Files
mm-cand-aim_on_task_arithmetic/README.md
ModelHub XC 5c95e4490e 初始化项目,由ModelHub XC社区提供模型
Model: libvm/mm-cand-aim_on_task_arithmetic
Source: Original Platform
2026-05-29 19:58:54 +08:00

592 B

base_model, pipeline_tag, tags
base_model pipeline_tag tags
Qwen/Qwen3-8B-Base
Qwen/Qwen3-8B
OpenDataArena/Qwen3-8B-ODA-Math-460k
mlabonne/Qwen3-8B-abliterated
text-generation
model-merging
qwen3

This model was produced by first merging Qwen/Qwen3-8B-Base with Qwen/Qwen3-8B, OpenDataArena/Qwen3-8B-ODA-Math-460k, mlabonne/Qwen3-8B-abliterated using the task arithmetic MergeKit method (task_arithmetic). AIM was then applied to that merged parent using calibration examples from HuggingFaceFW/fineweb-edu (sample-10BT), allenai/WildChat, open-web-math/open-web-math, allenai/wildjailbreak (train).