GraySoft
Model Comparison

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-ggufvsmoonride/gemma-4-31b-it-heretic-ara-gguf

Side-by-side comparison of failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf and moonride/gemma-4-31b-it-heretic-ara-gguf: downloads, license, context length, tasks, and benchmarks.

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf

failspy · —

# Llama-3-70B-Instruct-abliterated-v3.5 Model Card My original Jupyter "cookbook" to replicate the methodology can be found here My personal library o' code used (WIP, looking to improve and generalize) This is meta-llama/Meta-Llama-3-70B-Instruct with orthogonalized bfloat16 sa…

moonride/gemma-4-31b-it-heretic-ara-gguf

MoonRide · image-text-to-text

# In case of troubles with loading model files, please update to llama.cpp b8751 or newer

Side-by-side Specifications

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-ggufmoonride/gemma-4-31b-it-heretic-ara-gguf
AuthorfailspyMoonRide
Pipeline Taskimage-text-to-text
Librarytransformerstransformers
Downloads36,98228,949
Likes250
LicenseUnknownUnknown
Context Length
Created2024-05-282026-04-12
Last Modified2024-05-302026-04-13
Tags
transformersgguflicense:llama3endpoints_compatibleregion:usconversational
transformersggufhereticuncensoreddecensoredabliteratedaraimage-text-to-textbase_model:MoonRide/gemma-4-31B-it-heretic-arabase_model:quantized:MoonRide/gemma-4-31B-it-heretic-ara

View full details: failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf · moonride/gemma-4-31b-it-heretic-ara-gguf