Salim Belhaddad's picture

Salim Belhaddad

salym

·

https://salym.me

salym

AI & ML interests

Knowledge Graphs

Recent Activity

replied to philschmid's post about 1 month ago

Gemini 2.5 Pro, thinking by default! We excited launch our best Gemini model for reasoning, multimodal and coding yet! #1 on LMSYS, Humanity’s Last Exam, AIME and GPQA and more! TL;DR: - 💻 Best Gemini coding model yet, particularly for web development (excels on LiveCodeBench). - 🧠 Default "Thinking" with up to 64k token output - 🌌 1 Million multimodal input context for text, image, video, audio, and pdf - 🛠️ Function calling, structured output, google search & code execution. - 🏆 #1 on LMArena & sota on AIME, GPQA, Humanity's Last Exam - 💡 Knowledge cut of January 2025 - 🤗 Available for free as Experimental in AI Studio, Gemini API & Gemini APP - 🚀 Rate limits - Free 2 RPM 50 req/day Try it ⬇️ https://aistudio.google.com/?model=gemini-2.5-pro-exp-03-25

updated a model about 1 month ago

salym/ppo-LunarLander-v2

reacted to mlabonne's post with 🚀 about 1 month ago

✂️ Gemma 3 Abliterated I noticed that Gemma 3 was much more resilient to refusal removal than other models like Qwen 2.5. I experimented with different recipes and improved the abliteration technique I wrote about last year. It's still experimental but the refusal rate is super low in my tests. Enjoy! https://huggingface.co./mlabonne/gemma-3-4b-it-abliterated https://huggingface.co./mlabonne/gemma-3-12b-it-abliterated https://huggingface.co./mlabonne/gemma-3-27b-it-abliterated

View all activity

Organizations

models 15

salym/ppo-LunarLander-v2

Reinforcement Learning • Updated Mar 22 • 24

salym/rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning • Updated Mar 21

salym/PPO-CleanRL-LunarLander-v2

Reinforcement Learning • Updated Mar 20

salym/a2c-PandaPickAndPlace-v3

Reinforcement Learning • Updated Mar 20 • 12

salym/poca-SoccerTwos

Reinforcement Learning • Updated Mar 20 • 21

salym/a2c-PandaReachDense-v3

Reinforcement Learning • Updated Mar 20 • 9

salym/ppo-Pyramids

Reinforcement Learning • Updated Mar 19 • 40

salym/ppo-SnowballTarget

Reinforcement Learning • Updated Mar 19 • 39

salym/Reinforce-Pixelcopter-PLE-v0

Reinforcement Learning • Updated Mar 19

salym/Reinforce-CartPole-v1

Reinforcement Learning • Updated Mar 19

datasets 0

None public yet