Deacon 34B Qlora Adapter Benchmarks
ARC: 64.85-32.7%
HellaSwag: 85.56-10.2%
MMLU: 76.38-11.7%
TruthfulQA: 56.21-4.7%
WinoGrande: 83.11-5%
GSM8K: 62.24-32.3%
nn.n% — How the model compares to the GPT-4.
Deacon 34B Qlora Adapter Parameters and Internals
| LLM Name | Deacon 34B Qlora Adapter |
| Repository | Open on 🤗 |
| Model Size | 34b |
| Required VRAM | 0.1 GB |
| Updated | 2024-07-26 |
| Maintainer | KnutJaegersberg |
| Model Files | |
| Model Architecture | Adapter |
| License | other |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Deacon 34B Qlora Adapter
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| 30B 2e | 0.2 | 0K / 0 GB | 6 | 0 |
| Airoboros 34B 3.3 Peft | 0.2 | 0K / 0.5 GB | 0 | 1 |
| Bagel 34B V0.5 Peft | 0.2 | 0K / 0.5 GB | 0 | 1 |
| ...34B 200K AEZAKMI RAW 2301 LoRA | 0.2 | 0K / 0.5 GB | 0 | 1 |
| 34B Beta Onc V1 | 0.2 | 0K / 0 GB | 6 | 1 |
| ...pmoney 34B 200K Chat Evaluator | 0.2 | 0K / 2 GB | 0 | 34 |
| ...awrr V1 Run1 Experimental LoRA | 0.2 | 0K / 0.5 GB | 4 | 1 |
| ...awrr1 LORA DPO Experimental R2 | 0.2 | 0K / 0.1 GB | 4 | 1 |
| Yi 34B 200K MiniOrca Adapter | 0.2 | 0K / 0.1 GB | 0 | 1 |
| Yi 34B Alpaca Cot Lora | 0.2 | 0K / 0.1 GB | 0 | 15 |
Note: green Score (e.g. "73.2") means that the model is better than KnutJaegersberg/Deacon-34b-qlora-adapter .
Rank the Deacon 34B Qlora Adapter 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