datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
qwen36-kquant-offload-mtp-swebench-lite100-results
Qwen3.6 K-Quant Offload MTP SWE-bench Lite 100 Results
This dataset contains the complete 5-model x 100-prompt runtime benchmark artifacts plus a detailed statistical analysis layer.
Primary conclusion: hot30/cold30 was the best decode-throughput run, while Q4_K_M had the best total wall clock. The ATX hot30/cold30 quantization significantly outperformed both Q4_K_M and Q3_K_XL on paired decode throughput, but Q4_K_M remains the elapsed-time control.
The ATX/K3 hot10, hot20, and… See the full description on the dataset page: https://huggingface.co/datasets/jakeatx/qwen36-kquant-offload-mtp-swebench-lite100-results.qwen36-mtp-turbo-kv-analysis
Qwen3.6 MTP Turbo KV Runtime Analysis
This repository is a curated analysis artifact for local Qwen3.6-35B-A3B MTP GGUF inference experiments on Windows CUDA. It compares clean MTP llama.cpp, QuinsZouls llama-next TurboQuant, and the completed subset of Atomic TurboQuant runs under a fixed 64k context, MoE CPU offload, and Unsloth-aligned sampling settings.
The raw benchmark runs included incomplete and capability-incompatible rows. This repo keeps only completed, comparable… See the full description on the dataset page: https://huggingface.co/datasets/jakeatx/qwen36-mtp-turbo-kv-analysis.qwen36-35b-a3b-clawbench
Qwen3.6-35B-A3B ClawBench Full Results
This repository contains organized ClawBench run artifacts from bench/ClawBench/test-output/qwen36-35b-a3b-full-20260510-2140.
The formal result directories are preserved under results/. Quarantined infrastructure-failure directories and top-level runtime control files such as .pid, .proc, .logpath, and .monitor-hermes-state/ are intentionally excluded from this organized export.
Contents… See the full description on the dataset page: https://huggingface.co/datasets/whywhywhyyy/qwen36-35b-a3b-clawbench.FabricationGuard-linearprobe-qwen36-27b
🛡️ FabricationGuard — Linear Probe for Qwen3.6-27B
Activation-probe fabrication detection for Qwen3.6-27B. AUROC 0.88 cross-task on SimpleQA, -88% confident-wrong rate reduction in mitigation mode, ~1ms scoring latency.
This is the OpenInterp FabricationGuard production probe — derived from a multi-feature linear probe on the residual stream at layer 31, trained on a multi-benchmark hallucination corpus, validated cross-task on held-out splits.
Value
Base model… See the full description on the dataset page: https://huggingface.co/datasets/caiovicentino1/FabricationGuard-linearprobe-qwen36-27b.qwen3-vl-4b-pi-lossy-sft-dataset