Back to Rankings

huihui-ai

Qwen2.5-72B-Instruct-abliterated

fine-tunedondomain-specificdatasetsQwen2ForCausalLMbfloat16

Install and run this model locally using llmpm, the open-source LLM package manager.

Install
llmpm install huihui-ai/Qwen2.5-72B-Instruct-abliterated
Run
llmpm run huihui-ai/Qwen2.5-72B-Instruct-abliterated
View Model PageView on HuggingFace
Average Score (0–100)
48.1%
Weighted average of normalized scores from all benchmarks. Each benchmark is normalized to a 0–100 scale, then averaged together.

BENCHMARK SCORES

IFEval85.9%

Instruction-Following Evaluation. Tests the model's ability to follow explicit formatting instructions (instruction following, formatting, generation). Scored by strict format accuracy.

BBH60.5%

Big Bench Hard. A collection of challenging tasks across language understanding, mathematical reasoning, and common sense knowledge. Scored by accuracy on multiple-choice questions.

MATH Lvl 560.1%

Mathematics Aptitude Test of Heuristics, Level 5. High school competition problems covering complex algebra, geometry, and advanced calculus. Scored by exact match.

GPQA19.4%

Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.

MuSR12.3%

Multistep Soft Reasoning. Tests reasoning and understanding over long texts, including language understanding, reasoning capabilities, and long-context reasoning. Scored by accuracy.

MMLU-Pro50.4%

Massive Multitask Language Understanding – Professional. Expert-reviewed multiple-choice questions across medicine, law, engineering, and mathematics. Scored by accuracy.

MODEL INFO

Architecture
Qwen2ForCausalLM
Precision
bfloat16
Type
fine-tunedondomain-specificdatasets
Weight Type
Original
Parameters
72.7B
Chat Template
Yes

METADATA

Upload Date
2024-10-26
Submission Date
2024-12-07
License
other
Base Model
Qwen/Qwen2.5-72B
HF Hearts
10
CO₂ Cost (kg)
76.77