GraySoft
Model Comparison

bartowski/cerebras_glm-4.5-air-reap-82b-a12b-ggufvsfailspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf

Side-by-side comparison of bartowski/cerebras_glm-4.5-air-reap-82b-a12b-gguf and failspy/meta-llama-3-70b-instruct-abliterated-v3.5-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…

Side-by-side Specifications

bartowski/cerebras_glm-4.5-air-reap-82b-a12b-gguffailspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf
Authorbartowskifailspy
Pipeline Tasktext-generation
Librarytransformers
Downloads181,19136,982
Likes3825
LicenseUnknownUnknown
Context Length
Created2025-10-202024-05-28
Last Modified2025-10-232024-05-30
Tags
gguftext-generationbase_model:cerebras/GLM-4.5-Air-REAP-82B-A12Bbase_model:quantized:cerebras/GLM-4.5-Air-REAP-82B-A12Bendpoints_compatibleregion:usimatrixconversational
transformersgguflicense:llama3endpoints_compatibleregion:usconversational

View full details: bartowski/cerebras_glm-4.5-air-reap-82b-a12b-gguf · failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf