@jerryjliu0: If I only went off X posts, I'd think Ramp was an AI lab
Summary
Ramp Labs open-sourced PorTAL, a framework for shared task representations and cross-model LoRA adaptation, supporting hybrid attention models and multimodal systems including Gemma 4, Mistral 7B, and Inkling.
View Cached Full Text
Cached at: 07/28/26, 06:36 AM
If I only went off X posts, I’d think Ramp was an AI lab
Ramp Labs (@RampLabs): We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation.
It now spans from hybrid attention models to multimodal systems including Gemma 4 E2B, Mistral 7B & @thinkymachines’ Inkling.
Code: ramp-public/portallib Models:
Similar Articles
@didier_lopes: Incredible how Z. ai literally has their RL infrastructure open source. The entire OPD post-training of GLM-5.2 took on…
Z. ai has open-sourced its RL infrastructure, the slime framework, which enabled efficient OPD post-training of GLM-5.2 in about two days. slime is an LLM post-training framework for RL scaling that integrates Megatron and SGLang, and has been battle-tested by frontier models like GLM, Qwen, DeepSeek, and Llama.
@yifanzhang_: https://thinkingmachines.ai/news/introducing-inkling/… RoPE is dead, Long live GRAPE!
Thinking Machines AI releases Inkling, an open-weights Mixture-of-Experts model with 975B total parameters (41B active), supporting text, images, and audio over a 1M token context window. It is a broad foundation model designed for fine-tuning via their Tinker platform, with a smaller Inkling-Small variant also previewed.
@tbpn: FULL INTERVIEW: Engineers Edward Coristine (@as400495) and Tai Groot (@taigrr) just released an ML model called Rampart…
Engineers Edward Coristine and Tai Groot released Rampart, an open-source AI privacy model for on-device PII redaction that runs entirely in the browser, developed by the National Design Studio.
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
RAMP is a production-grounded evaluation framework for LLM agents that exposes significant capability degradation invisible to static benchmarks, showing task completion rates collapsing from 100% to 20% across serial workflows. The framework assesses 15 mainstream models on realistic compiler-construction workloads with complex toolchain interactions and staged recovery mechanisms.
@tom_doerr: Builds custom AI agents with reinforcement learning https://github.com/agentica-project/rllm…
rLLM is an open-source framework for post-training language agents via reinforcement learning, with notable model releases like DeepSWE-Preview and DeepCoder-14B-Preview achieving state-of-the-art results.