Downloads · 30 days
48
14% of all-time downloads
ermiaazarkhalili/Qwen2.5-3B-GRPO-NuminaMath-100K-GGUF
Qwen2.5-3B-GRPO-NuminaMath-100K-GGUF is a text generation model from ermiaazarkhalili. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
GGUF quantized versions of Qwen2.5-3B-GRPO-NuminaMath-100K, fine-tuned using GRPO (Group Relative Policy Optimization) on NuminaMath-CoT.
Downloads · 30 days
48
14% of all-time downloads
All-time downloads
351
Public
Repo size
7.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf7.4 GB · 100%
From the Hugging Face model README
GGUF quantized versions of Qwen2.5-3B-GRPO-NuminaMath-100K, fine-tuned using GRPO (Group Relative Policy Optimization) on NuminaMath-CoT.
| Property | Value |
|---|---|
| Developed by | Behrooz Azarkhalili |
| License | APACHE-2.0 |
| Language | English |
| Training Method | GRPO (Group Relative Policy Optimization) |
| Dataset | NuminaMath-CoT |
| Format | GGUF (llama.cpp quantized) |
This repository provides GGUF variants at multiple quantization levels (Q4_K_M, Q5_K_M, Q8_0). See the repository file list for exact filenames.
ollama pull hf.co/ermiaazarkhalili/Qwen2.5-3B-GRPO-NuminaMath-100K-GGUF:Q4_K_M
llama-cli -m qwen2.5-3b-grpo-numinamath-100k-gguf-q4_k_m.gguf -p "Your prompt here" -n 256
If you use this model in your research or applications, please cite:
@misc{azarkhalili2026_qwen2_5_3b_grpo_numinamath_100k_gguf,
author = {Azarkhalili, Behrooz},
title = {Qwen2.5-3B-GRPO-NuminaMath-100K-GGUF},
year = {2026},
publisher = {Hugging Face},
url = {https://huggingface.co/ermiaazarkhalili/Qwen2.5-3B-GRPO-NuminaMath-100K-GGUF}
}
To generate a citable DOI, click "Cite this model" on the model page.
Trained using GRPO (Group Relative Policy Optimization) on NuminaMath-CoT.
Base (merged) model: Qwen2.5-3B-GRPO-NuminaMath-100K