Post
81
Created a new benchmark called "Sleight of Word" (Accepted at INLG 2026)
https://fractalego.github.io/Sleight-of-Word/
https://arxiv.org/abs/2608.29921
https://fractalego.github.io/Sleight-of-Word/
https://arxiv.org/abs/2608.29921
Alberto Cetoli PRO
fractalego
AI & ML interests
Entity/relation extraction, Q&A, Summarisation
Recent Activity
updated a model 4 months ago
fractalego/gemma-4-12B-it-grpo-swebench published a model 4 months ago
fractalego/gemma-4-12B-it-grpo-swebenchOrganizations
posted an update 4 days ago
reacted to mitkox's post with 😎 about 1 year ago
Post
2134
I run Qwen3-Coder 480B locally on my Z8, with a 1-million token context window. It’s the equivalent of parallel-parking a Nimitz-class carrier in a kiddie pool. Thanks to whatever dark pact the llama.cpp, CUDA, and kernel folks signed, hybrid inferencing + VRAM↔RAM offload let me stream the model’s synapses across Xeon, RAM, and four lonely A6000s without summoning either the OOM killer or a small house fire.
reacted to merve's post with 🔥 over 1 year ago
Post
3078
Qwen2.5-Omni is soooo good that people build multimodal reasoning models off of it 🥹
> KE-Team/Ke-Omni-R-3B is open-source audio reasoning model sota on average of benchmarks, based on Qwen/Qwen2.5-Omni-3B 🗣️
> Haoz0206/Omni-R1 is a video reasoning model with pixel level grounding (see below) and it's super competitive ⏯️ based on Qwen/Qwen2.5-Omni-7B
> KE-Team/Ke-Omni-R-3B is open-source audio reasoning model sota on average of benchmarks, based on Qwen/Qwen2.5-Omni-3B 🗣️
> Haoz0206/Omni-R1 is a video reasoning model with pixel level grounding (see below) and it's super competitive ⏯️ based on Qwen/Qwen2.5-Omni-7B
reacted to jeffboudier's post with 🚀 over 1 year ago
Post
2656
Transcribing 1 hour of audio for less than $0.01 🤯
@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!
How they did it: https://huggingface.co/blog/fast-whisper-endpoints
1-click deploy with HF Inference Endpoints: https://huggingface.co/proxy/endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws®ion=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!
How they did it: https://huggingface.co/blog/fast-whisper-endpoints
1-click deploy with HF Inference Endpoints: https://huggingface.co/proxy/endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws®ion=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
reacted to BrigitteTousi's post with 🔥🚀 over 1 year ago
Post
3476
LeRobot goes to driving school! 🚗🚗🚗
Hugging Face just announced a new collab with Yaak to bring the largest open-source self-driving dataset to LeRobot!
Major kudos to HF's @cadene , as well as @sandhawalia , @Shnissen and the Yaak team!
Check out the blog post here: https://huggingface.co/blog/lerobot-goes-to-driving-school
Hugging Face just announced a new collab with Yaak to bring the largest open-source self-driving dataset to LeRobot!
Major kudos to HF's @cadene , as well as @sandhawalia , @Shnissen and the Yaak team!
Check out the blog post here: https://huggingface.co/blog/lerobot-goes-to-driving-school
- 1 reply
reacted to csabakecskemeti's post with 🔥 over 1 year ago
Post
3038
Testing Training on AMD/ROCm the first time!
I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)
For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.
Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.
I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)
For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.
Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.
- 8 replies
reacted to burtenshaw's post with 🔥 over 1 year ago
Post
6564
Now the Hugging Face agent course is getting real! With frameworks like smolagents, LlamaIndex, and LangChain.
🔗 Follow the org for updates
agents-course
This week we are releasing the first framework unit in the course and it’s on smolagents. This is what the unit covers:
- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use
The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .
🔗 Follow the org for updates
This week we are releasing the first framework unit in the course and it’s on smolagents. This is what the unit covers:
- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use
The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .
reacted to csabakecskemeti's post with 👍 over 1 year ago
Post
1643
I found if we apply the reasoning system prompt (that has been published on the NousResearch/DeepHermes-3-Llama-3-8B-Preview model card) other models are also react to it and start mimicking reasoning. Some better some worse. I've seen internal monologue and self questioning.
Here's a blogpost about it:
http://devquasar.com/ai/reasoning-system-prompt/
Here's a blogpost about it:
http://devquasar.com/ai/reasoning-system-prompt/
reacted to mmhamdy's post with 👍 over 1 year ago
Post
3044
⛓ Evaluating Long Context #2: SCROLLS and ZeroSCROLLS
In this series of posts about tracing the history of long context evaluation, we started with Long Range Arena (LRA). Introduced in 2020, Long Range Arens (LRA) is one of the earliest benchmarks designed to tackle the challenge of long context evaluation. But it wasn't introduced to evaluate LLMs, but rather the transformer architecture in general.
📜 The SCROLLS benchmark, introduced in 2022, addresses this gap in NLP/LLM research. SCROLLS challenges models with tasks that require reasoning over extended sequences (according to 2022 standards). So, what does it offer?
