Hugging Face's logo
Salma Mayorquin's picture
26 22 482

Salma Mayorquin PRO

salma-remyx
Papai25's profile picture rams1989's profile picture mhumeralna's profile picture
·
https://remyx.ai

AI & ML interests

None yet

Recent Activity

reacted to TravisMuhlestein's post with 🔥 1 day ago
The conversation around AI agents is evolving. We're moving beyond model capabilities and toward the infrastructure needed for agents to work together. Over the past few weeks we've seen meaningful momentum around the foundational building blocks of the emerging agentic web. Agent Name Service (ANS) is addressing identity and trust. Agentic Resource Discovery (ARD) is helping standardize how agents discover resources and capabilities. Together, these efforts represent something bigger than individual projects. They point toward an ecosystem built on open, interoperable infrastructure rather than isolated implementations. As builders, we'll likely spend the next few years solving challenges around identity, discovery, trust, interoperability, and governance—not just model performance. It will be interesting to see how these efforts evolve—and where the community chooses to collaborate next. Learn more: 🔗 Linux Foundation ANS: https://www.linuxfoundation.org/press/linux-foundation-announces-intent-to-launch-agent-name-service-to-establish-trusted-identity-infrastructure-for-ai-agents 🔗 Agentic Resource Discovery: https://developers.googleblog.com/announcing-the-agentic-resource-discovery-specification/
reacted to ManniX-ITA's post with 🔥 1 day ago
--- 🚀 Gemma-4-A4B 98e v7-coder cohort — loop-fixed re-release. Two 20.8B MoE coders (4B-active), fresh-map prunes of Gemma 4 26B-A4B, 30/128 experts dropped per layer. The headline isn't a benchmark: the agentic loop is gone at the weights, not papered over by the sampler. 🔧 How: at prune time we force-keep the 46 agentic_eog experts a loop-protection signal flags as load-bearing for clean multi-turn termination (+ shared-FFN α=1.2). Result: 0 loops across 48 seeds on every published tier. 📊 Q6_K · llama.cpp · greedy · same host (from summary.json): ⚖️ v7-coder (fkbroad code3/lcb2) — balanced coder: LCB-med-55 98.18, HumanEval 98.17, HE+ 92.07, AIME 80.0, MATH-500 95.0, GSM8K 91, IFEval 92, MultiPL-E 89.7, ARC 92.2. ⚡ v7-coderx (code4/lcb3) — code-maximal: all-hard LCB-77 85.71 (cohort-best; 128e 79.22, v7-coder 84.42), HE+ 93.29, GSM8K 93, MATH-500 95.0, AIME 76.67. Whole budget on code. 🎯 Both land near GPQA ~51 — graduate science is the budget axis, neither is a science model. Pick v7-coder for the broad LCB-medium + HumanEval lead; v7-coderx for the all-hard slice and HE+. 🧪 The harness we used to prove the fix is now an omk tool: agentic-loop-harness replays a frozen agentic conversation across a sampler×seed matrix and reports a fail-rate per chat-template, so you can isolate a loop to one variable. Model-agnostic — any OpenAI-compatible server. The version we shared with Google: https://huggingface.co/google/gemma-4-12B-it/discussions/41#6a3926720abc934d03fd85c0 📦 Each ships bf16 · GGUF (+ CD-* + imatrix + mmproj vision) · NVFP4A16 (~13 GB) · Ollama. 🔗 https://huggingface.co/ManniX-ITA/gemma-4-A4B-98e-v7-coder-it (+ -it-GGUF, -NVFP4A16) · https://ollama.com/mannix/gemma4-98e-v7-coder 🔗 https://huggingface.co/ManniX-ITA/gemma-4-A4B-98e-v7-coderx-it (+ -it-GGUF, -NVFP4A16) · https://ollama.com/mannix/gemma4-98e-v7-coderx 🔧 https://github.com/mann1x/omnimergekit/tree/main/tools/agentic-loop-harness
reacted to PeetPedro's post with 🔥 1 day ago
hey, I'm doing some experimenting, looping around :slight_smile: --- **kompress-v6** *shipped* — trained on Claude Code agent patterns (bash output, file reads, stack traces, search results, JSON tool responses). 3k synthetic pairs + 2k existing, fine-tuned from v4, $0.20 on vast.ai. Results: heretic exact_pct 0.962 (v4: 0.967), keep_rate 0.854 (v4: 0.823), override delta 0. Model got more conservative — higher keep_rate on structured technical content. Real proxy: v4 compressed 9.5%, v6 compressed 4.2% on the same session. Less aggressive, fewer must-keep tokens dropped on paths and identifiers. Interesting failure: self-labeling with v4+override collapsed mk_in_ref to 0.652. TokenExpiredError splits into `Token+Expired+Error` — subtokens that don't individually match the must-keep regex, so the force-keep never fires. Generator references (mk_in_ref=1.0 by construction) ended up being better labels than v4's compressed output for agent data. Fix for next run: slide a 2-3 subtoken window instead of checking individual subtokens. Would let self-labeling work on agent content and potentially produce a more compression-aggressive v7. Models on HF: - https://huggingface.co/PeetPedro/kompress-v6 - https://huggingface.co/PeetPedro/kompress-v4 - https://huggingface.co/PeetPedro/kompress-v3 Write-up: https://pocoo.vaked.dev/posts/2026-06-25-kompress-v6-agent-distribution
View all activity

Organizations

Remyx AI's profile picture