Zephyr Tiny DPO Qlora is an open-source language model by dball. Features: 1.1b LLM, VRAM: 0.1GB, License: apache-2.0, HF Score: 37.4, LLM Explorer Score: 0.16, Arc: 36.6, HellaSwag: 61.7, MMLU: 25.8, TruthfulQA: 36.4, WinoGrande: 61.6, GSM8K: 2.1.
Adapter Alignment-handbook Base model:adapter:tinyllama/t... Base model:tinyllama/tinyllama... Dataset:huggingfaceh4/ultrafee... Dpo Finetuned Generated from trainer Llama Lora Peft Region:us Safetensors Tensorboard Trl
Model Card on HF 🤗: https://huggingface.co/dball/zephyr-tiny-dpo-qlora
Zephyr Tiny DPO Qlora Benchmarks
ARC: 36.6 vs 96.7 (so35)-62.2%
HellaSwag: 61.66 vs 95.3 (gpt4)-35.3%
MMLU: 25.78 vs 88.3 (so35)-70.8%
TruthfulQA: 36.4 vs 59 (gpt4)-38.3%
WinoGrande: 61.56 vs 87.5 (gpt4)-29.6%
GSM8K: 2.12 vs 96.4 (so35)-97.8%
LLME Score: 0.15983
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 Tiny DPO Qlora Parameters and Internals
| LLM Name | Zephyr Tiny DPO Qlora |
| Repository 🤗 | https://huggingface.co/dball/zephyr-tiny-dpo-qlora |
| Base Model(s) | |
| Model Size | 1.1b |
| Required VRAM | 0.1 GB |
| Updated | 2026-04-09 |
| Maintainer | dball |
| Model Files | |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|v_proj|q_proj|k_proj|gate_proj|o_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Zephyr Tiny DPO Qlora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Testing | 0K / 0 GB | 5 | 0 |
| Openhermes Tinyllama Sft Qlora | 0K / 0 GB | 6 | 0 |
| Zephyr Tinyllama Sft Qlora | 0K / 0 GB | 5 | 0 |
| ...hyr Tiny Sft Qlora Quantized 2 | 0K / 0 GB | 77 | 0 |
| DPO Mcqa V1.02 | 0K / 0.4 GB | 5 | 0 |
| DPO Mcqa QuantizedBitsAndBytes | 0K / 0.8 GB | 5 | 0 |
| MCQDPO1 | 0K / 0 GB | 5 | 0 |
| Mcqa | 0K / 0 GB | 5 | 0 |
| ProjectElrondMCQv1 | 0K / 0 GB | 11 | 0 |
| Tinyllama Cs | 0K / 0 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than dball/zephyr-tiny-dpo-qlora .
Rank the Zephyr Tiny DPO Qlora 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? 52721 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