datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
llama-cpp-wheelsIf you like this please consider liking and donating (https://buymeacoffee.com/aiencoder)
🏭 llama-cpp-python Mega-Factory Wheels
"Stop waiting for pip to compile. Just install and run."
The most complete collection of pre-built llama-cpp-python wheels in existence — 8,333 wheels across every platform, Python version, backend, and CPU optimization level.
No more cmake, gcc, or compilation hell. No more waiting 10 minutes for a build that might fail. Just find your wheel and… See the full description on the dataset page: https://huggingface.co/datasets/AIencoder/llama-cpp-wheels.llama.cpp_AlgMor24_github
ΩFFFΣLLIa • llama.cpp • AlgMor24
██████╗ ███████╗███████╗███████╗██╗ ██╗ ██╗ █████╗
██╔═══██╗██╔════╝██╔════╝██╔════╝██║ ██║ ██║██╔══██╗
██║ ██║█████╗ █████╗ █████╗ ██║ ██║ ██║███████║
██║ ██║██╔══╝ ██╔══╝ ██╔══╝ ██║ ██║ ██║██╔══██║
╚██████╔╝██║ ██║ ███████╗███████╗███████╗██║██║ ██║
╚═════╝ ╚═╝ ╚═╝ ╚══════╝╚══════╝╚══════╝╚═╝╚═╝ ╚═╝
High-Performance LLM / VLM Inference & Autonomous Agentic Ecosystem… See the full description on the dataset page: https://huggingface.co/datasets/Brunobkr/llama.cpp_AlgMor24_github.llama.cppversion https://git-lfs.github.com/spec/v1
oid sha256:cfc44b7ba25614df70e6b65e3341cae0310163bd32fd31a6b928a542df433faf
size 30786
mmlu-redux-2.0-for-llama.cppMMLU-redux-v2.0 converted for the llama.cpp perplexity multiple choice tool.
Only valid entries where kept, there is no error based prompting included.
Dataset Card for MMLU-Redux-2.0
MMLU-Redux is a subset of 5,700 manually re-annotated questions across 57 MMLU subjects.
Citation
BibTeX:
@misc{gema2024mmlu,
title={Are We Done with MMLU?},
author={Aryo Pradipta Gema and Joshua Ong Jun Leang and Giwon Hong and Alessio Devoto and Alberto Carlo Maria… See the full description on the dataset page: https://huggingface.co/datasets/Green-Sky/mmlu-redux-2.0-for-llama.cpp.validation-datasets-for-llama.cppThis repository contains validation datasets for use with the perplexity tool from the llama.cpp project.
Note: PR #5047 is required to be able to use these datasets.
The simple program in demo.cpp shows how to read these files and can be used to combine two files into one.
The simple program in convert.cpp shows how to convert the data to JSON. For instance:
g++ -o convert convert.cpp
./convert arc-easy-validation.bin arc-easy-validation.json
llama-cpp-scripts
llama.cpp scripts
These are scripts that have helped me to manage llama.cpp, llama models, etc.
Install
Scripts are installed to ~/.local/bin.
bash install.sh
mmlu-redux-for-llama.cppMMLU-redux converted for the llama.cpp perplexity multiple choice tool.
Only valid entries where kept, there is no error based prompting included.
Dataset Card for MMLU-Redux
[!TIP]
Please consider using MMLU-Redux-2.0 which contains all 57 MMLU subjects.
MMLU-Redux is a subset of 3,000 manually re-annotated questions across 30 MMLU subjects.
Citation
BibTeX:
@misc{gema2024mmlu,
title={Are We Done with MMLU?},
author={Aryo Pradipta Gema and Joshua Ong… See the full description on the dataset page: https://huggingface.co/datasets/Green-Sky/mmlu-redux-for-llama.cpp.moss-tts-llamacpp-runtime-portable
MOSS-TTS runtime payload
This private Kaggle dataset is generated by Phorcys.Tools.MossTtsLlamaCppRuntimeUploader for PHRunner.Kaggle.Service.MossTtsGguf.
Runtime flavor: LinuxCuda
Python tag: python3.12
Generated UTC: 2026-09-24T22:50:28.4915472+00:00
The dataset intentionally contains runtime artifacts, not the GGUF model repository by default. Keep the model files in a separate private Kaggle dataset, for example kaggle-pool-account/moss-tts-v1-5-gguf-models.
Top-level… See the full description on the dataset page: https://huggingface.co/datasets/stokiz/moss-tts-llamacpp-runtime-portable.llama-cpp-rx7800xt-benchmarks
llama.cpp RX 7800 XT benchmarks
Sanitized benchmark archive for local llama.cpp/GGUF experiments on an AMD Radeon RX 7800 XT workstation. This dataset is benchmark data only: model weights, local system/network diagnostics, environment files, scripts, caches, and oversized raw dumps are excluded.
