What are the hardware requirements for Math Gpt2 Sft?

Math Gpt2 Sft requires approximately 0.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Math Gpt2 Sft and how large is it?

Math Gpt2 Sft is developed by Sharathhebbar24, a model with 124.4m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Math Gpt2 Sft perform on standard benchmarks?

Math Gpt2 Sft has the following published scores: MMLU 25.06. Compare against reference models on this page or on the LLM Explorer leaderboards.

Math Gpt2 Sft by Sharathhebbar24 — VRAM 0.5GB

Name: Math Gpt2 Sft
Author: Sharathhebbar24

Math Gpt2 Sft is an open-source language model by Sharathhebbar24. Features: 124.4m LLM, VRAM: 0.5GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.15, Arc: 22.9, HellaSwag: 30.4, MMLU: 25.1, GSM8K: 0.7.

Dataset:artifactai/arxiv-math-... Dataset:meta-math/metamathqa En Endpoints compatible Gpt2 Instruct Mathgpt2 Maths Model-index Region:us Safetensors Sft Trl

Model Card on HF 🤗: https://huggingface.co/Sharathhebbar24/math_gpt2_sft

Math Gpt2 Sft Parameters and Internals

Model Type

text-generation

Additional Notes

This model is a finetuned version of `Sharathhebbar24/math_gpt2` using `meta-math/MetaMathQA`.

Supported Languages

languages (en), proficiency (unknown)

LLM Name	Math Gpt2 Sft
Repository 🤗	https://huggingface.co/Sharathhebbar24/math_gpt2_sft
Model Size	124.4m
Required VRAM	0.5 GB
Updated	2026-08-06
Maintainer	Sharathhebbar24
Model Type	gpt2
Instruction-Based	Yes
Model Files	0.5 GB
Supported Languages	en
Model Architecture	GPT2LMHeadModel
License	apache-2.0
Model Max Length	1024
Transformers Version	4.39.3
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	50257
Torch Data Type	float32
Activation Function	gelu_new

Rank the Math Gpt2 Sft capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Math Gpt2 Sft

Best Alternatives	Context / RAM	Downloads	Likes
GPT 2 Instruct V0.1	0K / 0.5 GB	239	1
Code Gpt2	0K / 0.2 GB	81	0

Note: green Score (e.g. "73.2") means that the model is better than Sharathhebbar24/math_gpt2_sft.