1️⃣ Long Text Focus: SCROLLS (unlike LRA) focus mainly on text and contain inputs with thousands of words, testing models' ability to synthesize information across lengthy documents.
2️⃣ Diverse Tasks: Includes summarization, question answering, and natural language inference across domains like literature, science, and business.
3️⃣ Unified Format: All datasets are available in a text-to-text format, facilitating easy evaluation and comparison of models.
Building on SCROLLS, ZeroSCROLLS takes long text evaluation to the next level by focusing on zero-shot learning. Other features include:
1️⃣ New Tasks: Introduces tasks like sentiment aggregation and sorting book chapter summaries.
2️⃣ Leaderboard: A live leaderboard encourages continuous improvement and competition among researchers.
💡 What are some other landmark benchmarks in the history of long context evaluation? Feel free to share your thoughts and suggestions in the comments.
- SCROLLS Paper: SCROLLS: Standardized CompaRison Over Long Language Sequences (2201.03533)
- ZeroSCROLLS Paper: ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding (2305.14196)
In this series of posts about tracing the history of long context evaluation, we started with Long Range Arena (LRA). Introduced in 2020, Long Range Arens (LRA) is one of the earliest benchmarks designed to tackle the challenge of long context evaluation. But it wasn't introduced to evaluate LLMs, but rather the transformer architecture in general.
📜 The SCROLLS benchmark, introduced in 2022, addresses this gap in NLP/LLM research. SCROLLS challenges models with tasks that require reasoning over extended sequences (according to 2022 standards). So, what does it offer?
1️⃣ Long Text Focus: SCROLLS (unlike LRA) focus mainly on text and contain inputs with thousands of words, testing models' ability to synthesize information across lengthy documents.
2️⃣ Diverse Tasks: Includes summarization, question answering, and natural language inference across domains like literature, science, and business.
3️⃣ Unified Format: All datasets are available in a text-to-text format, facilitating easy evaluation and comparison of models.
Building on SCROLLS, ZeroSCROLLS takes long text evaluation to the next level by focusing on zero-shot learning. Other features include:
1️⃣ New Tasks: Introduces tasks like sentiment aggregation and sorting book chapter summaries.
2️⃣ Leaderboard: A live leaderboard encourages continuous improvement and competition among researchers.
💡 What are some other landmark benchmarks in the history of long context evaluation? Feel free to share your thoughts and suggestions in the comments.
- SCROLLS Paper: SCROLLS: Standardized CompaRison Over Long Language Sequences (2201.03533)
- ZeroSCROLLS Paper: ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding (2305.14196)
reacted to mitkox's post with 🤯🔥➕ almost 2 years ago
Post
2550
Can it run DeepSeek V3 671B is the new 'can it run Doom'.
How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.
Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.
Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
- 5 replies
reacted to julien-c's post with 🔥 almost 2 years ago
Post
3321
wow 😮
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
PrimeIntellect/INTELLECT-1-Instruct
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
PrimeIntellect/INTELLECT-1-Instruct
reacted to merve's post with ❤️ almost 2 years ago
Post
3414
your hugging face profile now has your recent activities 🤗
reacted to chansung's post with 👍 almost 2 years ago
Post
4784
Effortlessly stay up-to-date with AI research trends using a new AI tool, "AI Paper Reviewer" !!
It analyzes a list of Hugging Face Daily Papers(w/ @akhaliq ) and turn them into insightful blog posts. This project leverages Gemini models (1.5 Pro, 1.5 Flash, and 1.5 Flash-8B) for content generation and Upstage Document Parse for parsing the layout and contents.
blog link: https://deep-diver.github.io/ai-paper-reviewer/
Also, here is the link of GitHub repository for parsing and generating pipeline. By using this, you can easily build your own GitHub static pages based on any arXiv papers with your own interest!
: https://github.com/deep-diver/paper-reviewer
It analyzes a list of Hugging Face Daily Papers(w/ @akhaliq ) and turn them into insightful blog posts. This project leverages Gemini models (1.5 Pro, 1.5 Flash, and 1.5 Flash-8B) for content generation and Upstage Document Parse for parsing the layout and contents.
blog link: https://deep-diver.github.io/ai-paper-reviewer/
Also, here is the link of GitHub repository for parsing and generating pipeline. By using this, you can easily build your own GitHub static pages based on any arXiv papers with your own interest!
: https://github.com/deep-diver/paper-reviewer
reacted to Jofthomas's post with 🔥 about 2 years ago
Post
7923
Everchanging Quest is out !
It is an LLM controlled Rogue-Like in which the LLM gets a markdown representation of the map, and should generate a JSON with the objective to fulfill on the map as well as the necessary objects and their placements.
Come test it on the space :
Jofthomas/Everchanging-Quest
It is an LLM controlled Rogue-Like in which the LLM gets a markdown representation of the map, and should generate a JSON with the objective to fulfill on the map as well as the necessary objects and their placements.
Come test it on the space :
Jofthomas/Everchanging-Quest
- 2 replies