GraySoft
Model Comparison

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-ggufvsjiunsong/supergemma4-26b-uncensored-gguf-v2

Side-by-side comparison of failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf and jiunsong/supergemma4-26b-uncensored-gguf-v2: 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…

jiunsong/supergemma4-26b-uncensored-gguf-v2

Jiunsong · text-generation

The fast, uncensored llama.cpp build of the strongest SuperGemma text line. This release is for people who want three things together:

Side-by-side Specifications

failspy/meta-llama-3-70b-instruct-abliterated-v3.5-ggufjiunsong/supergemma4-26b-uncensored-gguf-v2
AuthorfailspyJiunsong
Pipeline Tasktext-generation
Librarytransformers
Downloads36,98242,468
Likes25336
LicenseUnknownUnknown
Context Length
Created2024-05-282026-04-11
Last Modified2024-05-302026-04-12
Tags
transformersgguflicense:llama3endpoints_compatibleregion:usconversational
ggufgemma4uncensoredfastllama.cppapple-siliconconversationalkoreancodingtool-use

View full details: failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf · jiunsong/supergemma4-26b-uncensored-gguf-v2