Oussema Harbi's picture

5

Oussema Harbi

Harbous

·

oharbi

AI & ML interests

None yet

Recent Activity

Reacted to csabakecskemeti's post with 👍 about 4 hours ago

The AMD Instinct MI50 (~$110) is surprisingly fast for inference Quantized models. This runs a Llama 3.1 8B Q8 with Llama.cpp https://huggingface.co/spaces/DevQuasar/Mi50 A little blogpost about the HW http://devquasar.com/uncategorized/amd-radeon-instinct-mi50-cheap-inference/

Reacted to freddyaboulton's post with 👍 4 days ago

Just created a cookbook of real time audio/video spaces created using Gradio and WebRTC ⚡️ Use this and the [docs](https://freddyaboulton.github.io/gradio-webrtc/) to get started building the next gen of AI apps! https://huggingface.co/collections/freddyaboulton/gradio-webrtc-cookbook-6758ba7745aeca7b1be7de0f

Reacted to qq8933's post with 👀 4 days ago

LLaMA-O1-PRM and LLaMA-O1-Reinforcement will release in this weekend. We have implemented a novel Reinforcement finetune(RFT) pipeline that taught models learning reasoning and reward labeling without human annotation.

View all activity

Organizations

None yet

models

None public yet

datasets

None public yet