🏗️ Building on HF

Ahmet

atasoglu

34 291 1533

https://atasoglu.github.io/

AI & ML interests

NLP, LLMs.

Recent Activity

liked a model about 10 hours ago

furkanbekmezci/turkextract-turkish-information-extraction

liked a model about 10 hours ago

furkanbekmezci/atif-turkish-attribution-verifier

liked a dataset about 10 hours ago

furkanbekmezci/atif-turkish-attribution-data

View all activity

Organizations

reacted to erayyapagci's post with 🔥 3 days ago

Post

🎙️ balbal-v1: a 15M-active-parameter Turkish speech recognizer, open weights.

• 11.93% WER on Mu-Bench (real Turkish phone calls, official harness). Best among the open models I tested: Qwen3-ASR 1.7B 13.95, Whisper large-v3 14.92 on the same clips and scoring.
• ~96× real time on CPU (8 threads, batch 1). No GPU needed.
• 45M stored / 15M active parameters: Conformer-CTC + a 3-pass shared refiner + a 30M-slot product-key memory, decoded with KenLM.

It started as a synthetic-data experiment: can TTS speech stand in for real recordings? About 70% of the final training audio is synthetic.

🤗 Weights: erayyapagci/balbal-v1
🕹️ Demo: erayyapagci/balbal-v1-demo
📝 How it was built: https://erayy.com/balbal-blog
💻 Code: https://github.com/erayyap/balbal

reacted to pollix's post with 🔥 about 1 month ago

Post

949

Built a Space for stuntd: pollix/stuntd

For each question it shows the same answer twice: zero-shot Laya, and a small head trained on the frozen Laya encoder. You get the option probabilities, the confidence threshold and the latency. When the head isn't sure, it hands the question back to the teacher instead of guessing.

On jevbench, same machine, n=500: agnews 86.0 → 92.6, banking77 38.2 → 69.6. Everything runs locally; heads train in 4-20 minutes on a laptop GPU.

Code (Apache-2.0): https://github.com/bladedevoff/stuntd

reacted to imnotkitty's post with 🔥 9 months ago

Post

2,216

👀Just published a first-look at tencent/HunyuanImage-3.0-Instruct

Tested its multi-image fusion and single-reference consistency. The results on complex prompts are quite impressive.

What’s the most creative image task you’d give it?

👉 Read the full analysis: https://huggingface.co/blog/imnotkitty/tencent-hy-image-v30-i2i

8 replies

posted an update 12 months ago

Post

2,070

Introducing ToolsGen 🛠️

I built a tool to solve a problem I kept running into: creating quality datasets for training LLMs to use tools.

ToolsGen takes your JSON tool definitions and automatically generates realistic user requests, corresponding tool calls, and evaluates them using an LLM-as-a-judge pipeline. It outputs datasets ready to use with Hugging Face.

What makes it useful:
- Generates realistic user requests + tool calls from JSON definitions
- LLM-as-a-judge quality scoring with multi-dimensional rubrics
- Multiple sampling strategies (random, parameter-aware, semantic)
- OpenAI-compatible API support
- Outputs JSONL with train/val splits

Still early days (API isn't stable yet), but it's already helping me generate tool-calling datasets much faster.

Check it out: https://github.com/atasoglu/toolsgen

Happy to hear feedback or ideas!

reacted to danielhanchen's post with 🔥 over 1 year ago

Post

4,146

Made some 245GB (80% size reduction) 1.8bit quants for Kimi K2!

unsloth/Kimi-K2-Instruct-GGUF

reacted to merve's post with 🚀 over 1 year ago

Post

3,208

GitHub refuses to render notebooks for a long time now 💔

so smol-vision now lives in Hugging Face model repository 🤗 merve/smol-vision

1 reply

reacted to merve's post with 🔥 over 1 year ago

Post

3,543

ByteDance released Tar 1.5B and 7B: image-text in image-text out models, fully open-source 👏 ByteDance-Seed/tar-6864cf0d9fe59a3b91cc4260

They have an image tokenizer unified with text, and they de-tokenize using either of two models (LLM and diffusion)
The model is actually a full LLM (Qwen2), the tokenizer converts image tokens 🤯

reacted to ProCreations's post with 🔥 over 1 year ago

Post

2,960

20 FOLLOWERS IN LESS THAN A DAY? YA'LL ARE CRAZY!

We zoomed pass 70, 80, and 90 followers in a day. That is insane.

