Model Card on HF 🤗: https://huggingface.co/SC56/Mistral-7B-orca-dpo-4h
Mistral 7B Orca DPO 4h Benchmarks
ARC: 73.38 vs 96.7 (so35)-24.1%
HellaSwag: 88.73 vs 95.3 (gpt4)-6.9%
MMLU: 64.97 vs 88.3 (so35)-26.4%
TruthfulQA: 71.65 vs 59 (gpt4)21.4%
WinoGrande: 84.29 vs 87.5 (gpt4)-3.7%
GSM8K: 69.52 vs 96.4 (so35)-27.9%
LLME Score: 0.14063
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)
Mistral 7B Orca DPO 4h Parameters and Internals
| LLM Name | Mistral 7B Orca DPO 4h |
| Repository 🤗 | https://huggingface.co/SC56/Mistral-7B-orca-dpo-4h |
| Model Size | 7b |
| Required VRAM | 0.1 GB |
| Updated | 2025-09-13 |
| Maintainer | SC56 |
| Model Files | |
| Model Architecture | Adapter |
| License | cc-by-4.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|o_proj|down_proj|v_proj|k_proj|gate_proj|q_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Mistral 7B Orca DPO 4h
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 | 6 | 0 |
| Zephyr 7B Ipo 0K 15K I1 | 0K / 0.7 GB | 11 | 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 | 7 | 0 |
| Mistral 7B Instruct Sa V0.1 | 0K / 0 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than SC56/Mistral-7B-orca-dpo-4h .
Rank the Mistral 7B Orca DPO 4h 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? 51352 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124