Start here
summaries/run-index.csv - index of benchmark result directories.
summaries/practical-audit-index.csv - compact index of practical-audit runs.
metadata.json -… See the full description on the dataset page: https://huggingface.co/datasets/NeoAiLabs/llama-cpp-rx7800xt-benchmarks.winogrande-eval-for-llama.cppWinogrande evaluation dataset for llama.cpp
moss-tts-v1-5-llamacpp-models
MOSS-TTS model payload
This dataset was generated by MossTtsLlamaCppModelsUploader for PHRunner.Kaggle.Service.MossTtsGguf.
Source
Hugging Face repository: niobures/MOSS-TTS-GGUF
Revision: main
Kaggle dataset: kaggle-pool-account/moss-tts-v1-5-llamacpp-models
Layout: python-llama-cpp
Required backend: python-llama-cpp-onnx
Default model file: MOSS_TTS_Q4_K_M.gguf
Files
MOSS_TTS_Q4_K_M.gguf - backbone - 4.7 GiB - SHA256… See the full description on the dataset page: https://huggingface.co/datasets/stokiz/moss-tts-v1-5-llamacpp-models.llama-cpp-binariesllama-cpp-turboquant-precompiledllama-cpp-cuda130-blackwell120precompiled_llama_cppLongBench-v2-for-llama.cppLongBench v2 converted for the llama.cpp perplexity multiple choice tool.
[!WARNING]
!! Currently does not work, will fix it in the near future. Probably.
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
🌐 Project Page: https://longbench2.github.io
💻 Github Repo: https://github.com/THUDM/LongBench
📚 Arxiv Paper: https://arxiv.org/abs/2412.15204
LongBench v2 is designed to assess the ability of LLMs to handle long-context problems… See the full description on the dataset page: https://huggingface.co/datasets/Green-Sky/LongBench-v2-for-llama.cpp.learnstral-1.5-llama-cpp-expOFFFELLIA_llama.cpp_Neon_Themes
ΩFFFΣLLIα llama.cpp
Inferência de LLM em C/C++, com a interface Web construída a partir deste código.
ggml · build · server · licença
Árvore local de llama.cpp. O nome ΩFFFΣLLIα llama.cpp aparece no centro de qualquer página da interface, em qualquer porta do llama-server. Os logos SVG da interface foram substituídos pelo caractere Ω.
Modificações
Área
Comportamento nesta árvore
Compilação
O CMake principal força… See the full description on the dataset page: https://huggingface.co/datasets/Brunobkr/OFFFELLIA_llama.cpp_Neon_Themes.qwen3-8-27B-llama-cpp-Q8llama.cpp_colabllama.cpp_jetson_benchmark
llama.cpp with CUDA support on a Jetson Nano 2019
This dataset contains some benchmark results for llama.cpp with GPU acceleration on the Jetson Nano from 2019.
For comparison llama.cpp was compiled with just CPU support, and a recent ollama version received the same 11 questions.
llama-cpp-wheelsvessel-llama.cppllama.cpp_omega_matrix.zip
⚡ llama.cpp_omega_matrix
██████╗ ███╗ ███╗███████╗ ██████╗ █████╗ ██████╗ ██████╗ ██████╗
██╔═══██╗████╗ ████║██╔════╝██╔════╝ ██╔══██╗ ██╔════╝██╔══██╗██╔══██╗
██║ ██║██╔████╔██║█████╗ ██║ ███╗███████║ ██║ ██████╔╝██████╔╝
██║ ██║██║╚██╔╝██║██╔══╝ ██║ ██║██╔══██║ ██║ ██╔═══╝ ██╔═══╝
╚██████╔╝██║ ╚═╝ ██║███████╗╚██████╔╝██║ ██║ ╚██████╗██║ ██║
╚═════╝ ╚═╝ ╚═╝╚══════╝ ╚═════╝ ╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═╝… See the full description on the dataset page: https://huggingface.co/datasets/Brunobkr/llama.cpp_omega_matrix.zip.llama-cpp-benchllama-cpp-cuda128-blackwell120llama-cpp-python-build-on-cu130-windows-py311llama-cpp-cuda128-ampere80llama-cpp-cuda12-ada89llama.cpp CUDA 12.8.1, target GPU: sm89
If you're new or just starting to learn setting up your own inferences this llama.cpp wheel will work for if you're using python, CUDA 12.8.1 with one of the following Ada Lovelace generation (sm_89) GPU's:
NVIDIA L4
NVIDIA L40
NVIDIA L40S
NVIDIA RTX 6000 Ada Generation
NVIDIA RTX 5000 Ada Generation
NVIDIA RTX 4500 Ada Generation
NVIDIA RTX 4000 Ada Generation
NVIDIA RTX 4000 SFF Ada Generation
NVIDIA RTX 2000 Ada Generation
NVIDIA GeForce RTX 4090… See the full description on the dataset page: https://huggingface.co/datasets/juiceb0xc0de/llama-cpp-cuda12-ada89.llama.cpp-0002