Adapter Alignment-handbook Base model:adapter:dual-gpo/ze... Base model:dual-gpo/zephyr-7b-... Dataset:huggingfaceh4/ultrafee... Dpo Finetuned Generated from trainer Lora Mistral Peft Region:us Safetensors Tensorboard Trl
Model Card on HF 🤗: https://huggingface.co/DUAL-GPO/zephyr-7b-ipo-0k-15k-i1
Zephyr 7B Ipo 0K 15K I1 Benchmarks
MMLU Pro: 23.67
GPQA: 5.48
MUSR: 10.57
BBH: 22.66
IFEval: 27.56 vs 88 (so35)-68.7%
MATH Lvl 5: 3.02
LLME Score: 0.22178
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 7B Ipo 0K 15K I1 Parameters and Internals
| LLM Name | Zephyr 7B Ipo 0K 15K I1 |
| Repository 🤗 | https://huggingface.co/DUAL-GPO/zephyr-7b-ipo-0k-15k-i1 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.7 GB |
| Updated | 2025-10-03 |
| Maintainer | DUAL-GPO |
| Model Files | |
| Model Architecture | Adapter |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | o_proj|gate_proj|up_proj|k_proj|v_proj|down_proj|q_proj |
| LoRA Alpha | 128 |
| LoRA Dropout | 0.05 |
| R Param | 128 |
Best Alternatives to Zephyr 7B Ipo 0K 15K I1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen Megumin | 0K / 0.1 GB | 5 | 1 |
| Uk Fraud Chatbot Llama2 | 0K / 0.4 GB | 5 | 0 |
| ...s 25 Mistral 7B Irca DPO Pairs | 0K / 0.1 GB | 5 | 0 |
| Qwen1.5 7B Chat Sa V0.1 | 0K / 0 GB | 5 | 0 |
| Hr Other 7B Lora | 0K / 0.2 GB | 30 | 0 |
| Deepseek Llm 7B Chat Sa V0.1 | 0K / 0 GB | 5 | 0 |
| Deepthink Reasoning Adapter | 0K / 0.2 GB | 4 | 3 |
| ... Days Of Sodom LoRA Mistral 7B | 0K / 0.2 GB | 5 | 0 |
| Mistral 7B Instruct Sa V0.1 | 0K / 0 GB | 5 | 0 |
| ...4a1 L512 R16a32 20241116091554 | 0K / 0 GB | 20 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than DUAL-GPO/zephyr-7b-ipo-0k-15k-i1 .
Rank the Zephyr 7B Ipo 0K 15K I1 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124