Mistral 7B OpenOrca Lora Benchmarks
ARC: 61.95-35.7%
HellaSwag: 83.62-12.3%
MMLU: 64.16-25.8%
TruthfulQA: 42.74-27.6%
WinoGrande: 79.08-9.6%
GSM8K: 17.29-81.2%
nn.n% — How the model compares to the GPT-4.
Mistral 7B OpenOrca Lora Parameters and Internals
| LLM Name | Mistral 7B OpenOrca Lora |
| Repository | Open on 🤗 |
| Model Size | 7b |
| Required VRAM | 0.3 GB |
| Updated | 2024-07-27 |
| Maintainer | uukuguy |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | llama2 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|k_proj|q_proj|up_proj|gate_proj|o_proj|v_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 64 |
Best Alternatives to Mistral 7B OpenOrca Lora
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| CodeAstra 7B | 0.3 | 0K / 0 GB | 651 | 2 |
| ...Sql Flash Attention 2 Dataeval | 0.3 | 0K / 1.9 GB | 754 | 2 |
| ...V0.1 Llm On Ray Deepspeed Lora | 0.3 | 0K / 0 GB | 212 | 0 |
| ...al 7B Instruct V0.3 1719344430 | 0.3 | 0K / 3.5 GB | 86 | 0 |
| Lora Adapted Mistral 7B | 0.3 | 0K / 0 GB | 139 | 0 |
| Qwen1.5 7B Chat Sa V0.1 | 0.3 | 0K / 0 GB | 5 | 0 |
| ...al 7B Instruct V0.3 1719350528 | 0.3 | 0K / 0.9 GB | 80 | 0 |
| ...al 7B Instruct V0.3 1719341325 | 0.3 | 0K / 1.7 GB | 74 | 0 |
| ...al 7B Instruct V0.3 1719297750 | 0.3 | 0K / 0.4 GB | 76 | 0 |
| ...al 7B Instruct V0.3 1719301256 | 0.3 | 0K / 0.9 GB | 77 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than uukuguy/Mistral-7B-OpenOrca-lora .
Rank the Mistral 7B OpenOrca Lora 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501