Zephyr Gemma Rpo is an open-source language model by ZHLiu627. Features: 7b LLM, VRAM: 17.1GB, Context: 8K, License: other, HF Score: 60.9, Arc: 56.9, HellaSwag: 83.5, MMLU: 59.3, TruthfulQA: 49.7, WinoGrande: 74, GSM8K: 42.2.
Alignment-handbook Base model:finetune:huggingfac... Base model:huggingfaceh4/zephy... Conversational Dataset:argilla/dpo-mix-7k Endpoints compatible Gemma Generated from trainer Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ZHLiu627/zephyr-gemma-rpo
Zephyr Gemma Rpo Benchmarks
ARC: 56.91 vs 96.7 (so35)-41.1%
HellaSwag: 83.5 vs 95.3 (gpt4)-12.4%
MMLU: 59.27 vs 88.3 (so35)-32.9%
TruthfulQA: 49.72 vs 59 (gpt4)-15.7%
WinoGrande: 73.95 vs 87.5 (gpt4)-15.5%
GSM8K: 42.23 vs 96.4 (so35)-56.2%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Zephyr Gemma Rpo Parameters and Internals
| LLM Name | Zephyr Gemma Rpo |
| Repository 🤗 | https://huggingface.co/ZHLiu627/zephyr-gemma-rpo |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 17.1 GB |
| Updated | 2026-03-30 |
| Maintainer | ZHLiu627 |
| Model Type | gemma |
| Model Files | |
| Model Architecture | GemmaForCausalLM |
| License | other |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Zephyr Gemma Rpo
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Kaggle Math Model Gemma V1 | 12K / 17.1 GB | 5 | 0 |
| Gemma 1.1 7B It | 8K / 17.1 GB | 13535 | 275 |
| Gemma 7B It | 8K / 17.1 GB | 11885 | 9 |
| Gemma 1.1 7B It | 8K / 17.1 GB | 23 | 4 |
| SeaLLM 7B V2.5 | 8K / 17.1 GB | 12904 | 50 |
| Zephyr 7B Gemma DPO Avg | 8K / 17.1 GB | 15 | 0 |
| Zephyr 7B Gemma Rpo Avg | 8K / 17.1 GB | 6 | 0 |
| ... Codegemma 2 7B It Alpaca V1.3 | 8K / 17.1 GB | 6 | 1 |
| ... 7B Finetuned Sft Navarasa 2.0 | 8K / 34 GB | 1218 | 22 |
| Zephyr 7B Gemma V0.1 | 8K / 17.1 GB | 302 | 124 |
Note: green Score (e.g. "73.2") means that the model is better than ZHLiu627/zephyr-gemma-rpo .
Rank the Zephyr Gemma Rpo Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52286 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a