GraySoft
Model Comparison

maziyarpanahi/mixtral-8x22b-v0.1-ggufvsmaziyarpanahi/wizardlm-2-7b-gguf

Side-by-side comparison of maziyarpanahi/mixtral-8x22b-v0.1-gguf and maziyarpanahi/wizardlm-2-7b-gguf: downloads, license, context length, tasks, and benchmarks.

maziyarpanahi/mixtral-8x22b-v0.1-gguf

MaziyarPanahi · text-generation

On April 10th, @MistralAI released a model named "Mixtral 8x22B," an 176B MoE via magnet link (torrent): The GGUF and quantized models here are based on v2ray/Mixtral-8x22B-v0.1 model

maziyarpanahi/wizardlm-2-7b-gguf

MaziyarPanahi · text-generation

pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_AR…

Side-by-side Specifications

maziyarpanahi/mixtral-8x22b-v0.1-ggufmaziyarpanahi/wizardlm-2-7b-gguf
AuthorMaziyarPanahiMaziyarPanahi
Pipeline Tasktext-generationtext-generation
Librarytransformerstransformers
Downloads89,59786,217
Likes7583
LicenseUnknownUnknown
Context Length
Created2024-04-102024-04-15
Last Modified2024-04-152024-04-15
Tags
transformersggufmixtraltext-generationquantized2-bit3-bit4-bit5-bit6-bit
transformersggufmistralquantized2-bit3-bit4-bit5-bit6-bit8-bit

View full details: maziyarpanahi/mixtral-8x22b-v0.1-gguf · maziyarpanahi/wizardlm-2-7b-gguf