy
This Space is a fork of the brilliant Eliahu/Model-Atlas, the official demo of "Charting and Navigating Hugging Face's Model Atlas" (Horwitz et al., arXiv 2503.10633). Their pre-computed HF model graph is the foundation of every node and edge you see, and we are deeply grateful for its open release.
The original atlas is a static snapshot of early 2025. Model Galaxy turns it into a living, multimodal map. We injected the 2026 trending originals that did not exist when the atlas was frozen ā DeepSeek-V4, Hy3-preview, GLM-5.1, Kimi-K2, gpt-oss, Nemotron-3 Super / Nano / Omni, Hermes-4.3, Qwen3-Coder-Next, Llama-3.3, Granite-4.1, plus the latest multimodal releases (FLUX.2, ERNIE-Image, HunyuanImage / Video, LTX-2.3, Wan2.2, Kokoro-82M, VoxCPM2, Voxtral-TTS, whisper-v3-turbo, Gemma-4, Qwen3-Omni, Phi-4-mm) ā each with proper base_model lineage edges.
We also added the complete VIDRAFT Darwin family ontology: 120 nodes covering Darwin Core, AETHER, every brand variant (Rogue, AWAXIS, TenOS, Warecube), NOESIS-Darwin multimodal extensions, and 40+ community quantizations ā the most complete Darwin lineage view anywhere.
The name "Galaxy" is now literal: our three injected clusters are re-laid out as logarithmic spiral galaxies, with bigger models near the bright cores and quantizations scattering to the outer arms ā just like real star mass distribution. A top-right toggle switches between Galaxy mode (deep-space gradient with 220 animated stars) and Atlas mode (clean white panels for reports). A 15-second progress bar narrates the render, and per-modality / per-company colors make every cluster legible at a glance.
Final scale: 22,480 nodes in the default Modalities atlas, 137,324 in the Large NLP atlas, and a 277-node compact Darwin + Trending view for instant exploration. Feedback and PRs welcome.
liked 2
datasets 13 days ago
Great quant!!
12
#6 opened 17 days ago
by 
tasticleeze
liked a
model 13 days ago
reacted to anakin87's post with ā¤ļøš„ 14 days ago
Post
3278
A small model that struggled against a random opponent now beats GPT-5-mini at tic-tac-toe
I took LiquidAI/LFM2-2.6B and trained it through play.
š§āš³ Here's how:
1ļøā£ Build a solid RL env with Verifiers (Prime Intellect)
2ļøā£ Generate synthetic data: <200 games sampled from GPT-5-mini playing in the env
3ļøā£ SFT warm-up to teach format
4ļøā£ Group-based RL (CISPO) against opponents making 20-70% random moves
5ļøā£ RL again with stronger opponents (0-25% random moves) + 1.25 temperature to push exploration and shake off suboptimal strategies
Done! Beats GPT-5-mini š
---
š® Play against the model: anakin87/LFM2-2.6B-mr-tictactoe
š¤ Model: anakin87/LFM2-2.6B-mr-tictactoe
š Walkthrough/course: https://github.com/anakin87/llm-rl-environments-lil-course
š¤ Dataset and checkpoints: https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
I took LiquidAI/LFM2-2.6B and trained it through play.
š§āš³ Here's how:
1ļøā£ Build a solid RL env with Verifiers (Prime Intellect)
2ļøā£ Generate synthetic data: <200 games sampled from GPT-5-mini playing in the env
3ļøā£ SFT warm-up to teach format
4ļøā£ Group-based RL (CISPO) against opponents making 20-70% random moves
5ļøā£ RL again with stronger opponents (0-25% random moves) + 1.25 temperature to push exploration and shake off suboptimal strategies
Done! Beats GPT-5-mini š
---
š® Play against the model: anakin87/LFM2-2.6B-mr-tictactoe
š¤ Model: anakin87/LFM2-2.6B-mr-tictactoe
š Walkthrough/course: https://github.com/anakin87/llm-rl-environments-lil-course
š¤ Dataset and checkpoints: https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
liked a
dataset 14 days ago