Arxiv:1910.09700 Adapter Base model:adapter:beomi/llama... Base model:beomi/llama-3-open-... Finetuned Lora Peft Region:us Safetensors
Adapter Test Benchmarks
ARC: 55.72 vs 96.7 (so35)-42.4%
HellaSwag: 74.92 vs 95.3 (gpt4)-21.4%
MMLU: 53.78 vs 88.3 (so35)-39.1%
TruthfulQA: 46.03 vs 59 (gpt4)-22%
WinoGrande: 72.53 vs 87.5 (gpt4)-17.1%
GSM8K: 22.29 vs 96.4 (so35)-76.9%
LLME Score: 0.23102
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)
Adapter Test Parameters and Internals
| LLM Name | Adapter Test |
| Repository 🤗 | https://huggingface.co/khKim/adapter_test |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.1 GB |
| Updated | 2024-08-16 |
| Maintainer | khKim |
| Model Files | |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|v_proj |
| LoRA Alpha | 128 |
| LoRA Dropout | 0.1 |
| R Param | 128 |
Best Alternatives to Adapter Test
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 5 | 0 |
| FatDPOv2LoRA | 0K / 0.8 GB | 3 | 1 |
| Llama3 C1 Full | 0K / 0.2 GB | 13 | 0 |
| Vortex2 | 0K / 4.4 GB | 8 | 0 |
| Fireball 3.1 8B ORPO | 0K / 16.1 GB | 6 | 2 |
| FineLlama3.1 8B Instruct Lora | 0K / 0.2 GB | 0 | 1 |
| Llama3 8B Instruct Code | 0K / 0.2 GB | 9 | 1 |
| Llama 3 8B Claudstruct V3 | 0K / 0.1 GB | 9 | 0 |
| Llama 3 8B Instruct 80K QLoRA | 0K / 2.2 GB | 0 | 24 |
| Llama 3 8B Claudstruct V1 | 0K / 0.1 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than khKim/adapter_test .
Rank the Adapter Test 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? 38149 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110