metadata
license: apache-2.0
datasets:
- open-r1/Mixture-of-Thoughts
language:
- en
base_model:
- open-r1/OpenR1-Distill-7B
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
OpenR1-Distill-7B-F32-GGUF
OpenR1-Distill-7B-F32-GGUF is a quantized version of OpenR1-Distill-7B, which is a post-trained model based on Qwen/Qwen2.5-Math-7B. It was further trained on Mixture-of-Thoughts, a curated dataset of 350k verified reasoning traces distilled from DeepSeek-R1. The dataset covers tasks in mathematics, coding, and science, and is designed to teach language models to reason step-by-step.
Model File
File Name | Size | Format | Notes |
---|---|---|---|
OpenR1-Distill-7B.BF16.gguf | 15.2 GB | GGUF | BF16 precision model |
OpenR1-Distill-7B.F16.gguf | 15.2 GB | GGUF | FP16 precision model |
OpenR1-Distill-7B.F32.gguf | 30.5 GB | GGUF | FP32 precision model |
OpenR1-Distill-7B.Q2_K.gguf | 3.02 GB | GGUF | 2-bit quantized (Q2_K) model |
OpenR1-Distill-7B.Q4_K_M.gguf | 4.68 GB | GGUF | 4-bit quantized (Q4_K_M) model |
.gitattributes | 1.84 kB | Text | Git LFS tracking config |
config.json | 31 B | JSON | Model configuration file |
README.md | 213 B | Markdown | This readme file |
Quants Usage
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):