As a thank you, ive published one of my largest and most expensive dataset (rip my 2 dollars, most of my datasets are free to make) to the hub. To be used for text summarization in english, check it out! ProCreations/simple-summaries

1 reply

reacted to ProCreations's post with 👀 over 1 year ago

Post

4,789

Transformers are getting old! It’s been 8 whole years since the architecture that powers almost all language models.

Read here for newer alternatives and variants of transformers:
https://huggingface.co/blog/ProCreations/transformers-are-getting-old

reacted to merve's post with 🔥 over 1 year ago

Post

3,742

Huge drops in open AI past week!
Find more models, datasets, demos here merve/releases-july-4-686bcc54ed7c45c341fbf654
Some of our picks 🫡
⏯️ BAAI/MTVCraft is a new Veo3-like text-to-video model, demo is here BAAI/MTVCraft
🧑🏻‍💻 apple/diffucoder-6868139f56672ae046fe04e8 is a new family of diffusion LLMs (7B base and instruct) for coding
🗣️ kyutai/tts-1.6b-en_fr is a new small TTS model for English and France
👀 aharley/alltracker is a new pixel tracking model by Stanford, demo is here aharley/alltracker
📖 https://huggingface.co/datasets/racineai/OGC_MEGA_MultiDomain_DocRetrieval is a new large visual document retrieval dataset

1 reply

replied to merve's post over 1 year ago

Thanks @merve ! Super helpful roundup as always 🙌🔥

reacted to merve's post with 🔥 over 1 year ago

Post

5,145

VLMS 2025 UPDATE 🔥

We just shipped a blog on everything latest on vision language models, including
🤖 GUI agents, agentic VLMs, omni models
📑 multimodal RAG
⏯️ video LMs
🤏🏻 smol models
..and more! https://huggingface.co/blog/vlms-2025

1 reply

reacted to ngxson's post with 🚀 over 1 year ago

Post

7,083

A comprehensive matrix for which format should you use.

Read more on my blog post: https://huggingface.co/blog/ngxson/common-ai-model-formats

| Hardware        | GGUF      | PyTorch                | Safetensors              | ONNX  |
|-----------------|-----------|------------------------|--------------------------|-------|
| CPU             | ✅ (best) | 🟡                      | 🟡                       | ✅    |
| GPU             | ✅        | ✅                      | ✅                       | ✅    |
| Mobile          | ✅        | 🟡 (via executorch)     | ❌                       | ✅    |
| Apple silicon   | ✅        | 🟡                      | ✅ (via MLX framework)   | ✅    |

reacted to merve's post with ❤️ over 1 year ago

Post

5,328

Your weekly recap of open AI is here, and it's packed with models! merve/feb-14-releases-67af876b404cc27c6d837767

👀 Multimodal
> OpenGVLab released InternVideo 2.5 Chat models, new video LMs with long context
> AIDC released Ovis2 model family along with Ovis dataset, new vision LMs in different sizes (1B, 2B, 4B, 8B, 16B, 34B), with video and OCR support
> ColQwenStella-2b is a multilingual visual retrieval model that is sota in it's size
> Hoags-2B-Exp is a new multilingual vision LM with contextual reasoning, long context video understanding

💬 LLMs
A lot of math models!
> Open-R1 team released OpenR1-Math-220k large scale math reasoning dataset, along with Qwen2.5-220K-Math fine-tuned on the dataset, OpenR1-Qwen-7B
> Nomic AI released new Nomic Embed multilingual retrieval model, a MoE with 500 params with 305M active params, outperforming other models
> DeepScaleR-1.5B-Preview is a new DeepSeek-R1-Distill fine-tune using distributed RL on math
> LIMO is a new fine-tune of Qwen2.5-32B-Instruct on Math

