👋 Open to Work

vigneshwar l

vigneshwar234

AI & ML interests

Retrieval-Augmented Generation Natural Language Processing Artificial Intelligence Machine Learning Causal Reasoning Information Retrieval

Recent Activity

new activity 10 days ago

mradermacher/LlamaForecaster-8B-i1-GGUF:TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture

liked a model 10 days ago

mradermacher/LlamaForecaster-8B-i1-GGUF

new activity 10 days ago

llm-jp/open-japanese-llm-leaderboard-v2:Cost + latency + hallucination evaluation for Japanese LLM selection

View all activity

Organizations

None yet

spaces 5

Vilvona AI

🪷

Self-hosted AI assistant — Claude Fable 5, Tamil & Hindi

LLM Evaluation Framework Demo

📊

Benchmark LLMs on accuracy, cost, and hallucination.

PHANTASM LLM Hallucination Inverter

🔮

Invert LLM hallucination into productive features

VORTEXRAG

🌀

7-Layer RAG: +13.6 EM, 0.94 Faithfulness

TemporalMesh Transformer Demo

🕸

Visualize TemporalMesh Transformer token flow and early exits

models 3

datasets 5

vigneshwar234/llm-eval-benchmark

Viewer • Updated Jun 7 • 1.2k • 87 • 1

vigneshwar234/PHANTASM-benchmark

Updated Jun 7 • 18

vigneshwar234/VORTEXRAG-Benchmarks

Preview • Updated Jun 7 • 19

vigneshwar234/TMT-Benchmarks

Viewer • Updated Jun 7 • 1k • 51 • 1

vigneshwar234/phantasm-hallucination-benchmark

Updated May 30 • 54 • 1