1 16 98

Mert Erbak PRO

merterbak

AI & ML interests

Currently NLP and Image Processing

Recent Activity

reacted to mmhamdy's post with 🔥 about 9 hours ago

🎉 We're excited to introduce MemoryCode, a novel synthetic dataset designed to rigorously evaluate LLMs' ability to track and execute coding instructions across multiple sessions. MemoryCode simulates realistic workplace scenarios where a mentee (the LLM) receives coding instructions from a mentor amidst a stream of both relevant and irrelevant information. 💡 But what makes MemoryCode unique?! The combination of the following: ✅ Multi-Session Dialogue Histories: MemoryCode consists of chronological sequences of dialogues between a mentor and a mentee, mirroring real-world interactions between coworkers. ✅ Interspersed Irrelevant Information: Critical instructions are deliberately interspersed with unrelated content, replicating the information overload common in office environments. ✅ Instruction Updates: Coding rules and conventions can be updated multiple times throughout the dialogue history, requiring LLMs to track and apply the most recent information. ✅ Prospective Memory: Unlike previous datasets that cue information retrieval, MemoryCode requires LLMs to spontaneously recall and apply relevant instructions without explicit prompts. ✅ Practical Task Execution: LLMs are evaluated on their ability to use the retrieved information to perform practical coding tasks, bridging the gap between information recall and real-world application. 📌 Our Findings 1️⃣ While even small models can handle isolated coding instructions, the performance of top-tier models like GPT-4o dramatically deteriorates when instructions are spread across multiple sessions. 2️⃣ This performance drop isn't simply due to the length of the context. Our analysis indicates that LLMs struggle to reason compositionally over sequences of instructions and updates. They have difficulty keeping track of which instructions are current and how to apply them. 🔗 Paper: https://huggingface.co/papers/2502.13791 📦 Code: https://github.com/for-ai/MemoryCode

reacted to lysandre's post with ❤️ about 10 hours ago

SmolVLM-2 and SigLIP-2 are now part of `transformers` in dedicated releases! They're added on top of the v4.49.0 release, and can be installed from the following tags: `v4.49.0-SmolVLM-2` and `v4.49.0-SigLIP-2`. This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures). Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models. Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.

liked a Space about 11 hours ago

gradio/theme-gallery

View all activity

Organizations

merterbak's activity

liked a Space about 11 hours ago

196

Theme Gallery

🌍

liked a dataset 2 days ago

microsoft/bleeding-edge-gameplay-sample

Updated 2 days ago • 802 • 5

liked a model 2 days ago

microsoft/wham

Updated 1 day ago • 157

liked a model 3 days ago

nvidia/nemotron-3-8b-base-4k

Text Generation • Updated Feb 9, 2024 • 17 • 85

liked a Space 3 days ago

Paligemma2 Mix

🌖

Generate text or segment objects from an image

liked a model 3 days ago

perplexity-ai/r1-1776

Updated 3 days ago • 6.44k • 1.37k

liked a model 4 days ago

fal/AuraFlow-v0.3

Text-to-Image • Updated Aug 15, 2024 • 571 • 121

liked 3 Spaces 5 days ago

smolagents and tools gallery

🎨

Browse tools and agents to use in smolagents

237

Zonos

🌍

Generate high-quality audio from text using various controls

271

OmniParser V2

🏢

OmniParser, turn your LLM into GUI agent

liked a model 7 days ago

agentica-org/DeepScaleR-1.5B-Preview

Text Generation • Updated 3 days ago • 14.5k • • 463

liked a model 8 days ago

meta-llama/Llama-3.2-11B-Vision

Image-Text-to-Text • Updated Sep 27, 2024 • 217k • 470

liked a Space 8 days ago

DeepSeek R1 Distill Qwen 1.5B

💬

Try DeepSeek-R1-Distill-Qwen-1.5B on CPU

liked a model 9 days ago

merterbak/Mistral-Small-24B-Instruct-2501-Q4_K_M-GGUF

Updated 9 days ago • 54 • 1

liked a Space 9 days ago

1.23k

GGUF My Repo

🦙

liked 2 models 9 days ago

simplescaling/s1.1-32B

Text Generation • Updated 10 days ago • 4.8k • 58

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • Updated 13 days ago • 1.08M • • 905

liked a Space 22 days ago

1.8k

Chat With Janus-Pro-7B

🌍

A unified multimodal understanding and generation model.

liked a model 22 days ago

deepseek-ai/Janus-Pro-1B

Any-to-Any • Updated 21 days ago • 116k • 373

liked a model 24 days ago

meta-llama/Llama-3.2-11B-Vision-Instruct

Image-Text-to-Text • Updated Dec 4, 2024 • 1.23M • • 1.34k