🗣️ Audio
> Zonos-v0.1 is a new family of speech recognition models, which contains the model itself and embeddings

🖼️ Vision and Image Generation
> We have ported DepthPro of Apple to transformers for your convenience!
> illustrious-xl-v1.0 is a new illustration generation model

3 replies

reacted to merve's post with 🚀 almost 2 years ago

Post

2,350

smolagents can see 🔥
we just shipped vision support to smolagents 🤗 agentic computers FTW

you can now:
💻 let the agent get images dynamically (e.g. agentic web browser)
📑 pass images at the init of the agent (e.g. chatting with documents, filling forms automatically etc)
with few LoC change! 🤯
you can use transformers models locally (like Qwen2VL) OR plug-in your favorite multimodal inference provider (gpt-4o, antrophic & co) 🤠

read our blog http://hf.co/blog/smolagents-can-see

reacted to merve's post with 🔥 almost 2 years ago

Post

5,691

Oof, what a week! 🥵 So many things have happened, let's recap! merve/jan-24-releases-6793d610774073328eac67a9

Multimodal 💬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG 💗
- UI-TARS are new models by ByteDance to unlock agentic GUI control 🤯 in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark

LLMs 📖
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! 🤯
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)

Audio 🗣️
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO

Image/Video/3D Generation ⏯️
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images

7 replies

reacted to merve's post with 🔥 almost 2 years ago

Post

4,974

supercharge your LLM apps with smolagents 🔥

however cool your LLM is, without being agentic it can only go so far

enter smolagents: a new agent library by Hugging Face to make the LLM write code, do analysis and automate boring stuff!

Here's our blog for you to get started https://huggingface.co/blog/smolagents

reacted to merve's post with ❤️ almost 2 years ago

Post

5,793

This week in open-source AI was insane 🤠 A small recap🕺🏻 merve/dec-6-releases-67545caebe9fc4776faac0a3

Multimodal 🖼️
> Google shipped a PaliGemma 2, new iteration of PaliGemma with more sizes: 3B, 10B and 28B, with pre-trained and captioning variants 👏
> OpenGVLab released InternVL2, seven new vision LMs in different sizes, with sota checkpoint with MIT license ✨
> Qwen team at Alibaba released the base models of Qwen2VL models with 2B, 7B and 72B ckpts

LLMs 💬
> Meta released a new iteration of Llama 70B, Llama3.2-70B trained further
> EuroLLM-9B-Instruct is a new multilingual LLM for European languages with Apache 2.0 license 🔥
> Dataset: CohereForAI released GlobalMMLU, multilingual version of MMLU with 42 languages with Apache 2.0 license
> Dataset: QwQ-LongCoT-130K is a new dataset to train reasoning models
> Dataset: FineWeb2 just landed with multilinguality update! 🔥 nearly 8TB pretraining data in many languages!

Image/Video Generation 🖼️
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux

Audio 🔊
> Indic-Parler-TTS is a new text2speech model made by community

reacted to merve's post with ❤️ almost 2 years ago

Post

1,548

Apple released AIMv2 🍏 a family of state-of-the-art open-set vision encoders
apple/aimv2-6720fe1558d94c7805f7688c
> like CLIP, but add a decoder and train on autoregression 🤯
> 19 open models come in 300M, 600M, 1.2B, 2.7B with resolutions of 224, 336, 448
> Load and use with 🤗 transformers

reacted to ezgikorkmaz's post with 🚀 almost 2 years ago

Post

2,109

I wrote a recent survey about deep reinforcement learning. The paper is a compact guide to understand some of the key concepts in reinforcement learning. Find the paper below:

Paper: https://arxiv.org/pdf/2401.02349v2
Twitter: https://x.com/EzgiKorkmazAI/status/1851934161138798615

Ahmet

AI & ML interests

Recent Activity

Organizations

atasoglu's activity