A Gradio-based demonstration for the AllenAI Molmo2-8B multimodal model, enabling image QA, multi-image pointing, video QA, and temporal tracking. Users upload images or videos, provide natural language prompts.

“A clean, from-scratch implementation of the OLMo architecture with KV caching, RoPE, and an efficient autoregressive inference pipeline. Designed as a minimal yet extensible foundation for post-training research, including RLHF, preference optimization, and reasoning-focused systems.”

Experimenting with AllenAI's Olmo 3 7B models

Telegram bot for Allen AI's open-source models — OLMo, Tülu, and Molmo 2 vision. Chat, reason, analyze images, and point at objects.

Mock’n-Hire redefines hiring end-to-end by ranking resumes with semantic precision and delivering real-time, emotion-aware mock interview feedback - giving recruiters bias-resistant insights and candidates targeted, actionable practice.

Provide an open-source implementation of the OLMo language model for efficient and accurate natural language processing tasks.